WO2025003618A1 - Procede et dispositif pour inspecter des recipients selon au moins deux directions d'observation differentes en vue de classer les recipients - Google Patents
Procede et dispositif pour inspecter des recipients selon au moins deux directions d'observation differentes en vue de classer les recipients Download PDFInfo
- Publication number
- WO2025003618A1 WO2025003618A1 PCT/FR2024/050859 FR2024050859W WO2025003618A1 WO 2025003618 A1 WO2025003618 A1 WO 2025003618A1 FR 2024050859 W FR2024050859 W FR 2024050859W WO 2025003618 A1 WO2025003618 A1 WO 2025003618A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- container
- images
- class
- defect
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Definitions
- Title of the invention Method and device for inspecting containers according to at least two different observation directions with a view to classifying the containers.
- the present invention relates to the technical field of the inspection of transparent or translucent containers such as, for example, glass bottles, jars or flasks or even plastic preforms or bottles (including returnable containers) for the purpose of their quality control in order to detect and identify possible defects likely to affect these containers.
- transparent or translucent containers such as, for example, glass bottles, jars or flasks or even plastic preforms or bottles (including returnable containers) for the purpose of their quality control in order to detect and identify possible defects likely to affect these containers.
- the subject of the invention finds particularly advantageous applications for analyzing physical characteristics of containers with a view to determining the presence or absence of defects and identifying conforming optical singularities such as decorations, functional reliefs, mold joints or non-conforming optical singularities corresponding to defects, such as for example surface defects, such as folds or crevices, internal defects in the material, such as cracks, inclusions, or bubbles, dimensional defects such as deformations.
- defects such as for example surface defects, such as folds or crevices, internal defects in the material, such as cracks, inclusions, or bubbles, dimensional defects such as deformations.
- the manufacturing process comprising melting the glass and then transporting it to forming units is implemented by means of a manufacturing installation comprising a melting furnace, a feeder for supplying molten glass to a forming machine generally of the type designated by IS machine.
- the containers which have just been formed by the forming machine are placed successively on an output conveyor to form a row of containers.
- the containers are transported in a row by a conveyor in order to transport them successively to different processing stations.
- the formed containers are brought into an annealing furnace, which raises their temperature and then cools them in a controlled manner so that disappear the thermal stresses created by the forming process.
- patent application WO2021/209704 describes an inspection station comprising at least six imagers (typically 6, 12, 18 or 24) forming images and having an optical axis directed towards the inside of the inspection zone, being mounted so that their optical axes are distributed around the central axis of the containers by choosing their azimuth angles between 0 and 360° relative to the translation direction, so that all the points of the circumference of the edge of the containers are represented in at least one image acquired during the crossing of the inspection zone by the edge of the container.
- imagers typically 6, 12, 18 or 24
- the containers are also illuminated by at least twelve projectors each having a beam direction, tangent to a cylinder centered on the central axis of the container, and the illumination beam directions are distributed in azimuth.
- Such a device allows for multiple beam directions and multiple observation directions to ensure the detection of glazes that reflect incident light toward the imagers.
- Patent application WO2023/052732 describes an inspection device provided on each side of the conveyor with a series of three cameras opposite which a light panel is arranged.
- Patent application WO2021/213864 proposes a method for more reliably inspecting containers transported by a conveyor on a line, in particular a bottling line.
- the containers are transported to at least a first inspection unit and a second inspection unit, each comprising a transmitter and a receiver.
- the inspection units can inspect the containers using white light, laser light, high-frequency electromagnetic waves, gamma rays and/or X-rays as transmitters.
- the containers are transported between the transmitter and a receiver such as a camera making it possible to acquire, with the first inspection unit, first measurement data and with the second inspection unit, second measurement data.
- the first measurement data and the second measurement data are combined to form common input data for an evaluation unit based on artificial intelligence and providing as output, an inspection result, such as a filling level.
- this document describes the detection of the filling level of containers by combining X-ray imaging and inspection with an infrared light source. This document specifies that such a method can be used to also check the side wall, the bottom, the mouth, the contents of the container such as for example contamination by foreign bodies or product residues.
- the result of the inspection can also be defects, such as damage to the containers, in particular cracks and/or glass shards.
- patent application WO2021/213864 does not provide any teaching for detecting or identifying with certainty, in particular, appearance defects. Regardless of the obligation to detect these defects, there appears to be a need to identify exactly the nature of the appearance defects in order to identify critical appearance defects compared to other defects that may be considered non-critical.
- An erroneous identification of a type of defect on a container may lead to the rejection of this container when a correct identification of this defect would have made it possible to identify the container as good, or to the non-rejection of a critical defect generating a serious non-quality, or to an inappropriate correction of the manufacturing process which may go so far as to destabilize it, or even to the failure to take into account a process error because if a system generates false alarms too frequently, the operator may end up no longer taking into account correctly the indications of the inspection system.
- a container inspection device making it possible to increase the reliability of detection, in particular to be able to reliably distinguish decorative elements by in relation to contamination or soiling.
- the device comprises a light source emitting in spatially separated zones, radiation with different wavelength and intensity ranges. This light source illuminates the container to be examined and a colour camera is configured to detect the radiation emitted by the source and having passed through the container.
- the device also comprises an evaluation device which is designed to analyze the intensity image to determine pixels or regions therein which have an intensity different from that of their neighborhood to deduce therefrom the presence of a light-absorbing defect such as dirt.
- the evaluation device makes it possible to analyze the color images to determine pixels or regions which have a color different from that of their neighborhood to deduce therefrom the presence of light-refracting elements such as decorative elements.
- the evaluation unit detects the presence of a decorative element.
- the evaluation unit can also identify structures that cause local color contrast but virtually no local brightness contrast or only low local brightness contrast. For example, chips in glass or water droplets can cause such local color contrast, while light shining through can radiate through these areas substantially without loss of brightness.
- Such an inspection device makes it possible to distinguish decorative elements from dirt or contamination.
- light-refracting defects are distinguished from light-absorbing defects.
- this inspection device does not make it possible to distinguish light-refracting defects from each other, as indicated by this application in particular with regard to glass inclusions and water droplets.
- document JP 4886830 is also known, which describes the inspection of a rotating bottle to reveal a crevasse. This document proposes to process images, but remains silent on the image processing methods to be used. Document WO 2018/061196 has a teaching close to this document, and it has the same shortcomings.
- Document EP 3180135 is also known, which describes an acquisition of images in stereoscopy to remove the parts of images visible in the two stereoscopic images.
- the present invention aims to remedy the drawbacks of the prior art by proposing a method for controlling the quality of containers, designed to achieve more effective detection of defects by ensuring their identification in a more reliable and certain manner in order to optimize the sorting or classification of containers.
- An object of the invention is to propose a control method making it possible to classify each container according to at least one class taken from a list of classes comprising in particular a class of absence of defect, a class of presence of defect, a class relating to a normal optical singularity and/or a class relating to an abnormal optical singularity.
- the subject of the invention relates to a method for inspecting containers made of transparent or translucent material (typically glass or plastic, the person skilled in the art being able to identify the containers considered to be transparent or translucent) with a view to classifying a container, the method comprising; a use phase comprising:
- a single deep learning model is here configured to receive at least two images as input and output a class membership for the container, based on the two images.
- the deep learning model may for example comprise a number of inputs chosen to receive at least two images as input (or processing results of these two images if processing or preprocessing is performed on the images).
- the images are images of at least one portion of a container.
- it may be an image acquired by a sensor, a portion of an image acquired by a sensor, an image of an entire container, an image of a part of a container.
- the at least two images target the same portion.
- the deep learning model can be an artificial neural network (typically a neural network with convolution layers) or a transformer-type model.
- the number of input neurons can correspond to the cumulative number of pixels in the two images.
- multi-view data fusion is implemented before classification.
- the multi-view fusion can be done by means of image concatenation techniques, channel concatenation, pixel-to-pixel addition, or on vectors representing information of the images and by adding the vectors, by performing an element-by-element multiplication of the vectors or by concatenation of the vectors.
- the fusion operation aims to preserve the useful information of the data to be merged while excluding the redundant information. This operation can be performed at any time in the defect recognition process and can occur several times.
- the inventors have noticed that certain defects seen from a particular angle have a signature that does not allow the type to be determined with certainty.
- the shape of the image of the defect under a single observation direction is not always sufficiently characteristic, due to different optical phenomena.
- the defect is not entirely visible in any image and/or the defect is deformed by refraction of light through the wall of the container and/or its appearance is different in photometry and geometry according to different observation directions.
- the deep learning model may be preceded by one or more processing modules individually processing each image, the results of these processings then being provided as input to the deep learning model.
- the method comprises:
- the method comprises the provision of an inspection system configured to acquire images of the same portion of a container according to at least two different observation directions and according to at least one modality taken from the list of the following modalities: absorption, birefringence, refraction, reflection, infrared radiation.
- each portion of container is classified according to at least one class taken from a list of classes comprising at least one class of absence of defect in the portion and one class of presence of defect in the portion.
- each portion of container is classified according to at least one class taken from a list of classes comprising at least one class including the presence in the portion of at least defects such as in particular, trapezium, inclusion, bubble.
- each portion of container is classified according to at least one class taken from a list of classes comprising at least one class including the presence in the portion of at least one singularity such as a marking, a mold seal, a notch, a thread, an impression, a stitch, a handle, a counter ring.
- the method comprises the acquisition, for each container having a central axis, of at least four images of at least one same portion of a container according to four different observation directions and according to at least the first modality, the observation directions being distributed around the central axis two by two according to an azimuth angle of at least 45°.
- At least one sorting characteristic is compared to a rejection criterion, the sorting characteristic and the rejection criterion rejection being dependent on the membership class to decide whether or not the container is compliant, the sorting characteristic being calculated on at least one image of the container according to a modality.
- a step is implemented for taking into account at least one identified defect in order to deduce adjustment information for at least one control parameter of a container manufacturing installation.
- the deep learning model associates a confidence score with the ranking of containers that are part of an inspected production
- Accounting may involve the implementation of time statistics (defect frequencies). For example, time statistics may be provided for a sliding window in order to determine trends (emergence/occurrence of defects, drift in the process, etc.).
- the invention also proposes a method for training a deep learning model for inspecting containers made of transparent or translucent material with a view to classifying a container, the method comprising a construction phase comprising:
- a learning set comprising recordings each composed of at least a first and a second image of the same portion of container according to two different observation directions and according to at least one modality;
- the deep learning model determining at least one membership class for said portion from a list of classes.
- This learning method can be configured to obtain models according to all the modes of implementation of the inspection method defined above.
- the method comprises providing at least one deep learning model having been trained on a learning set comprising recordings each composed of at least two images of the same portion of container according to observation directions different by at most 5° during the acquisition of the images.
- the method comprises providing at least one deep learning model having been trained on a training set comprising recordings each composed of images of the same portion of container according to different directions and modalities.
- the invention also proposes a method comprising a phase of construction of the learning method defined above to obtain a deep learning model, and a phase of inspection of the inspection method defined above using the deep learning model of said construction phase.
- the image records are ordered according to a determined sequence while during the use phase, the image records are ordered according to a sequence identical to the sequence of the construction phase.
- the images are ordered according to, for example, a direction of observation and a modality specific to each image, in an identical manner within each recording.
- a recording therefore comprises a set images for a container, captured by a device similar to the inspection device.
- Also by sequence, we mean an ordered series of elements, the order being able to be fixed by the directions and the modalities.
- the invention also provides a device for inspecting containers made of transparent or translucent material leaving a manufacturing or recovery installation with a view to classifying the containers in relation to defects, the device comprising:
- an inspection system comprising at least one camera arranged to recover light or radiation (for example infrared) coming from at least one portion of a container and configured to acquire images of the same portion of a container according to at least two different observation directions and according to at least one first modality;
- light or radiation for example infrared
- an information processing unit connected to the inspection system and comprising a deep learning model, the deep learning model determining at least one membership class for said portion from a list of classes, the deep learning model receiving as input, for each container, a recording of at least two images of at least one portion of the container according to the first modality and according to two different observation directions, the deep learning model, for each container, analyzing this recording to determine the membership of this portion of container, to a result class from the list of classes.
- This device can be configured to implement the inspection method as defined above.
- the invention also proposes a device configured for implementing the learning method defined above.
- the invention also proposes a deep learning model obtained by the learning method defined above.
- Various other characteristics emerge from the description given below with reference to the attached drawings which show, by way of non-limiting examples, embodiments of the subject of the invention.
- Figure 1 shows an exemplary embodiment of an installation for manufacturing containers inspected by an inspection device according to the invention.
- Figure 2 is a schematic view illustrating an exemplary embodiment of an inspection device according to the invention using two cameras adapted, for example, to simultaneously take two images of a container from two different observation directions.
- Figure 3A is a schematic top view showing the taking of successive images, by a camera, under a first observation direction of a container moving in translation.
- Figure 3B is a schematic top view showing the taking of images, by a camera, under a second observation direction of a container moved in translation relative to its position illustrated in Figure 3A.
- Figure 3C is a schematic top view showing the taking of images, by a camera, under a third direction of observation of a container moved in translation relative to its position illustrated in Figure 3B.
- Figure 4 is a schematic view illustrating an exemplary embodiment of an inspection device according to the invention using two cameras adapted to obtain from each three analysis images according to three different modalities, in order to constitute a recording of analysis images comprising at least 6 container images.
- Figure 5 is a schematic view illustrating yet another exemplary embodiment of an inspection device according to the invention adapted to simultaneously take three images of a container from three different observation directions and analyzed by four neural networks which collaborate to classify the container.
- Figure 6 is a schematic view illustrating yet another example of an embodiment of an inspection device according to the invention using two cameras adapted to simultaneously take two images of a container from two different observation directions and analyzed by algorithms for detecting image singularities and then by a neural network which classifies the container.
- Fig. 7A shows an arrangement of a plurality of cameras arranged at different elevations.
- Figure 7B corresponds to the arrangement of Figure 7A but where the different azimuths are visible.
- Figure 8A is a photograph of a container in which a defect is visible.
- Figure 8B is a photograph of the container of Figure 8A in which the defect is no longer visible.
- Figure 9A shows a photograph of another container in which a defect is visible.
- Figure 9B is a photograph of the container of Figure 9A in which the defect is still visible, but with a different appearance.
- Figure 9C shows how the cameras used to obtain the images of Figures 9A and 9C are arranged.
- Fig. 10A is a photograph of yet another container on which a two-part defect is visible.
- Figure 10B is a photograph of the container of Figure 10A in which the defect remains visible with a different appearance.
- FIGS 1 and 2 illustrate a device 1 according to the invention for inspecting containers 2 leaving an installation 3 of all types known per se.
- the installation 3 provides transparent or translucent containers 2 such as, for example, bottles, pots, flasks, syringes, ampoules or preforms.
- a container 2 has a central axis R, considered as an axis of symmetry, or even an axis of symmetry of revolution.
- These containers 2 can be made of different materials such as glass, plastic or renewable raw material such as wheat, sugar cane or corn for example. These containers 2 can be filled or empty.
- the installation 3 thus ensures the manufacture of the containers 2 or even their decoration or dressing, filling and closing. It should be noted that the installation 3 is capable of manufacturing the new containers 2 from raw or recycled materials, or of reconditioning recovered containers. According to a preferred example of implementation, the installation 3 is a forming installation from which empty glass containers emerge.
- the installation 3 comprises a production computer 4 for supervising the various functionalities of the installation 3 during the manufacture of the containers.
- the production computer 4 is typically for a glass container forming machine, a sequencer which controls pneumatic or motorized actuators as well as valves controlling the circulation of the cooling air or the blowing pressure for the manufacturing molds.
- the containers 2 are taken in charge by an outlet conveyor 5 to form a line of containers, being in the example illustrated, placed successively on the outlet conveyor.
- the containers 2 are transported in line by the conveyor 5 in a direction of movement F in order to convey them successively to different treatment and/or control stations and in particular to an annealing arch 6 (i.e. a treatment station) and to the inspection device 1 according to the invention (i.e. a control station).
- the direction of movement F of the containers 1 is established according to a rectilinear trajectory of horizontal axis X of a direct orthonormal reference frame X, Y, Z comprising a vertical axis Z perpendicular to the horizontal axis X and a transverse axis Y perpendicular to the vertical axis Z and to the horizontal axis X, and the axes X and Y being in a plane parallel to a conveying plane Pc of the containers which is considered to be horizontal.
- the inspection device 1 according to the invention can also, in a variant, be installed downstream of the installation 3 and upstream of the annealing arch 6, when the hot containers 2' are transported in line by the conveyor 5' towards the arch. In other words, the inspection device 1 according to the invention can be installed upstream or downstream of any treatment of formed containers and transported according to the movement F.
- the inspection device 1 aims to implement a method for detecting for each container 2 moving in translation, whether the container has a defect and to identify for a container having a defect, a type of defect from a family of possible defects.
- the inspection device 1 comprises an inspection system 7 visible in FIG. 2 and comprising at least one camera Ci (Cl, C2,...Ci,...Cn, with i ranging from 1 to n) arranged to recover light or radiation (for example infrared) coming from at least one portion of a container 2 and configured to acquire images of the same portion of a container according to at least two different observation directions DI, D2 and according to at least one first inspection method.
- Ci Camera
- each camera Ci comprises in a conventional manner (FIGS. 3A to 3C), an optical lens B having an optical center O and an optical axis A, allowing the formation of an optical image on a photoelectric sensor E, linear or matrix, generally flat, positioned in the focal plane of the lens.
- the images acquired by the cameras Ci are transmitted to an electronic information processing unit 9 forming part of the inspection device 1, but which may possibly be remote.
- This electronic information processing unit 9 is a computer system of all types comprising computers, external peripherals (display unit, storage unit, keyboards, connection to different factory networks, connection to cameras, etc.), equipped with programs implementing in particular image processing algorithms, databases, etc.
- This information processing unit 9 is connected to the production computer 5 in order to receive, if necessary, from the production computer (or even from other peripherals), manufacturing information for an association with the containers 2, their images and their detected defects with this manufacturing data.
- the manufacturing information can be time information, mold or molding cavity numbers, etc.
- received time information makes it possible to associate the containers 2, their images and their detected defects, with the mold number or the forming cavity or with a time stamp or with an individual identifier.
- the operation of the inspection system 7 is synchronized with the operation of the forming cavities of the containers, in particular in the case where it is installed between the forming installation 3 and a processing station such as the annealing arch 6.
- this information processing unit 9 transmits to the production computer 4 the identified defects and the measurements made, so that the production computer can automatically deduce adjustment information for at least one control parameter of the installation 3 or processing 6. Such an adjustment of the control parameters is carried out manually or automatically.
- the information processing unit 9 is connected to an ejector to control the ejection of containers identified as defective, and/or to a display unit to present to an operator the identified defects and the images of the containers.
- the inspection system 7 is configured to recover, by at least one camera, the light coming from the container 2 in order to acquire images of the same portion of a container according to at least two different observation directions DI, D2, D3, ... Dj and according to at least one inspection method.
- each observation direction D1, D2, D3 corresponds to the straight line passing through the center optical O of the camera and the center T of the portion P of the container 2 placed in the field of observation of the camera.
- the different observation directions D1, D2, D3 are produced for different positions of the container in the observation field of the camera.
- the containers 2 are moved along a rectilinear trajectory represented by the arrow F so as to pass in front of a fixed camera C1 positioned to inspect the body of a container.
- the center T of the portion P of the container 2 observed by the camera corresponds to the central axis R of the container.
- the camera C1 takes an image ICI 1 of the container 2 when the direction of observation D1 forms an angle alpha with the optical axis A.
- FIG. 3A the camera C1 takes an image ICI 1 of the container 2 when the direction of observation D1 forms an angle alpha with the optical axis A.
- the movement of the container leads to its positioning in a position for which the direction of observation D2 corresponds to the optical axis A.
- the camera C1 takes an image IC12 of the container 2 when the direction of observation D2 coincides with the optical axis A.
- the continued movement of the container leads to its positioning in a position for which the direction of observation D3 has passed the optical axis A and forms an angle alpha with the optical axis A (FIG. 3C).
- the camera C1 takes an image IC13 of the container 2 when the direction of observation D3 forms an angle alpha with the optical axis A.
- the direction of observation is modified by the relative movement between the container 3 and the camera.
- the camera is fixed while the container is mobile.
- the object of the invention also applies to a fixed container and a mobile camera.
- the different observation directions D1, D2 are produced by cameras having observation directions of the container which are different at the time of acquisition of the images.
- two cameras C1, C2 are positioned so that in a vertical plane, parallel to the central axis R, the optical axes A of the cameras form between them an elevation angle alpha determined so that if the observation directions correspond to the optical axes, the observation directions are offset by an angle alpha.
- the cameras may be envisaged to distribute the cameras in the azimuth plane (plane parallel to the conveying plane, as will be visible with reference to figures 7 A and 7B described below) so that the optical axes A of the cameras form between them an azimuth angle alpha determined so that if the observation directions correspond to the optical axes, the observation directions are offset by an angle alpha.
- two observation directions DI, D2, D3...Di have different observation directions if these two observation directions are offset by at least 5°.
- this inspection system provides the information processing unit 9 with images of the same portion of a container according to at least two different observation directions and according to at least one first inspection method.
- the same portion it is meant that an overlap of the views is possible between the images.
- An inspection modality corresponds to a type of interaction of light with the wall of the containers and with the defects to be identified.
- the inspection system 7 is configured to acquire images of the same portion of a container according to at least two different observation directions and according to at least one modality taken from the list of the following modalities: absorption, birefringence, refraction, reflection, infrared radiation.
- an inspection modality is called absorption.
- This modality mainly highlights the absorption of the light passing through by the wall of the container passed through, but also refraction effects such as shadows on the edges of the container or refracting defects or thickness variations.
- Some defects have an absorbent character, totally or partially absorbent. These defects thus appear opaque or dark when they are seen in transmission, that is to say that the light passing through a wall of flawless glass undergoes a so-called normal absorption corresponding to the color and thickness of the material constituting the container, assumed to be homogeneous with the glass wall.
- the absorbent defects present a local anomaly with an absorption sometimes lower (bubble or thin) but generally higher than the normal absorption.
- Such defects include in particular inclusions in the glass, in particular of ceramic or metals, and/or dirt (grease, ...) on the glass. But such defects also include certain glazes (cracks) which would be oriented in the glass so as to block the inspection light, mainly by the fact that the inspection light is then reflected in a direction which is not seen by the camera. Due to the limitation in size of the light source, shadows appear in the image due to refraction on the outer edges of the silhouette of the container. Shadows do not generally reveal defects. Certain forms of shadows reveal defects in the glass distribution. Some refracting defects have a particular signature at the edge of the container silhouette and another signature in the center. They will therefore be distinguished by observation from different viewing angles.
- birefringence Another inspection method is called birefringence.
- This method mainly involves a modification of the polarization state of the light passing through the wall of the container by a so-called stress defect, which gives the glass a birefringence property.
- Some defects have a birefringent character. Thus, some defects result in the presence of residual mechanical stresses in the material (sometimes called internal mechanical stresses or, in particular in English, "stress").
- a birefringent or stress defect such as an inclusion of foreign bodies (ceramic, metal, "devitrified glass) causes a modification of the polarization state, i.e. a polarization phase shift between two components of the electric field or a modification of the direction of linearly repolarized light.
- refraction is another inspection method.
- This method mainly implements a modification of the direction of propagation of the light passing through the wall of the container by a refracting defect, due to an angle between the dioptric surfaces crossed and/or a difference in refractive index.
- Each surface is an air/glass or glass/air interface, therefore a dioptric surface that refracts the light passing through it.
- the surfaces of the walls are substantially parallel and the refraction does not cause any visible deviation of the light rays passing through the container.
- a so-called refracting defect is a defect that locally causes abnormal refraction, mainly when the defect manifests itself by slope differences between the surfaces or dioptric surfaces crossed by the wall(s).
- Refractive defects are defects that are mainly detectable by the refraction anomalies they generate, especially in a through-light inspection.
- surface defects folds, rivers,
- glass distribution defects bubbles, thin, compression ring
- trapezoids and fins are generally classified as refractive defects. It should be noted that trapezoids and fins generally cause such strong refractions that these defects are generally clearly visible also in absorption images.
- Glazes are very narrow cracks, of different shapes and lengths and different orientations in the material. Glazes behave like diopters reflecting light. Their detection consists of illuminating a part of the container according to one or more directional beams having specific angles of incidence on the illuminated portion of the container. The direction of the light reflected by a glaze is specific to the shape and orientation of the glaze, and the image by a camera receiving or not the reflected light allows the detection of glazes. In other words, the direction of observation is a characteristic of the glaze. According to this method and in the example of patent WO 2021/209704, a A large number of cameras are arranged around the container with observation directions distributed in azimuth and elevation.
- the invention is not limited to these modalities. It can be applied for example in the case of a pure reflection modality, according to which a light source is designed to illuminate the surface of a portion of container, the surface reflecting the light in the direction of the camera. The image is then mainly constituted by the reflected light, and we observe as potential defect, either deformations of geometry of the surface, or of its reflectivity, or the appearance of a reflection outside the normal contour of the surface.
- Another inspection method is called infrared radiation.
- This inspection method without using a light source to illuminate the containers, aims to inspect the still hot containers, typically made of glass, at the end of their manufacture and emitting, given their temperature, infrared radiation depending on the volume (in other words, the thickness) and/or the temperature of the material constituting the containers.
- So-called infrared cameras are used, equipped with image sensors sensitive to the infrared radiation emitted by the still hot containers, the temperature of which is greater than 300°C.
- the sensors used in this type of modality have a length sensitivity spectrum adapted according to the cases of use, for example in near infrared (SWIR or NIR) and/or mid infrared (MWIR).
- a defect modifying the emissivity, therefore the image of the infrared radiation of a container can be linked to an accumulation of material at a specific location corresponding for example to an excess thickness of the wall or to a trapezoid or swing defect (defect of a glass wire inside the container and connected by its ends to the inner wall).
- the observation of the infrared radiation of hot containers according to at least two different observation directions allows for example that the neural network (or the model used) takes into account the directional emissivity and/or the depth of the defect to determine the class to which it belongs.
- the inspection of the containers 2 according to one and/or the other of these inspection methods can be carried out using various configurations of the inspection system 7.
- the inspection system is configured to acquire images in order to obtain images according to at least one modality and advantageously images relating to several modalities. It should be noted that depending on the inspection system 7 used, the images according to these modalities can be obtained directly from the acquired images or from calculations or processing.
- a first simple method is to produce on the light source a uniform intensity and non-polarized illumination in an active portion.
- a second solution for obtaining the absorption image is to use a linearly or circularly polarized uniform intensity light source and to produce the image by means of a camera without any polarizing filter between the container and the camera.
- the intensity uniformity of the light source can be perfect, that is to say that the intensity is constant over the entire active zone of a flat and extended light source emitting diffuse light.
- the uniformity can also be local, in particular when the glass of the containers is tinted, it can be provided that a region of the source illuminating the neck where the glass wall is thicker, emits a stronger uniform intensity, while a region illuminating the body of the container where the wall is thinner emits a weaker uniform intensity.
- the intensity of a light source which generates, as described in document FR 2794241, a continuous spatial variation of intensity slower than that observed in the vicinity of a defect is also considered to be uniform or relatively uniform, such that an image analysis algorithm which compares the pixels to their neighbors to detect rapid local variations in intensity as defects does not detect the slow variations in intensity emitted by the source.
- Another solution for obtaining the absorption image is to use a linearly or circularly polarized monochrome intensity uniform light source and to produce a composite polarimetric image using a polarimetric camera, and to calculate the absorption image from at least two partial polarimetric images corresponding to observations through two linear filters with analysis directions at 90° to each other.
- Another solution for obtaining an absorption image is to produce the illumination using a source exhibiting variations in a polarization characteristic with the intensity remaining relatively uniform and to acquire a composite image containing at least 2 to 4 partial images using a polarimetric camera and to calculate an absorption image from 2 to 4 partial images taken through polarization analyzers at 90° to each other.
- a first simple method is to produce on the light source, a uniform monochrome illumination linearly polarized in a determined direction, in an active portion.
- the image is acquired either by a black and white camera in front of which is placed a linear polarization analyzer whose direction is orthogonal to the determined direction, or by a polarimetric camera whose pixels of the partial image corresponding to the analysis are taken into account through a linear filter orthogonal to the determined direction.
- the value of the pixels of the birefringence image is then almost zero except in the presence of a stress defect. When light passes through a stress defect, the measured/received light intensity obtained depends on the direction and intensity of the stresses.
- a second method for obtaining a birefringence image is to produce on the light source, a uniform monochrome illumination circularly polarized in a given direction in an active portion.
- the image is acquired with a black and white camera in front of which is placed a 1/4 wave retardation plate then a linear polarization analyzer.
- the value of the pixels of the birefringence image is then almost zero except in the presence of a stress defect.
- the outgoing light intensity depends on the intensity of the stresses but not on the direction of the stresses.
- a third method of obtaining a birefringence image is to produce on the light source, a uniform monochrome illumination polarized linearly in a single direction or circularly in a single sense in an active portion.
- the image is acquired by a polarimetric camera in front of which is optionally placed a 1/4 wave delay plate delivering a composite image.
- a birefringence quantity is calculated which depends on the polarization phase shift between the Ex and Ey components of the electric field and which is a measure of the stress.
- a person skilled in the art will be able to find the calculation formulas from the Mallus equation and the Stockes formalism.
- the polarization phase shift can be calculated to obtain as pixel values in the birefringence image, a value which depends on the intensity of the stresses but preferably not on the direction of the stresses, the detection is therefore isotropic and proportional to the stresses.
- the polarization phase shift can be measured between 0 and 90° or even between 0 and 180°. This method also makes it possible to calculate an absorption image with the composite image delivered by the same polarimetric camera, by calculating each pixel as explained previously.
- US4606634 describes a type of refracting defect detection that involves modifying the “spectrum angular" of an extended light source.
- a light source of variable dimension for example a luminous disk of variable diameter, is at the focus of a converging projection lens.
- an enhanced contrast is obtained on the refracting objects, this contrast being able to be increased by reducing the angular spectrum, which is produced by reducing the diameter of the luminous disk.
- a second set of methods for obtaining a refraction image consists in varying spatially along the emitting surface of an extended light source, such as a light panel, a property of the light emitted by the source that the camera can distinguish.
- an extended light source such as a light panel
- its intensity was initially used.
- At least one image is acquired with an intensity-sensitive camera, therefore a priori monochrome, delivering monochrome images.
- the intensity of light emitted by each unit of light emitting surface varies spatially according to a spatial variation law in one or two dimensions.
- these inspection methods adapted for detecting refracting defects implement illumination devices that provide light that is sometimes called "structured", that is to say having an emitting surface, generally two-dimensional, which has variations or patterns of intensity.
- a third set of methods for obtaining a refraction image consists in varying spatially along the emitting surface, as a property of the light emitted by the source, a polarization property, a color property and/or a phase property.
- documents WO2020/244815 and EP3679356 illustrate variants of this third set of methods for obtaining a refraction image.
- the inspection system 7 is configured to obtain images according to two different inspection modalities. According to a preferred alternative embodiment, the inspection system 7 is configured to obtain images according to three different inspection modalities.
- the method according to the invention aims to inspect the containers 2 using the inspection system 7 configured to acquire absorption, refraction and birefringence images, making it possible to recognize defects characterized by all of their 3 types of interaction with light.
- the invention is also advantageous for an inspection system for detecting glazes using a device as described in EP4136434, a certain number of cameras observing the same portion of containers under different observation directions.
- the variations in the shape and the position of the reflections corresponding to the glazes between the different images mainly make it possible to distinguish them from parasitic reflections, and a learning classification model allows effective detection/classification while it is difficult to define a priori by professional knowledge, the geometric characteristics of these very random shape defects.
- the objective of the combination of these various lighting and image acquisition techniques is to obtain from each inspected region of each container, at least two and preferably at least three images each according to a different modality and different directions, with for each modality, the value of each pixel which depends on a different modality of interaction of the light with the wall crossed and with the defects to be detected.
- the configuration of the lighting and the cameras depends on the inspected region of the container which can correspond to the body, the bottom, the neck, the shoulder, the rim, the ring or to an area where engravings are present for example.
- the images acquired from the same portion of a container according to at least two different observation directions and according to at least one first modality are made available to the information processing unit 9.
- pre-processing such as:
- this information processing unit 9 comprises a neural network having been trained during a construction phase, on a learning set comprising recordings each composed of at least two images of the same portion of the same container according to at least two different observation directions and according to at least one modality.
- the neural network determines at least one membership class Kj for said portion from a list of classes Kl, K2, ... Kj, ... Kp.
- the trained neural network receives as input, for each container, a recording of at least two images of at least one portion of the container according to a modality and according to two different observation directions, these images being acquired using the inspection system 7 during the scrolling of the containers.
- the neural network analyzes this recording to determine the membership of this portion of container, to a result class among the list of classes Kl, K2, ... Kj, ... Kp..
- each container 2 scrolling in front of the device 1 is inspected in order to detect in the images taken, the presence of defects and to classify the detected defects.
- the classes Ki should also include non-defect objects such as decorations, markings, shadows, etc.
- the information processing unit 9 is thus adapted to implement an inspection method for detecting defects on containers and classifying the containers, according to previously defined classes.
- the inspection method thus makes it possible to classify each container according to at least one class taken from a list of classes including in particular a class for the absence of a defect and a class for the presence of a defect. It should be understood that the subject of the invention makes it possible at least to detect the presence of a defect or the absence of a defect.
- the subject of the invention makes it possible to identify or recognize defects, thus allowing them to be classified.
- the list of classes Kl, K2, ... Kj, ... Kp comprises at least one class comprising the presence in the image portion of at least one abnormal optical singularity corresponding to a defect.
- some of the classes correspond to glass defects, i.e. defects linked to the manufacturing process of the containers.
- the glass defects concerned are glass defects having optical properties of interaction with the light passing through the container, such as at least one part of absorption, and/or one part of birefringence and/or one part of refraction, so that they are detectable using the aforementioned devices.
- these classes may correspond to a bubble, an inclusion, a fold, a grain, a stone, a fin, a large bubble, a trapezoid or a swing.
- several classes can correspond to the same type of glass defect, such as the trapezoid-type glass defect.
- one class can correspond to large trapezoids with thick glass threads and another class to small trapezoids with small unconnected points.
- the list of classes Kl, K2, ...Kj, ...Kp comprises at least one class comprising the presence in the portion of at least one normal optical singularity not corresponding to defects.
- classes may correspond to reliefs with a technical function such as positioning notches or the striations of the laying plane, with a decorative function such as coats of arms, or with a function of technical or commercial indications such as brand, capacity, mold number.
- Other classes may correspond to elements that can be distinguished on the container such as mold seals, which may be circular at the bottom or linear on the vertical wall.
- the number p of image classes is independent of the number of modalities.
- the list of classes includes a number of classes greater than the number of modalities implemented.
- the list of classes may include classes that do not correspond to glass defects.
- the list may include, as a class that does not correspond to glass defects, a class corresponding to a container 2 without defects, a class corresponding to a container 2 with a mold seal, a class corresponding to a container 2 with a coat of arms.
- the list of classes contains a non-glass defect class, at least one trapezoid class, at least one inclusion class, and at least one bubble class. These classes are recorded and accessible to the information processing unit 9.
- the number of classes is therefore determined first by the need for production and quality control, therefore by the need to identify production defects in order to make the right decisions during sorting and to allow possible correction of the process. Conversely, the number of modalities is only determined by the technical and economic limits of the known means of highlighting absorption, refraction and birefringence properties.
- the number of classes also depends on the quality of the sorting obtained by means of the neural network. Indeed, during the training of the neural network, it It is known to verify on test sets the rate of good classifications obtained. It has been observed that the classification is better when the list of classes contains several classes for the same defect such as trapezoids. In other words, the number of classes can be increased to improve the quality of the automatic classification.
- the classification operation is performed by a neural network receiving as input, for each container, a recording of at least two images of at least one portion of the container according to a modality and according to two different observation directions.
- the at least two images are analyzed at the same time by a deep learning neural network which can determine, based on all significant photometric and/or geometric characteristics, the membership of an image singularity to a class.
- Figure 2 illustrates an exemplary embodiment of a convolutional neural network CNN1 receiving as input the images of portions of the containers according to at least two different observation directions and one modality.
- the outputs of the convolutional neural network CNN1 are the input data of a neural network NN for classifying the containers.
- Figure 4 is a schematic view illustrating an exemplary embodiment of an inspection device according to the invention using two cameras adapted to obtain from each three analysis images according to three different modalities, in order to constitute a recording of analysis images comprising at least 6 container images.
- a container 2 and two cameras C1 and C2 configured to respectively acquire images of the same portion of a container according to two different observation directions DI, D2.
- the camera C1 is configured to obtain three images according to three different modalities
- the camera C2 is configured to obtain three images according to these same different modalities.
- K1, K2 are designated as possible classes for the recordings of these six images.
- these six images can be recorded with the appropriate class, and during the learning phase, detection, we can acquire the six images for classification.
- X context data or metadata about the images, which can be taken as input data to the classifier, for example X contains viewing directions, viewing direction differences, camera numbers, modality identifiers for each image.
- FIG. 5 illustrates another exemplary embodiment of an inspection system 7 allowing the acquisition of images of portions of containers according to three different observation directions and one modality.
- One of the two cameras shown delivers images according to two different observation directions.
- Three convolutional neural subnetworks CNN1, CNN2, CNN3 each receive as input the images of portions of the containers according to a determined observation direction.
- the outputs of the three convolutional neural subnetworks CNN1, CNN2, CNN3 are the input data respectively of neural networks NN1, NN2, NN3 collaborating together with a neural subnetwork NN4 allowing the classification of the containers.
- the convolutional neural subnetworks CNN1, CNN2, CNN3, the neural subnetworks NN1, NN2, NN3, and the neural subnetwork NN4 form a neural network, i.e. a single deep learning model within the meaning of the invention.
- the outputs of the networks NN1 NN2 NN3 are for example, when singularities such as defects are present in the images, DSI DS2 DS3 singularities each associated with an output vector of their network, the vectors being able to be considered either as measurements of morphological or photometric properties of the singularities, or as classifications of the singularities.
- the MC module consists in associating the DSI DS2 DS3 singularities of the different views as being descriptions of the same singularity under different observation directions, and the role of the sub-network NN4 is then to determine a unique classification Dj from the outputs of the networks NN1 NN2 NN3.
- the data fusion includes: structuring the classifier into subnetworks, with an output network NN4 which merges the results of the input subnetworks NN1 NN2 NN3.
- the input subnetworks are replaced by classic segmentation modules ANDI AND2 and DSI DS2.
- Figure 6 illustrates another exemplary embodiment of an inspection system 7 allowing the acquisition of images of portions of containers according to two different observation directions and one modality.
- a single NN network is used and is shown in the figure.
- a singularity detection operation is carried out in order to detect the presence of one or more singularities (by the DSI module for the image obtained by the camera C1, by the DS2 module for the image obtained by the camera C2).
- This DSI or DS2 singularity detection detects and locates in the image an image singularity in the sense of a connected or non-connected set of pixels having particular local characteristics relative to neighboring pixels or to the background.
- DSI or DS2 singularity detection can implement any image processing method suitable for detecting singularities with here one or more preliminary processing steps (AND1 and AND2 in the figure) such as filtering, thresholding, mathematical morphology transformations, labeling, variance analysis, edge detection etc.
- a typical result of DSI or DS2 singularity detection can include only the position of a pixel or a set of pixels (typically the connected pixels that form the singularity).
- singularity detection implements a segmentation of the images. For each image, a rectangle framing the detected singularity can easily be sent to the neural network. It is possible to associate additional information with the detected singularities, such as image primitives (perimeter, contrast) or information relating to the container such as its orientation on the conveyor.
- both singularity detection modules can output the position and dimensions of a bounding box that contains a detected singularity.
- a matching is implemented by means of the MC module between the two singularities detected by the DSI and DS2 modules, on the basis of their positions in the images or on the container. For example, if relative to the image of the container or to its external contours, the two framing rectangles (if the DSI and DS2 modules deliver such rectangles) overlap, or are at the same height for images of the vertical wall, or on the same circle during a background check, etc., they are considered as corresponding to the same part or to the same singularity of the container.
- a precise matching can be carried out according to the position on the container of the singularity(ies) detected by the DSI and DS2 modules, knowing the geometry of the container and of the acquisition device.
- the NN network of the figure is of the CNN type, the quality and precision of the upstream detection of singularity does not matter, provided that this detection detects all singularities, including false detections, the CNN type NN network comprising so-called convolution steps capable of detecting artifacts, singularities, and of determining primitive forms for them in order to perform a classification whose result may be the absence of singularity, the presence or absence of a defect, or the type of normal or defect singularity.
- Figures 7A and 7B show an arrangement of a plurality of cameras arranged at different azimuths and elevations and usable for implementing the invention, in an inspection system 7.
- Figures 8A and 8B are two images of the same portion of the same container, here two images of the base of the same glass bottle.
- the figure also shows the orientations of the cameras C1 and C2 used respectively to obtain two images II and 12 in opposite directions and facing each other (angle of 180°).
- the defect DF1 is here only visible on image II.
- a model according to the invention may be able to deduce from the visibility of the defect on image II alone that the defect is of the “open blister” type.
- the invention makes it possible to better classify defects in glass containers.
- Figures 9A and 9B are two images of the same portion of the same other container, acquired by two cameras whose arrangement is visible in Figure 9C.
- two images of the same glass bottle are obtained, the bottom of this bottle resting on a conveyor, the axis of symmetry of the container being vertical.
- Figure 9C more precisely, the orientations of the cameras C1 and C2 used respectively for obtaining two images I1 and I2 according to observation directions forming an angle in a vertical plane denoted P (which is an elevation difference) and an angle in the horizontal plane denoted o (which is an azimuth difference).
- P which is an elevation difference
- o which is an azimuth difference
- the invention therefore reinforces confidence in the classification of defects.
- Figures 10A and 10B are two images of the same portion of yet another same container, here two images of the same glass bottle.
- the figure also shows the orientations of the cameras C1 and C2 used respectively to obtain two images II and 12 in directions forming an angle in a horizontal plane denoted a.
- DFA1 is the front view, by the camera Cl, of a first part DFA of the defect (larger)
- DFB1 is the rear view (camera Cl) of a second DFB part of the defect (small)
- DFA2 is the rear face view (camera C2) of the first DFA part of the defect (larger)
- DFB2 is the front view (camera C2) of the second part of the DFB defect (small)
- the angle a between the 2 directions of observation is here at least 60°.
- the invention makes it possible to automatically detect and recognize/classify defects visible only partially in a single observation direction.
- the object of the invention aims to train a neural network (construction or learning phase) on a learning set comprising recordings each composed of at least a first and a second image of the same portion of container according to two different observation directions and according to at least one modality.
- the recordings of this learning set are made by an inspection system 7 which is the same system used for the use phase.
- the inspection systems 7 used to acquire the images during the construction phase and the use phase are the same.
- these are substantially the same observation directions as those during the inspection, with the same modality.
- the construction phase may precede the use/inspection phase.
- a construction phase may be implemented after an inspection use phase. For example, records usable for learning may be obtained after a first implementation of the use/inspection phase, and the implementation of a construction phase subsequent to the use/inspection phase allows the operation of the model according to the invention to be further improved.
- a construction phase subsequent to a use phase is analogous to a construction phase preceding a use phase, and it may itself be followed by a use phase.
- the image recordings are ordered according to a determined sequence.
- the images coming from the different cameras are classified according to a determined order.
- the image recordings are ordered according to a sequence identical to the sequence of the construction phase.
- the way in which the images are organized or arranged between them within the recordings to be presented as inputs to the classifier network, whether in an inspection phase, therefore classification phase, or in a construction phase, therefore training phase is the same.
- the images obtained according to a given observation direction and a given modality will preferably be presented to the same input connectors of the model in both phases (typically to the same input neurons).
- the identical order for both phases is a preferred method, it is possible alternatively, for example when the images are obtained by means of a device in which the observation directions are distributed in azimuth around the axis of the containers, and taking into account that the containers during inspection may arrive in the device with an indeterminate orientation, only the relative arrangement modulo 360° of the observation directions for each image of a recording counts.
- the learning base To construct the learning base, several containers exhibiting defects to be recognized are selected, but also several containers without defects, several containers bearing normal optical singularities to be recognized: decorations, codes, notches, screw moldings, positioning notches, etc., and/or several containers exhibiting commercially acceptable optical singularities.
- the images of these recordings show at least a portion of a container to be inspected corresponding to regions of interest of the container such as the ring, the neck, the shoulder, the body, the rim or a half-right or left side or an area of presence of engravings.
- Some of these images include normal optical singularities to be recognized or abnormal optical singularities corresponding to defects. These images can be limited to these optical singularities or take into account a rectangle framing these optical singularities. These images can also take into account an enlarged rectangle framing these optical singularities, taking into account the context or the positioning of these singularities in the image.
- the method aims to gather these recordings in a learning base, in a large number, typically at least a thousand recordings.
- several recordings are made comprising images of defects to be recognized, images with normal optical singularities to be recognized or images of containers without defects.
- the containers are preferably of the same material (glass or plastic material) as those to be inspected, and are preferably manufactured according to the same process. These containers can be of the same model, the same color, etc. but preferably the method consists of including in the learning base images of several containers of different models for each type of defect and several types of defects for each container model.
- the construction phase is supervised learning.
- the neural network is trained by supervised learning, i.e. by operations imposing on it the classification to be carried out with an error to be minimized for a given set of records.
- Each record of the learning base is associated, at least as a label, with a membership class such as a defect type or a non-defect type.
- the system is provided with a set of sorted records, labeled according to one of the previously defined classes. Each record is associated, via sorting and labeling, with a of said classes, which will allow the algorithm to calculate a more general model that will subsequently allow any unknown, unlabeled data to be associated with one of the previously defined classes.
- This supervised learning method differs from the unsupervised learning method (having no a priori on the classes). According to this unsupervised method, data is provided in bulk to the system, without any form of sorting or labeling. The system itself is responsible for defining the number of classes that it considers most relevant and associates one of said classes with each piece of data (example: X-Means clustering algorithm).
- the supervised learning method also differs from unsupervised learning (with an a priori on the number of classes): data is provided in bulk to the system, without any form of sorting or labeling. On the other hand, the system is told the number p of expected classes. The system then automatically associates each piece of data with one of the p expected classes (example: K-Means clustering algorithm). Unsupervised learning is not suitable for the objective of classifying defects according to a defect nomenclature in particular for glass, which would be determined a priori.
- the method according to the invention aims to train the neural network so that it recognizes the types of defect and the containers not containing defects.
- This learning phase is carried out by a person skilled in the art of artificial intelligence who chooses in particular a neural network model, a learning base and a learning algorithm.
- This neural network is trained and tested iteratively until the result is obtained desired (confidence matrix, metrics (precision, recall, fl-score, mAP50 and mAP75 (mAP being an anglo-saxon acronym meaning "mean Average Precision").
- the databases of these image records are reorganized with additions or deletions and/or the neural network model is changed as well as the learning algorithm.
- the subject of the invention is based on the observation that the shape (morphology) and sometimes the photometry (contrast in the broad sense, therefore intensity or color as well as separation of intensity and color) of a defect or non-defect type singularity varies according to the direction of observation and specifically according to the type of singularity.
- the change in appearance (morphology and/or photometry) in the image of a defect according to the directions of observation or even the lighting is a characteristic which makes it possible to differentiate the defects.
- a region of the container is illuminated at precise incidences, by directed light beams reaching the surface of the container at a precise incidence so that the majority of the beam penetrates the glass wall and propagates in the glass. If a glaze is present on the light path in the wall, then the glaze reflects the beam which leaves in a modified direction to exit the wall at a precise exit angle, which is a function of the incident angle and the position and shape of the glaze.
- a glaze-type defect in an image of observed shape differs depending on the observation angle, or is invisible in another direction even close (+/-10 0 ) to the first direction.
- a bubble in a transparent container has a different observed shape depending on the observation angle, and this difference is not directly deducible by a geometric transformation.
- the observed shape of the bubble and even the contrasts of the bubble depend on the relative position of i) the light source, ii) the bubble in the container (position/orientation of the container) and iii) the observation direction.
- an inclusion or a grease stain on the surface will have an image shape that varies with the observation direction but in a quasi-deterministic manner by the geometry of the container and the observation direction, while the photometry varies little. It follows that the variation of the geometry and the photometry between different points of view is a discriminating characteristic of bubbles and stains or inclusions.
- the method according to the invention not only makes it possible to identify glass defects in containers, but also to classify these defects in order to move from inspection to optimization of the manufacturing process.
- One of the characteristics of the invention is to define a list of classes comprising classes of defects, which makes it possible to relate glass defects to characteristics of the manufacturing process to be regulated. Improving the classification of glass defects makes it possible to better trace back the causes of glass defects.
- the object of the invention is advantageously exploited in the context of manufacturing installations to allow better detection and categorization of defects present within the containers. Certain defects can be seen, detected and categorized more easily thanks to the different observation directions possibly combined with different modalities.
- the inspection method according to the invention is designed so that the neural network associates a confidence score with the classification of each inspected container of a production.
- the confidence score is typically the probability of belonging of the container to the membership class.
- the score can be expressed as a % or a value between 0 and 1.
- a container may have several defects.
- analysis images of the same container can be extracted, several image regions and for example several SR segments are recognized as belonging to defect classes.
- the class to which the container belongs will be that of the segment classified in the defect class with the highest criticality.
- the confidence score of the classification i.e. the class assigned to the container will be that of the segment classified with a confidence score greater than the threshold of confidence.
- the statistical analysis of the production which will be presented later, can account for the distribution of defects independently of the number of containers rejected.
- the neural network and in particular the CNN type detects the defects and also gives as information, their position in the container. This position is useful for correcting the method, for example it is useful to know if a defect is in the body or the neck.
- the CNN can take into account the position of the singularities in the container to perform the classification.
- the neural network also takes into account the relative position of the defect in the images according to different observation directions.
- the subject of the invention is used for sorting the production of containers in the following manner. After classifying a container, at least one container sorting characteristic is compared to a rejection criterion, and when the sorting characteristic exceeds the rejection criterion for a container, the container is considered non-compliant and rejected. Indeed, the installation comprises an ejector for removing defective containers from production.
- the sorting characteristic and the rejection criterion are dependent on the membership class to decide whether or not the container is compliant, the sorting characteristic being calculated on at least one image of the container according to one of the two or three modalities.
- the sorting characteristic and the rejection criterion are for example a defect dimension such as its surface or its length measured in at least one analysis image.
- the confidence score can optionally be taken into account for sorting, by rejecting containers belonging to a low-critical defect class only if the confidence score is high and conversely by rejecting containers belonging to a critical defect class even if the confidence score is low. Since the neural network is able to determine the position of a defect, with high confidence thanks to the different observation directions, according to a variant of the invention the position is an additional rejection criterion, because the position of a defect can influence its criticality. [0178]According to the invention, it is possible to define different rejection criteria depending on the position of the defects in the container.
- the object of the invention is used to carry out a statistical analysis of a production of containers, that is to say an analysis of the frequency or distribution of the different types of defects and their criticality, the types of defects included in the list of classes and their criticality being determined in advance for the purposes of process control.
- the inspection device 1 When the inspection device 1 according to the invention is installed downstream of the annealing arch 5, it is preferably equipped with a device for reading information carried on the containers and indicating the mold or the original section of the containers and/or a time stamp of their manufacture and/or a unique identifier of each container such as a serial number, or else connected to such a reading device. It is therefore possible and preferable to carry out the statistical analysis of the production, from the classification of the containers by the inspection method, according to the distribution of the defects in direct relation to the production parameters at the time of manufacture of each container and/or according to the different cavities and sections of the manufacturing machine.
- the classification of the containers is only taken into account when the confidence score of the assigned class exceeds a confidence threshold for:
- the confidence threshold corresponds to a predetermined or adjustable minimum value of the confidence score as an operating parameter of the inspection device, the adjustment being made on its HMI or remotely.
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP24746007.4A EP4736111A1 (fr) | 2023-06-30 | 2024-06-28 | Procede et dispositif pour inspecter des recipients selon au moins deux directions d'observation differentes en vue de classer les recipients |
| CN202480055769.5A CN121773452A (zh) | 2023-06-30 | 2024-06-28 | 用于根据至少两个不同观察方向检查容器以对容器进行分类的方法和装置 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR2307021A FR3150596A1 (fr) | 2023-06-30 | 2023-06-30 | Procédé et dispositif pour inspecter des récipients selon au moins deux directions d’observation différentes en vue de classer les récipients |
| FRFR2307021 | 2023-06-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025003618A1 true WO2025003618A1 (fr) | 2025-01-02 |
Family
ID=89767074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/FR2024/050859 Ceased WO2025003618A1 (fr) | 2023-06-30 | 2024-06-28 | Procede et dispositif pour inspecter des recipients selon au moins deux directions d'observation differentes en vue de classer les recipients |
Country Status (4)
| Country | Link |
|---|---|
| EP (1) | EP4736111A1 (fr) |
| CN (1) | CN121773452A (fr) |
| FR (1) | FR3150596A1 (fr) |
| WO (1) | WO2025003618A1 (fr) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121114039A (zh) * | 2025-11-13 | 2025-12-12 | 陕西鹤鸣健康科技有限公司 | 一种保健胶囊类产品的异物检测方法及系统 |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4606634A (en) | 1984-07-27 | 1986-08-19 | Owens-Illinois, Inc. | System for detecting selective refractive defects in transparent articles |
| FR2794241A1 (fr) | 1999-05-25 | 2000-12-01 | Emhart Glass Sa | Machine pour l'inspection de recipients |
| EP1109008A1 (fr) | 1999-12-15 | 2001-06-20 | Saint Gobain Cinematique Et Controle | Procédé de contrôle de la qualité d'un article notamment en verre |
| JP4886830B2 (ja) | 2009-10-15 | 2012-02-29 | 東洋ガラス株式会社 | 透明ガラス容器の焼傷検査方法及び装置 |
| EP3180135A1 (fr) | 2014-08-14 | 2017-06-21 | Krones AG | Procédé d'inspection optique et dispositif d'inspection optique de récipients |
| WO2018061196A1 (fr) | 2016-09-30 | 2018-04-05 | 東洋ガラス株式会社 | Dispositif d'inspection de marques de brûlure sur un récipient en verre |
| EP3679356A1 (fr) | 2017-09-07 | 2020-07-15 | Heuft Systemtechnik GmbH | Dispositif d'inspection comprenant un éclairage de couleur |
| EP3745298A1 (fr) * | 2019-05-28 | 2020-12-02 | SCHOTT Schweiz AG | Procédé et système de classification pour articles transparents à haut rendement |
| WO2020244815A1 (fr) | 2019-06-06 | 2020-12-10 | Krones Ag | Procédé et dispositif d'inspection optique de contenants |
| WO2021209704A1 (fr) | 2020-04-16 | 2021-10-21 | Tiama | Poste et procédé pour détecter en translation des défauts de glaçures sur des récipients en verre |
| WO2021213864A1 (fr) | 2020-04-24 | 2021-10-28 | Krones Ag | Procédé et dispositif d'inspection de contenants |
| EP4078156A1 (fr) | 2019-12-16 | 2022-10-26 | Applied Vision Corporation | Imagerie séquentielle pour l'inspection de parois latérales de récipients |
| WO2023052732A1 (fr) | 2021-09-30 | 2023-04-06 | Tiama | Procede et dispositif d'inspection pour des recipients deplaces selon une trajectoire rectiligne |
-
2023
- 2023-06-30 FR FR2307021A patent/FR3150596A1/fr active Pending
-
2024
- 2024-06-28 WO PCT/FR2024/050859 patent/WO2025003618A1/fr not_active Ceased
- 2024-06-28 EP EP24746007.4A patent/EP4736111A1/fr active Pending
- 2024-06-28 CN CN202480055769.5A patent/CN121773452A/zh active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4606634A (en) | 1984-07-27 | 1986-08-19 | Owens-Illinois, Inc. | System for detecting selective refractive defects in transparent articles |
| FR2794241A1 (fr) | 1999-05-25 | 2000-12-01 | Emhart Glass Sa | Machine pour l'inspection de recipients |
| EP1109008A1 (fr) | 1999-12-15 | 2001-06-20 | Saint Gobain Cinematique Et Controle | Procédé de contrôle de la qualité d'un article notamment en verre |
| JP4886830B2 (ja) | 2009-10-15 | 2012-02-29 | 東洋ガラス株式会社 | 透明ガラス容器の焼傷検査方法及び装置 |
| EP3180135A1 (fr) | 2014-08-14 | 2017-06-21 | Krones AG | Procédé d'inspection optique et dispositif d'inspection optique de récipients |
| WO2018061196A1 (fr) | 2016-09-30 | 2018-04-05 | 東洋ガラス株式会社 | Dispositif d'inspection de marques de brûlure sur un récipient en verre |
| EP3679356A1 (fr) | 2017-09-07 | 2020-07-15 | Heuft Systemtechnik GmbH | Dispositif d'inspection comprenant un éclairage de couleur |
| EP3745298A1 (fr) * | 2019-05-28 | 2020-12-02 | SCHOTT Schweiz AG | Procédé et système de classification pour articles transparents à haut rendement |
| WO2020244815A1 (fr) | 2019-06-06 | 2020-12-10 | Krones Ag | Procédé et dispositif d'inspection optique de contenants |
| EP4078156A1 (fr) | 2019-12-16 | 2022-10-26 | Applied Vision Corporation | Imagerie séquentielle pour l'inspection de parois latérales de récipients |
| WO2021209704A1 (fr) | 2020-04-16 | 2021-10-21 | Tiama | Poste et procédé pour détecter en translation des défauts de glaçures sur des récipients en verre |
| EP4136434A1 (fr) | 2020-04-16 | 2023-02-22 | Tiama | Poste et procédé pour détecter en translation des défauts de glaçures sur des récipients en verre |
| WO2021213864A1 (fr) | 2020-04-24 | 2021-10-28 | Krones Ag | Procédé et dispositif d'inspection de contenants |
| WO2023052732A1 (fr) | 2021-09-30 | 2023-04-06 | Tiama | Procede et dispositif d'inspection pour des recipients deplaces selon une trajectoire rectiligne |
Non-Patent Citations (3)
| Title |
|---|
| LIANG QIAOKANG ET AL: "Real-time comprehensive glass container inspection system based on deep learning framework", ELECTRONICS LETTERS, THE INSTITUTION OF ENGINEERING AND TECHNOLOGY, GB, vol. 55, no. 3, 7 February 2019 (2019-02-07), pages 131 - 132, XP006075830, ISSN: 0013-5194, DOI: 10.1049/EL.2018.6934 * |
| MIGUEL CARRASCO: "Visual inspection of glass bottlenecks by multiple-view analysis", INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING., vol. 23, no. 10, 1 October 2010 (2010-10-01), GB, pages 925 - 941, XP093161205, ISSN: 0951-192X, DOI: 10.1080/0951192X.2010.500676 * |
| PRZEMYSLAW DOLATA: "Double-stream Convolutional Neural Networks for Machine Vision Inspection of Natural Products", vol. 31, no. 7-8, 14 September 2017 (2017-09-14), US, pages 643 - 659, XP093161211, ISSN: 0883-9514, Retrieved from the Internet <URL:https://dx.doi.org/10.1080/08839514.2018.1428491> DOI: 10.1080/08839514.2018.1428491 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121114039A (zh) * | 2025-11-13 | 2025-12-12 | 陕西鹤鸣健康科技有限公司 | 一种保健胶囊类产品的异物检测方法及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4736111A1 (fr) | 2026-05-06 |
| CN121773452A (zh) | 2026-03-31 |
| FR3150596A1 (fr) | 2025-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4457507B1 (fr) | Procede et dispositif d'inspection de recipients chauds en verre en vue d'identifier des defauts | |
| TWI698628B (zh) | 用於檢查潮溼眼用鏡片的系統及方法 | |
| EP3963284B1 (fr) | Ligne de contrôle de récipients vides en verre | |
| EP2856122B1 (fr) | Procede optique d'inspection de recipients transparents ou translucides portant des motifs visuels | |
| EP4558810A1 (fr) | Procede et dispositif pour inspecter des recipients en verre selon au moins deux modalites en vue de classer les recipients selon des defauts verriers | |
| EP1891419B1 (fr) | Procede et installation pour la detection de defauts de surface et de structure d un produit long en defilement | |
| US20240420314A1 (en) | Foreign material inspection system | |
| EP4736111A1 (fr) | Procede et dispositif pour inspecter des recipients selon au moins deux directions d'observation differentes en vue de classer les recipients | |
| EP3443330A1 (fr) | Méthode et système de vérification d'une installation d'inspection optique de récipients en verre | |
| FR3098583A1 (fr) | Installation et procédé pour mesurer l’épaisseur des parois de récipients en verre | |
| WO2014041416A1 (fr) | Dispositif de controle de pieces en defilement | |
| WO2024141740A1 (fr) | Dispositif et procédé d'analyse d'un relief d'inspection d'une paroi d'un récipient en verre | |
| Liu et al. | Automatic detection technology of surface defects on plastic products based on machine vision | |
| EP3956652B1 (fr) | Système et procédé de détection de vitrocéramique | |
| WO2023098187A1 (fr) | Procédé de traitement, appareil de traitement et système de traitement | |
| EP1109008A1 (fr) | Procédé de contrôle de la qualité d'un article notamment en verre | |
| WO2020212266A1 (fr) | Procede de detection de vitroceramique | |
| US20260141681A1 (en) | Method and device for inspecting glass containers according to at least two modes with a view to classifying the containers by their glass defects | |
| WO2001055705A1 (fr) | Installation et procede pour la detection de glacures | |
| WO2022136761A1 (fr) | Procede pour detecter des defauts du joint horizontal de moule pour des recipients en verre | |
| CN115239709B (zh) | 一种玻璃瓶烫金工艺的质量检测方法 | |
| Tellbach et al. | Multimodal Optical Telemetry for Defect Detection in Vaccine Vials | |
| EP4413356A1 (fr) | Dispositif et procede opto-informatique d'analyse en lumiere traversante d'un recipient en materiau transparent ou translucide a l'aide d'une camera numerique polarimetrique | |
| WO2025017257A1 (fr) | Procédé de tri de déchets combinant une analyse de composition chimique et l'usage de marqueurs | |
| Huang et al. | Feature area size prediction method of spherical fruit based on projection transformation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24746007 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024746007 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024746007 Country of ref document: EP Effective date: 20260130 |
|
| ENP | Entry into the national phase |
Ref document number: 2024746007 Country of ref document: EP Effective date: 20260130 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2024746007 Country of ref document: EP |