CN121113402B - Seal detection method, device and system - Google Patents
Seal detection method, device and systemInfo
- Publication number
- CN121113402B CN121113402B CN202511658696.1A CN202511658696A CN121113402B CN 121113402 B CN121113402 B CN 121113402B CN 202511658696 A CN202511658696 A CN 202511658696A CN 121113402 B CN121113402 B CN 121113402B
- Authority
- CN
- China
- Prior art keywords
- detection
- sealing line
- sealing
- outer packaging
- points
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B57/00—Automatic control, checking, warning, or safety devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/38—Investigating fluid-tightness of structures by using light
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of seal detection equipment, in particular to a seal detection method, a device and a system, wherein a detected object respectively shoots the top surface and the bottom surface of the detected object under a target point position at a first detection station and a second detection station by a detection camera, after shooting, an inner package region extraction and an outer package contour extraction are carried out on shot images, whether an outer package is sealed or not is judged by judging whether the distance between the edge of the inner package and the outer package contour is larger than a specified pixel, after the seal of the outer package is confirmed, the tightness of the inner package is judged by fitting a seal line on the inner package, when the seal of the inner package and the outer package is confirmed to be good, the seal line of the outer package is extracted again to judge the inclination angle of the seal line of the outer package, and finally, the seal detection result is obtained based on the detection for multiple times.
Description
Technical Field
The invention belongs to the technical field of seal detection equipment, and particularly relates to a seal detection method, a seal detection device and a seal detection system.
Background
After the medical instruments such as medical consumables and the like are produced, two layers of packaging are needed, wherein the first layer is an inner packaging bag, a light blue medical paper plastic bag is used, and the second layer is a transparent polyvinyl chloride plastic packaging bag.
In the requirements of sealed package, the condition that the first layer is not sealed successfully can not appear, and the condition that the second layer of packaging bag is not sealed and sealed askew can not appear, otherwise can lead to sealing failure, the medical instrument of medical consumable etc. production is polluted, causes the medical malpractice.
In the prior art, most of the manual observation methods are used for checking the sealing of medical consumable packaging in medical terms, and the like, so that the cost is high, the checking efficiency is low, and the conditions of missed checking and misjudgment are easily caused by fatigue during long-time checking.
Disclosure of Invention
Therefore, the invention aims to provide a seal detection method, which is used for relieving the conditions of higher cost, lower detection efficiency and easy missed detection and judgment of manual observation in the prior art.
In a first aspect, the present application provides a seal detection method, applied to a control unit in a seal detection system, the system further comprising:
The detection mechanism comprises a light source and a detection camera, wherein the light source comprises a surface light source and an arch tunnel light source, the light-emitting end of the surface light source faces towards a detection object, the arch tunnel light source is arranged on one side, far away from the surface light source, of the detection object, the detection camera is arranged on one side, far away from the detection object, of the arch tunnel light source, the detection end faces towards the detection object, and the detection mechanism is provided with two detection stations and a first detection station and a second detection station, so that the detection stations are respectively used for detecting two sides of the detection object.
The method comprises the following steps:
Acquiring a shooting image under a target point position;
carrying out inner package region extraction and outer package contour extraction on the shot image;
Judging whether the distance between the edge of the inner packaging bag and the outline of the outer packaging bag is larger than a specified pixel or not;
If so, performing sealing line fitting on the inner packaging bag to obtain a sealing line fitting result, extracting an outer packaging sealing line, and determining an inclination angle of the outer packaging sealing line relative to the outer packaging edge;
And obtaining a seal detection result based on the seal line fitting result, the outer package seal line and the outer package seal line inclination angle.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, a step of obtaining a seal detection result based on a fitting result of a sealing line of an inner package bag, a sealing line of an outer package and an inclination angle of the sealing line of the outer package, including:
if the fitting result of the sealing line of the inner packaging bag, the sealing line of the outer packaging bag and the inclination angle meet preset requirements, the sealing detection result is determined to be good in sealing.
With reference to the first aspect, the embodiment of the present invention provides a first possible implementation manner of the first aspect, a step of performing seal line fitting on the inner packaging bag to obtain a seal line fitting result, where the step includes:
after the edge lines of the shot image are extracted, aiming at each edge line, the designated pixels are shifted inwards, and a datum line is obtained.
And (3) aiming at each datum line, carrying out seal line searching by adopting an operator for searching points at the edge to obtain a plurality of points.
And judging whether a fitting sealing line can be obtained after a plurality of points are linearly fitted by a specified algorithm.
If yes, determining that the fitting result of the sealing line is qualified.
If not, determining that the fitting result of the sealing line is abnormal.
With reference to the first aspect, the embodiment of the present invention provides a first possible implementation manner of the first aspect, wherein the algorithm is designated as an improved least square method, and the step of judging whether a fitting sealing line can be obtained after a plurality of points are linearly fitted by the designated algorithm includes:
Randomly extracting two sampling points from a plurality of points to determine a temporary straight line;
calculating the distance from all other points to the temporary straight line, and classifying the target points with the distance smaller than a preset threshold value into a consensus set to obtain a plurality of consensus sets;
selecting a consensus set corresponding to a temporary straight line with the largest number of target points in the consensus set as a largest consensus set;
Based on all target points in the consensus set, performing final fitting through a least square method to obtain a fitting linear equation of the sealing line;
and judging whether the continuity of the sealing line is qualified or not according to the fitting goodness of the fitting linear equation or the proportion of the internal target points of the consensus set.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, the step of extracting the outer package sealing line and determining an inclination angle of the outer package sealing line with respect to an edge of the outer package, further includes:
performing enhancement processing on the photographed image to obtain an increased photographed image;
And (3) carrying out canny edge extraction on the shot image so as to extract edge lines on two sides of the whole outer packaging bag.
For each edge line, the specified pixels are shifted inward, and the outer package seal line extraction is performed.
And judging whether the angle between the outer package sealing line and the outer package edge line is smaller than a preset angle threshold value.
If so, the sealing of the outer packaging bag is good.
If not, the inclination of the sealing line of the outer packing bag is confirmed.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, a step of performing enhancement processing on a captured image, including:
acquiring a preset target gray scale range;
Analyzing a gray level histogram of the photographed image, and determining a characteristic gray level range representing effective information in the photographed image based on a histogram morphology;
calculating a linear transformation coefficient according to the target gray scale range and the characteristic gray scale range, wherein the linear transformation coefficient comprises a gain parameter and an offset parameter;
After the dot operation is performed on the photographed image to calculate the gray level square of each pixel, linear transformation is performed based on the gain parameter and the offset parameter, and an enhanced photographed image is obtained.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the step of calculating the linear transformation coefficient according to the target gray scale range and the feature gray scale range includes:
calculated by the following formula:
α = (Z_max - Z_min)÷(X_high - X_low);
β = Z_min - (α × X_low)
Where α is a gain parameter, β is an offset parameter, z_max is an upper limit value of the target gray scale range, z_min is a lower limit value of the target gray scale range, x_high is an upper limit value of the characteristic gray scale range, and x_low is a lower limit value of the characteristic gray scale range.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, before the step of acquiring a captured image under a target point, the method further includes:
the packaging type of the target workpiece is obtained.
Based on the package type, a target point location is determined.
And moving the target workpiece to the target point position.
In a second aspect, the present application provides a seal detection device, for use in a control unit in a seal detection system, the device comprising:
And the acquisition module is used for acquiring the shot image under the target point position.
And the extraction module is used for extracting the inner package area and the outer package outline of the shot image.
And the judging module is used for judging whether the distance between the edge of the inner packaging bag and the outline of the outer packaging bag is larger than the appointed pixel.
And the fitting module is used for fitting the sealing line of the inner packaging bag to obtain a sealing line fitting result under the condition that the distance between the edge of the inner packaging bag and the outline of the outer packaging bag is larger than the appointed pixel, and extracting the outer packaging sealing line to determine the inclination angle of the outer packaging sealing line relative to the edge of the outer packaging bag.
And the detection module is used for obtaining a sealing detection result based on the sealing line fitting result, the outer packing sealing line and the inclination angle.
In a third aspect, the present application provides a seal detection system, including a control unit, where the control unit is configured to perform the seal detection method provided above.
Further, the system further comprises:
The detection platform is made of high-permeability materials and is used for bearing detection objects.
And the transfer mechanism is used for picking up the detection object and transferring the detection object to the detection platform or removing the detection object from the detection platform.
The conveying device is in transmission connection with the detection platform so as to drive the detection platform to sequentially pass through the first detection station and the second detection station;
wherein, all be provided with a plurality of check points in first detection station and the second detection station. The detection platform pauses at the detection points so that the detection camera can shoot the detection objects at the corresponding positions.
The embodiment of the invention has the following beneficial effects:
According to the invention, the top surface and the bottom surface of the detected object under the target point are respectively shot by the detection cameras at the first detection station and the second detection station, after shooting, the inner package region extraction and the outer package contour extraction are carried out on shot images, whether the outer package is sealed or not is judged by judging whether the distance between the edge of the inner package and the outer package contour is larger than a specified pixel, after the outer package sealing is confirmed, the tightness of the inner package is judged by carrying out sealing line fitting on the inner package, when the inner package and the outer package are confirmed to be well sealed, the outer package sealing line is extracted again to judge the inclination angle of the outer package sealing line, and based on the detection for multiple times, the sealing detection result is finally obtained.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are some embodiments of the invention and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart provided in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a seal detection device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an isometric view of a seal detection system according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an isometric view of a seal detection system according to an embodiment of the present invention;
FIG. 5 is a schematic top view of a seal detection system according to an embodiment of the present invention;
fig. 6 is a schematic side view of a seal detection system according to an embodiment of the present invention.
Reference numerals:
The device comprises a 1-acquisition module, a 2-extraction module, a 3-judgment module, a 4-fitting module and a 5-detection module;
100-detection platform, 200-detection mechanism, 210-detection camera, 220-surface light source, 230-arched tunnel light source, 300-transfer mechanism, 310-horizontal driving component, 311-first driving component, 312-second driving component, 320-longitudinal driving component, 330-pickup component, 400-conveying device, 500-storage component, 510-storage tank, 520-partition board and 530-proximity sensor.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to facilitate understanding of the present embodiment, technical terms designed by the present application will be briefly described below.
Blob analysis (connected domain analysis), a fundamental technique in machine vision and image processing, is used to detect, analyze and process features of connected regions (i.e. "blobs") in images. Where "Blob" is understood to mean a group of connected sets of pixels in an image that have similar properties (e.g., gray value, color, texture). It generally corresponds to a "spot" or a "region" in an image, such as a part in industrial inspection, a product defect (e.g., black spot, scratch), a cell in a medical image, a tumor, a vehicle in traffic monitoring, an apple in natural scene, a human face, etc. "analysis" refers to extracting various attributes of these connected regions, and screening, counting, and measuring.
Canny edge extraction (CANNY EDGE Detection) is an edge Detection algorithm in image processing. For extracting accurate, continuous and slim edges from the image. The method accurately locates the boundary of gray level change in the digital image through the process of denoising, calculating gradient, non-maximum value suppression and double-threshold connection.
Example 1
The embodiment of the application provides a seal detection method, which is applied to a control unit in a seal detection system, wherein the system further comprises a detection mechanism 200, wherein the detection mechanism 200 comprises a light source and a detection camera 210, the light source comprises a surface light source 220 and an arch-shaped tunnel light source 230, the light emitting end of the surface light source 220 faces towards a detected object, the arch-shaped tunnel light source 230 is arranged on one side of the detected object far away from the surface light source 220, the detection camera 210 is arranged on one side of the arch-shaped tunnel light source 230 far away from the detected object, the detection end faces towards the detected object, and the detection mechanism 200 is provided with two detection stations and is provided with a first detection station and a second detection station for detecting two sides of the detected object respectively.
Referring to fig. 1, the method is as follows:
S100, acquiring a shooting image under a target point position.
S200, extracting an inner package area and an outer package contour of the shot image.
S300, judging whether the distance between the edge of the inner packaging bag and the outline of the outer packaging bag is larger than a specified pixel.
If yes, go to step S400-S500.
S400, performing sealing line fitting on the inner packaging bag to obtain a sealing line fitting result, extracting an outer packaging sealing line, and determining the inclination angle of the outer packaging sealing line relative to the outer packaging edge.
S500, obtaining a seal detection result based on the seal line fitting result, the outer package seal line and the inclination angle.
Specifically, in this embodiment, the top surface and the bottom surface of the detection object under the target point are respectively photographed by the detection camera 210 at the first detection station and the second detection station. After photographing, the image photographed by the inspection camera 210 is subjected to inner package region extraction and outer package contour extraction, and then, whether the outer package is sealed is judged by whether the distance between the inner package edge and the outer package contour is greater than a specified pixel. After the outer package is confirmed to be sealed, the tightness of the inner package is judged by a mode of fitting a sealing line to the inner package. When the inner and outer packages are confirmed to be well sealed, the outer package sealing line is extracted again to judge the inclination angle of the outer package sealing line. And finally obtaining a sealing detection result based on the multiple detection. In the whole detection process, human participation is not needed, the detection efficiency is high, and the detection is more accurate.
Wherein, during the detection, because the detection camera 210 is the facial light setting and circumference is provided with arch tunnel light source 230, can also show the sealing port of outer wrapping bag when alleviating the reflection of light problem of the wrapping bag of medical consumable, guarantee the accuracy of detection. The surface light source 220 can cover internal sealing defects and content problems, and the dome-shaped tunnel light source 230 can catch surface sealing defects and appearance defects. In this embodiment, both are combined so that the sealing state of the detection object can be detected in one-time and all-around manner by the sealing detection method.
In addition, under the combined use of the surface light source 220 and the arched tunnel light source 230, the illumination requirements of sealing detection objects with different materials and different structures can be met, meanwhile, the image quality and the detection precision can be improved, and in specific defect types, the most suitable light source illumination mode or combination mode can be used, so that images with higher contrast, clearer details and less interference can be obtained, and the accuracy and the reliability of the sealing detection method are improved.
Specifically, in this embodiment, the target points are multiple and are located in the first detection station and the second detection station, and after the detected object moves to the first detection station and the second detection station, the detected object is illuminated by the surface light source 220 and the arch tunnel, and the detected object is photographed by the detection camera 210 to obtain a photographed image.
Here, in this embodiment, the designated pixel is 150 pixels. The distance between the edge of the inner package and the outline of the outer package is the linear distance between the sealing edge of one side of the inner package and the sealing edge of the opposite, nearest outer package.
In this embodiment, after step S300, the method further includes:
If not, go to step S310.
And S310, determining that the sealing detection result is that the outer packaging bag is not sealed.
In the step of judging whether the distance between the edge of the inner packaging bag and the outline of the outer packaging bag is larger than the specified pixel, if the distance is not larger than the specified pixel, the sealing detection result is directly determined to be that the outer packaging bag is not sealed, the subsequent processing such as sealing line fitting and inclination angle judgment is not needed, the processing steps are reduced, the detection efficiency is improved, and meanwhile misjudgment caused by unsealing of the outer packaging bag is avoided.
In this embodiment, step S500 includes:
s510, if the fitting result of the sealing line of the inner packaging bag, the sealing line of the outer packaging bag and the inclination angle all meet the preset requirements, determining that the sealing detection result is good in sealing.
Specifically, in this embodiment, by comprehensively determining whether the fitting result of the sealing line of the inner packaging bag, the existence of the sealing line of the outer packaging bag and the inclination angle all meet the preset requirements, the sealing detection result is finally determined, and the overall and automatic determination of the sealing quality of the inner packaging bag and the outer packaging bag is realized. Therefore, the method ensures that the detection result is judged to be sealed well only when all key sealing indexes are qualified, remarkably improves the accuracy and reliability of the detection result, avoids missed judgment or misjudgment possibly caused by single detection, and further ensures the integrity and safety of the detection object package.
In this embodiment, step S500, the step of performing seal line fitting on the inner package bag to obtain a seal line fitting result further includes:
s501, after edge line extraction is carried out on a shot image, aiming at each edge line, inward shifting of specified pixels is carried out, and a datum line is obtained.
S502, carrying out seal line searching by adopting an operator for searching points at the edge aiming at each datum line to obtain a plurality of points.
S503, judging whether a fitting sealing line can be obtained after a plurality of points are linearly fitted by a specified algorithm.
If yes, go to step S504, otherwise go to step S505.
S504, determining that the fitting result of the sealing line is qualified.
S505, determining that the fitting result of the sealing line is abnormal.
In this embodiment, the extracted edge lines are the left and right edge lines of the inner bag region. I.e. the actual boundary of the inner bag. A fiducial line is generated by translating the edge line inward (in a direction from the edge of the package toward the center of the package). Based on accurate reference line searching and the fitting sealing points, linear fitting and existence judgment are carried out by utilizing an algorithm, so that high-precision and automatic positioning and judgment of the inner package sealing line are realized. And the accuracy and reliability of the seal defect identification are improved, false detection or missing detection caused by fuzzy seal lines or position deviation is effectively avoided, and the robustness and the automation level of the whole detection system are further improved.
Specifically, in this embodiment, if the pixels of the inner and outer edge lines are less than or equal to 150 pixels, it is directly determined that the outer packaging bag is not sealed. Firstly, the inner packaging bag is required to be extracted from a photographed image, the color of the inner packaging bag after sealing is darker than that of the outer packaging bag after sealing, a sealing line can be seen, the color difference between the inner packaging bag (light blue), the outer packaging bag (transparent) and the background is utilized, a G channel-R channel (the light blue is higher in the value of the G channel and lower in the value of the R channel) is utilized, the contrast ratio between the inner packaging area and the background can be obviously enhanced after subtraction, irrelevant information is restrained, and therefore the pixel value of a green channel is subtracted from the pixel value of a red channel, linear image enhancement is carried out at the same time, the surrounding pixels are blackened while the light blue object is highlighted, and the inner packaging area is more prominent, so that the image with the inner packaging bag only is obtained.
Subsequently, the inner bag is extracted using blob (connected domain analysis) analysis, and the enhanced image is converted into a binary image by setting a threshold. The inner bag area turns white (foreground, pixel value 255) and the background turns black (background, pixel value 0), and Blob analysis is performed on the binary image to identify and mark all connected white areas. At this time, according to the known approximate area and shape of the package bag, a suitable filter (aspect ratio in this embodiment) is provided, the pixel region representing the inner package bag is extracted accurately from all the connected regions, possible noise points are eliminated, then the region is converted into edges, only edge lines at both ends are extracted, and after the edges at both sides are translated to the inner designated pixels (150 pixels), two new reference lines are obtained, so that the search range of the seal line is positioned accurately to the position where the seal line is most likely to appear.
Then, a narrow "calliper" shaped search area is set centered on each reference line after translation. In this region, points with the most intense gray level variation (i.e., edge points) are searched and located at regular intervals along the reference line using an edge point detection operator. These points are potential seal line feature points. And (3) carrying out straight line fitting on all the collected characteristic points of the sealing line by using a least square method, and judging that the inner packaging bag is sealed if the line is successfully fitted, which shows that the found points are sufficiently arranged linearly to form an effective sealing line. If the line cannot be fitted, it is considered that the number of found feature points is very small and the fitting error is huge due to too many scattered points, the side inner packaging bag is judged to be unsealed or poor in sealing, and if the continuous linear edge feature is not found in the area, the inner packaging bag is judged to be unsealed.
In the above procedure, although a narrow "calliper" shaped search area is provided, it is not excluded that a "spot" on the sealing line may cause the edge point to jump to the boundary of the "spot" instead of the sealing line. If the conventional least squares method is used, it is very sensitive to such points. The algorithm specified in the present application refers to an improved least squares method whose improved core idea is to use the geometric feature that the seal line should be a continuous path within the caliper.
With reference to the first aspect, step S503 includes:
S5031, randomly extracting two sampling points from a plurality of points to determine a temporary straight line.
S5032, calculating the distance between all other points and the temporary straight line, and classifying the target points with the distance smaller than the preset threshold value into a consensus set to obtain a plurality of consensus sets.
S5033, selecting the consensus set corresponding to the temporary straight line with the largest target point number in the consensus sets as the largest consensus set.
S5034, based on all target points in the consensus set, final fitting is carried out through a least square method, and a fitting linear equation of the sealing line is obtained.
S5035, judging whether the continuity of the sealing line is qualified or not according to the fitting goodness of the fitting linear equation or the proportion of the internal target points of the consensus set.
First, in step S5031, from among the points found in step S502, two points are completely randomly extracted as sampling points, and a straight line model is constructed with the minimum sample size based on the principle that two points define a straight line.
Subsequently, a consensus set is constructed at step S5032, which calculates distances (specifically, vertical distances) from all points except the sampling point to the temporary straight line determined at step S5031. Points whose distance is less than a certain threshold (e.g., half the caliper width) are marked as "inner points" (i.e., target points) that are considered to be in common with this temporary straight line.
The above process of randomly selecting sampling points, constructing temporary straight lines and determining the consensus sets is repeatedly executed for a plurality of times (such as 100 times and 1000 times) to obtain a plurality of consensus sets. With a large number of repeated random samplings and evaluations, the algorithm traverses the possible model space in a "brute force" but efficient manner.
Subsequently, the consensus set corresponding to the temporary model having the most target points (i.e., the consensus set rule maximum) is selected and named as "maximum consensus set" in step S5033.
It will be appreciated that the "correct points" created by the true seal line will be dominant in number. Even if there are up to 30% -40% of interference points (outliers), as long as there is one sample drawn to two "correct points", the temporary straight line thus established will be supported by a large number of other "correct points" (i.e. a large consensus set). And a model with "smudges" drawn, it is difficult to achieve acceptance at a large number of other points. Therefore, by declaring the consensus set corresponding to the temporary straight line with the largest number of target points as the largest consensus set, a clean data set can be obtained, points in the data set have extremely high probability of all coming from the real sealing line, and the spots and noise points are effectively excluded.
Subsequently, a final fitting is performed in step S5034, after the screened, high quality "maximum consensus set" is taken, a least squares fitting is performed again on all points in this set with all points in this "maximum consensus set", and the fitting results in a final fitted linear equation.
It will be appreciated that the conventional least squares method is very sensitive to outliers, but has the advantage of giving the best fit without bias. The outliers have now been removed in the previous step, leaving all the target points with high confidence. At this time, the advantage of high precision can be fully exerted by using the least square method, and the disadvantage of interference is avoided.
Finally, step S5035 is executed to perform continuity judgment, wherein there are two judgment bases, i.e. the proportion of the target point or the goodness of fit of the fit straight line equation.
For the target point ratio = number of target points in the maximum consensus × number of all points found in step S502, which directly reflects the "continuity" or "cleanliness" of the sealing line, which is continuous and clear, the vast majority of edge points should fall within the maximum consensus, and the ratio will be high (e.g., > 85%). If there is a break in the seal line, severe stain coverage, then a large number of points are excluded as outliers, resulting in a low interior point ratio. A threshold (e.g., 70%) may be set below which the failure is judged.
For the goodness of fit of the fit straight line equation, for example, the sum of squares of residuals of the final fit straight line or R 2 is calculated to determine the coefficient, which measures how tight the points in the maximum consensus set are to the final straight line, even if the interior point ratio is high, if the interior points are themselves very dispersed, the fit straight line residuals are large, indicating that the seal line is continuous but not straight, and there may be bending or jitter, which is also a quality defect.
And (3) combining the indexes to give out a binary judgment of 'pass' or 'fail', thereby realizing automatic detection of sealing quality.
Thus, by combining random sampling with a consensus set mechanism, it is ensured that the algorithm is not affected by individual "blemishes" and is always striving to find the geometric model representing the continuous path of the seal line supported by the most evidence (edge points).
In this embodiment, step S400 further includes:
S410, enhancement processing is carried out on the photographed image, and the increased photographed image is obtained.
S420, carrying out canny edge extraction on the shot image so as to extract edge lines on two sides of the whole outer packaging bag.
S430, for each edge line, shifting the designated pixel inwards, and extracting the outer package sealing line.
S440, judging whether the angle between the outer package sealing line and the outer package edge line is smaller than a preset angle threshold value.
S450, if yes, confirming that the outer packaging bag is sealed well.
If not, S460 confirms that the outer packing bag sealing line is inclined.
In the embodiment, the Canny edge extraction is performed on the shot image to accurately obtain the edge lines on two sides of the transparent outer packaging bag, and the seal line extraction is performed on the basis of the area after the specified pixels are translated inwards, so that the technical problems that the contrast between the edge of the transparent material and the background is low and the transparent material is difficult to accurately capture are solved. Whether the angle between the outer package sealing line and the edge line is smaller than a preset threshold value is calculated and judged, so that automation and quantitative judgment on whether the outer package sealing is askew or not is realized, the detection accuracy and reliability are remarkably improved, the problem of sealing failure caused by the inclination of the sealing line is solved, and the integrity and safety of medical consumable packaging are further ensured.
In particular, in this embodiment, the outline of the overwrap bag needs to be extracted first, and the edge of the overwrap bag is very low in contrast to the background (usually white or gray glass plate) due to the transparent material used for the overwrap bag, which is difficult for the human eye to distinguish, and the conventional threshold segmentation method is basically ineffective. Therefore, enhancement processing is performed on the captured image first. And then, extracting the canny edge of the outer packaging bag image, extracting the edges on the left side and the right side of the whole packaging bag, translating 150 pixels inwards from the left side and the right side to extract the sealing line, and judging the angle of the included angle between the sealing line and the outer edge element.
The adopted Canny edge detection algorithm specifically comprises the steps of slightly blurring an image to remove interference such as camera noise and micro scratches on a packaging bag, and calculating brightness gradient strength and direction of each pixel point in the image. Wherein, although the gray level change is weak at the transparent edge, gradient change still exists, and the Canny algorithm is very sensitive to the gradient change. Subsequently, only the point of maximum intensity in the gradient direction is reserved, and the edge line is thinned. The gradient strength is then compared to preset high and low thresholds, and if the gradient strength is greater than the high threshold, a strong edge (i.e., must be a boundary), if the gradient strength is between the low and high thresholds, a "weak edge" (i.e., can be a boundary), and if the gradient strength is less than the low threshold, a "suppressed" (i.e., not a boundary). Finally, only the "weak edges" that are connected to the "strong edges" are preserved to effectively ensure that the extracted edges are continuous, complete contours, rather than intermittent points. Thus, a binary image is obtained in which white pixel points constitute edge lines on the left and right sides and the upper and lower sides of the outer bag.
With reference to the first aspect, step S410 includes:
s411, acquiring a preset target gray scale range;
S412, analyzing a gray level histogram of the shot image, and determining a characteristic gray level range representing effective information in the shot image based on the histogram morphology;
s413, calculating a linear transformation coefficient according to the target gray scale range and the characteristic gray scale range, wherein the linear transformation coefficient comprises a gain parameter and an offset parameter;
s414, after performing a point operation on the captured image to calculate the gray scale square of each pixel, linear transformation is performed based on the gain parameter and the offset parameter, so as to obtain an enhanced captured image.
Specifically, in step S411,
(1) For display it is typically [0, 255] (8 bit image).
(2) For subsequent processing, it may be [0, 1023] (10 bits), [0, 4095] (12 bits), or [0.0, 1.0] (floating point normalization), depending on your camera bit depth or library function requirements.
Let us note that the target minimum value is z_min and the maximum value is z_max, thereby determining the target gray scale range [ z_min, z_max ] of the output image.
By this step, the "start line" z_min and the "finish line" z_max of the gradation are set according to the demands of the downstream application.
S412, analyzing the gray level histogram of the input image, and determining the characteristic gray level range representing the effective information in the input image based on the histogram morphology.
Specifically, the feature gray scale range [ x_low, x_high ] of the input image is counted, wherein x_low is the minimum value of the feature gray scale range, specifically, the critical point at which the number of pixels on the low gray scale side of the histogram starts to steadily increase, and x_high is the maximum value of the feature gray scale range, specifically, the critical point at which the number of pixels on the high gray scale side of the histogram starts to significantly decrease.
This is the most critical step. The minimum gray value (i_min) and the maximum gray value (i_max) of the image are directly used, since they may be determined by only a few extreme noise pixels or saturated pixels and cannot represent the true dynamic range of the image subject content. The direct calculation using them results in poor conversion and inadequate contrast stretching. Therefore, we need to find the boundary of "effective information" by analyzing the morphology of the gray level histogram, i.e., find the range that can represent "effective information".
And (3) drawing a gray level histogram, namely analyzing the gray level histogram of the square enhanced input image I.
The low threshold value x_low is determined by omitting a small number of pixels representing "pure background noise" which may exist on the left side from the low gray value end on the histogram, and finding a gray value point x_low. To the right of this point, the number of pixels starts to grow significantly and steadily. This point represents the starting point of the valid signal area, indicating that the actual object information starts to appear, which is X low, which effectively filters out dark field noise.
And determining a high threshold value X_high, and similarly, at the high gray value end of the histogram, ignoring the possible few saturated pixels or high-bright point noise on the right side, and finding a gray value point X_high. To the left of this point, the number of pixels begins to drop significantly. This point represents the end point of the active signal area, which is x_high, which effectively filters out bright field noise and overexposure points.
The interval [ x_low, x_high ] determined in the above manner can accurately capture the gray scale dynamic range of the distribution of most of useful information (such as edges and textures in the figure) contained in the image, which is a key premise for realizing high-quality adaptive enhancement. Our goal is to map this interval to [ Z_min, Z_max ].
S413, calculating a linear transformation coefficient according to the target gray scale range and the characteristic gray scale range, wherein the linear transformation coefficient comprises a gain parameter alpha and an offset parameter beta.
Specifically, the calculation formula is as follows:
Alpha= (total width of target output range)/(width of input effective signal range)
Expressed by the formula:
α = (Z_max - Z_min)÷ (X_high - X_low)
Where (X_high-X_low) is the "width" of the input signal and (Z_max-Z_min) is the "width" of the desired output. The gain parameter α is the ratio of these two widths. If a >1, the contrast is shown enlarged, and if a <1, the contrast is shown compressed. According to the description (let bright be brighter, dark be darker), α will typically be greater than 1.
Meanwhile, a preset value beta (offset parameter) is calculated, and specifically, a calculation formula is as follows:
β=start of target output- (start of input after stretching)
Expressed by the formula:
β = Z_min - (α × X_low)
After the gain of α, the original input valid signal start point x_low becomes α×x_low. But we hope that it should be mapped to Z min. Therefore, we need to add an offset β such that α×x_low+β=z_min, and back-calculate the above formula.
The following is an example:
Assume that:
the target output range is [0, 255].
After analyzing the histogram, it is determined that the effective gray scale range of the input image is [100, 600].
And (3) calculating:
α = (255 - 0)÷(600 - 100) = 255÷500 = 0.51
Here, α <1 is because the input range (500) is wider than the output range (255), and is therefore the compression contrast. If forced amplification is desired, then [ X_low, X_high ] is adjusted, e.g., only [300, 600], then α=255++300=0.85 (still less than 1). If more than 1, the input range must be less than 255, e.g. take [100, 300], α=255+.200+.1.28.
β = 0 - 0.51 × 100 = -51
The final transformation is: i_out=0.51 x I_in-51
When i_in=100 (the effective range start), i_out=0.51×100-51=0.
When i_in=600 (end of effective range), i_out=0.51×600-51=255.
This accurately maps the effective range to the entire output range.
Then, after performing a point operation on the captured image to calculate the gray scale square of each pixel, linear transformation is performed based on the gain parameter and the offset parameter, resulting in an enhanced captured image.
Specifically, the image enhancement is realized by multiplying the image with itself. Specifically, for each pixel in the input image, the gray value I new(x,y),Inew (x, y) =i (x, y) ×i (x, y) in the new image is calculated from the square of the original gray value I (x, y) and output, which greatly amplifies the contrast between the weak target (edge) and the background so that the edge that is not originally obvious becomes very prominent. Then, on the basis of the square operation, a linear transformation is further performed, i_final (x, y) =α× [ I (x, y) ×i (x, y) ]+β, where α is a gain parameter and β is an offset parameter. Alpha is typically a Gain parameter greater than 1 which serves to further amplify the square enhanced contrast difference, making the bright brighter, dark darker, and making the edge signal stronger, and beta is an offset (Bias) parameter which serves to adjust the overall brightness level because the overall gray value of the image becomes very large after square sum multiplied by the coefficient, possibly exceeding the standard display range (0-255) or camera bit depth (e.g., 0-4095), plus a fixed value to shift it back to a suitable range, or to set a more ideal brightness baseline for the subsequent Canny algorithm.
In this embodiment, before step S100, the method further includes:
s10, acquiring the packaging type of the target workpiece.
S20, determining a target point position based on the package type.
S30, moving the target workpiece to the target point position.
Specifically, in this embodiment, before the detection, the detection object needs to be detected, so as to query the model according to a preset database, thereby determining that the package type to which the detection object belongs is "long package" (length is greater than or equal to 150 mm) or "short package" (length is less than 150 mm).
And a main control unit (such as a PLC or an industrial personal computer) of the system invokes a preset moving and photographing program from the memory according to the determined packaging type. If the package is short, 1 target point is set, i.e., the center point directly below the detection camera 210. At this point an image is taken that covers the entire sealing area of the workpiece. If the package is long, the target points are set to 2, namely a first point (for shooting the left sealing area of the package) and a second point (for shooting the right sealing area of the package). The system needs to move to the two points in sequence to shoot, so that a complete detection image can be obtained.
Then, the workpiece is accurately positioned on each of the determined target points in the first detection station and the second detection station in sequence, and the image is acquired by the detection camera.
According to the embodiment, the short package is photographed once, and the long package is photographed twice, so that efficiency waste caused by photographing all workpieces uniformly for many times is avoided, the problems of insufficient edge resolution or distortion increase and the like possibly caused by photographing only one image for the long workpiece are also prevented, the detection quality is ensured, and the maximization of the throughput of the system is realized.
The seal detection device provided by the embodiment is applied to a control unit in the provided seal detection system. The device comprises an acquisition module 1, an extraction module 2, a judgment module 3, a fitting module 4 and a detection module 5, which are shown in the figure 2.
The acquisition module 1 is used for acquiring a photographed image under the target point.
The extraction module 2 is used for carrying out inner package region extraction and outer package contour extraction on the shot images.
The judging module 3 is used for judging whether the distance between the edge of the inner packaging bag and the outline of the outer packaging bag is larger than a specified pixel.
The fitting module 4 is configured to perform seal line fitting on the inner package bag to obtain a seal line fitting result when a distance between an edge of the inner package bag and an outline of the outer package bag is greater than a specified pixel, and extract an outer package seal line.
The detection module 5 is used for obtaining a seal detection result based on the seal line fitting result, the outer package seal line and the inclination angle.
In a third aspect, an embodiment of the present application further provides a seal detection system, please refer to fig. 3 to 6. The seal detection system provided in this embodiment includes a control unit for performing the seal detection method provided above, and further includes a detection platform 100, a transfer mechanism 300, and a conveying device 400.
The bottom surface of the detection platform 100 is made of a high-permeability material and is used for carrying a detection object. The transfer mechanism 300 is used for picking up the detection object and transferring the detection object to the detection platform 100, or removing the detection object from the detection platform 100. The conveying device 400 is in transmission connection with the detection platform 100.
The conveyor 400 drives the inspection platform 100 to pass through the first inspection station and the second inspection station in sequence.
In addition, the two detecting mechanisms 200 in the present embodiment are formed with a first detecting station and a second detecting station in the circumferential direction of the detecting platform 100.
Specifically, the light emitting end of the surface light source 220 in the present embodiment faces the detection platform 100, the arch-shaped tunnel light source 230 is disposed on the side of the detection platform 100 away from the surface light source 220, and the detection camera 210 is disposed on the side of the arch-shaped tunnel light source 230 away from the detection platform 100 with the detection end facing the detection platform 100.
Specifically, after the medical consumables are packaged, the medical consumables with the packaging bags are stacked at the material taking position of the transfer mechanism 300. Subsequently, the transfer mechanism 300 picks up the packaged medical consumable and moves onto the inspection platform 100, at this time, the inspection platform 100 is at the initial position, the transfer mechanism 300 stays at this position, and the conveyor 400 is driven to move the inspection platform 100 to the inspection position of the inspection mechanism 200.
After the detection platform 100 reaches the detection position, the light source irradiates the detection platform 100, and the first detection position and the second detection position respectively shoot and detect the upper side and the lower side of the packaged medical consumable to realize the detection of the outer package of the medical consumable.
During detection, as the detection camera 210 is provided with the arched tunnel light source 230 for the surface light, the sealing opening of the outer packaging bag can be highlighted while the reflection problem of the packaging bag of medical consumables is relieved, and the detection accuracy is ensured.
The surface light source 220 can cover internal sealing defects and content problems, and the dome-shaped tunnel light source 230 can catch surface sealing defects and appearance defects. In this embodiment, both are combined so that the sealing state of the detection object can be detected in one-time and all-around manner.
In addition, under the combined use of the surface light source 220 and the arched tunnel light source 230, the illumination requirements of sealing detection objects with different materials and different structures can be met, meanwhile, the image quality and the detection precision can be improved, and in specific defect types, the most suitable light source illumination mode or combination mode can be used, so that images with higher contrast, clearer details and less interference can be obtained, and the recognition accuracy and reliability of a machine vision algorithm are improved.
In addition, when detecting the packaging bags with different specifications, the conveying device 400 can accurately place the packaging bags with the medical consumables in the detection points of the detection mechanism 200 so as to realize the detection of the packaging bags with the medical consumables with different specifications.
After the detection is finished, the conveying device 400 drives the detection platform 100 to perform reset movement, the detection platform 100 moves back to the initial position, and the transfer mechanism 300 picks up the detected detection object again and transfers the detection object to the next area according to the detection result.
In this embodiment, a plurality of detection points (i.e., the target points) are disposed in the first detection station and the second detection station. The inspection platform 100 pauses at the inspection points, so that the inspection camera 210 can photograph the inspection object at the corresponding position.
In this embodiment, a package having a length of less than 150mm is considered a short package. When the short packaging bag is detected, the conveying device 400 drives the short packaging bag to move to the opposite position of the detecting mechanism 200, the detecting mechanism 200 shoots the middle part of the short packaging bag, and then the whole short packaging bag can be shot, namely, a detection point is arranged in each of the first detecting station and the second detecting station. When the detection platform 100 reaches the detection point, the detection mechanism 200 can shoot the whole short package, and then the detection of the tightness of the short package can be realized by performing image analysis on the shot picture.
In this embodiment, the package bag with a length of 150mm-300mm is a long package bag, and when the long package bag is detected, the conveying device 400 drives the detection platform 100 or the detection mechanism 200, so that the detection mechanism 200 performs two times of shooting on the long package bag, that is, two detection points are respectively and correspondingly arranged in the first detection station and the second detection station, so that two sides of the long package bag are respectively and independently shot, and then an image analysis is performed on a picture obtained by the two times of shooting, so as to realize detection on the tightness of the long package bag.
Under this structure, the sealing detection device that this embodiment provided adopts the mode of removing the shooting to shoot the leakproofness of the wrapping bag of medical consumable, can set up a plurality of check points in first detection station and the second detection station to correspond the packing of different length, can both realize accurate detection short package and long packing, can compatible sealing detection of the medical consumable packing of different length, the suitability is better.
Specifically, in the present embodiment, the conveying device 400 specifically adopts a linear module. The linear module in the embodiment comprises a ball linear guide rail and a servo motor which are in transmission connection, and can realize stable linear motion. So that the packaging bag can be accurately moved to the preset detection point of the detection mechanism 200 when the detection platform 100 is driven to move, thereby ensuring that the target area (particularly the sealing port) of the packaging bag is positioned at a fixed position of the imaging visual field during each shooting.
In this embodiment, the seal-testing apparatus further includes a storage assembly 500. The storage assembly 500 has a first storage space for placing the pass and a second storage space for placing the fail, both of which are located on the moving track of the transfer mechanism 300.
In this embodiment, after the detection mechanism 200 completes the shooting detection of the tightness of the medical consumable packaging bag on the detection platform 100, a determination can be automatically made according to the image analysis result (pass or fail).
Then, according to the determination result, the transfer mechanism 300 transfers and places the qualified product in the first storage space by the transfer mechanism 300. If the packaging bag is determined to be a defective product, the transfer mechanism 300 transfers the packaging bag to the second storage space, thereby realizing full-automatic detection and classification of the packaging bag.
In this embodiment, the storage assembly 500 includes a storage slot 510 and a partition 520. The inner wall of the storage groove 510 is provided with a plurality of clamping grooves along the extending direction of the storage groove 510. The partition 520 is adapted to the card slot, and the plurality of partitions 520 are detachably inserted into the storage slot 510 to form a first storage space and a second storage space.
Wherein, a plurality of clamping grooves are arranged on the inner wall of the storage groove 510 along the extending direction of the storage groove 510. The partition 520 is adapted to the card slot, and the plurality of partitions 520 are detachably inserted into the storage slot 510 to form a first storage space and a second storage space.
In this embodiment, the inner wall of the storage groove 510 is provided with a plurality of clamping grooves along the length direction, and the partition 520 is detachably inserted into the clamping grooves to separate the space in the storage groove 510, so as to form a first storage space (qualified product area) and a second storage space (unqualified product area), and the sizes and positions of the first storage space and the second storage space can be quickly and flexibly adjusted according to actual requirements.
When short packaging bags need to be stored, more separation plates 520 can be inserted to separate the storage groove 510 into a plurality of smaller independent spaces, so that the short packaging bags are convenient to be classified and stacked and are not easy to topple. When it is desired to store long packages, a portion of the barrier 520 may be reduced or even removed, allowing for longer storage space to accommodate long packages (up to 400mm in length). Under this structure, can realize depositing the medical consumable wrapping bag of different specifications, need not to change whole storage module 500, greatly promoted the adaptability and the simple operation nature of equipment.
In this embodiment, the undetected packaging bag containing the medical consumable supplies is placed in the storage box, and a plurality of storage slots 510 are also provided in the storage box, and the undetected packaging bag containing the medical consumable supplies is stacked in the storage box.
In this embodiment, the storage assembly 500 includes a proximity sensor 530. The proximity sensor 530 is provided in plurality and spaced apart on the outer wall of the storage tank 510.
Specifically, in this embodiment, a plurality of proximity sensors 530 are disposed on the outer wall of the storage tank 510 and spaced apart from each other, and the proximity sensors 530 can detect the distance between themselves and the detecting mechanism 200, and the detecting result of the proximity sensors 530 can determine whether the storage tank 510 is placed at a preset position, so as to ensure that the transferring mechanism 300 can place the detected packaging bags into the storage tank 510.
In this embodiment, the transfer mechanism 300 includes a horizontal drive assembly 310, a longitudinal drive assembly 320, and a pick-up assembly 330.
The horizontal driving assembly 310 has a horizontal moving end, and the horizontal driving assembly 310 is disposed on one side of the detection platform 100. The longitudinal driving assembly 320 has a longitudinal moving end, and the longitudinal driving assembly 320 is in driving connection with the horizontal moving end. The pick-up assembly 330 includes a pick-up member for picking up the test object, the pick-up member being drivingly connected to the longitudinally movable end.
In this embodiment, the horizontal driving component 310 can drive the horizontal moving end to move in a horizontal plane. The longitudinal driving assembly 320 is mounted on the horizontal moving end so as to move horizontally along with the horizontal moving end, and can drive the longitudinal moving end in a vertical direction to perform lifting movement, thereby driving the pick-up member to move in horizontal and vertical directions.
In addition, in this embodiment, the moving track of the horizontal moving end is opposite to the material stacking position, the storage slot 510 and the detection platform 100, so that the pickup element can perform the actions of down material taking, material transferring and down material discharging under the driving of the linkage structure of the horizontal driving assembly 310 and the longitudinal driving assembly 320.
In this embodiment, the horizontal driving assembly 310 includes a first driving piece 311 and a second driving piece 312. The first driving piece 311 is disposed on one side of the detection platform 100 and has a first moving end. The second driving element 312 is disposed at the first moving end, and the moving end of the second driving element 312 is a horizontal moving end.
In this embodiment, the first driving member 311 and the second driving member 312 in driving connection with the first driving member 311 form a horizontal moving structure.
In one embodiment, the first driving member 311 may be a driving member moving in a large range, and the second driving member 312 may be a fine-tuning driving member in a small range, which are used cooperatively to achieve accurate movement of the picking member.
In this embodiment, the first driving member 311 and the second driving member 312 both realize driving in the horizontal direction through the rotation structure, that is, the moving tracks of the moving ends of the first moving end and the second driving member 312 are both arc-shaped. Thus, a working area covering the space from the material taking position to the detecting platform 100 to the storage assembly 500 is formed, compared with a linear reciprocating movement track, the arc-shaped movement path is generally shorter and smoother, and the ineffective travel is reduced, so that the efficiency of the picking member moving in a large range is remarkably improved.
In this configuration, the second driver 312 can finely and flexibly adjust the position of the first driver 311 after positioning. The overlapping of the two arcs expands the achievable working range and positioning flexibility of the pick-up in the horizontal plane.
In this embodiment, the movement mechanism further includes a positioning camera. The positioning camera is arranged on the longitudinal driving component 320, and the shooting direction of the positioning camera faces downwards.
Specifically, the positioning camera in the present embodiment is a 3D camera. The 3D camera is disposed at one side of the first driving piece 311, and the photographing direction of the 3D camera is directed downward. When the transfer mechanism 300 picks up an undetected packaging bag filled with medical consumables, the 3D camera can capture the relative positions of the pickup assembly 330 and the packaging bag, so as to determine the size of the packaging bag and the detection mode of the packaging bag, and can drive the first driving member 311, the second driving member 312 and the longitudinal driving assembly 320 according to the specific positions of the packaging bag, so that the pickup assembly 330 can accurately pick up the packaging bag.
In this embodiment, the picking member is a vacuum chuck. The pick-up assembly 330 also includes a vacuum generator that interfaces with the vacuum chuck.
The vacuum chuck picks up the wrapping bag that is equipped with medical consumable through negative pressure absorption mode, and area of contact is big and the atress is even, not fragile wrapping bag.
When picking up, the horizontal driving assembly 310 drives the longitudinal driving assembly 320 and the vacuum chuck to move above the packaging bag, and then the longitudinal driving assembly 320 drives the vacuum chuck to move downwards to be attached to the packaging bag, and the vacuum generator generates negative pressure to enable the chuck to be firmly adsorbed on the surface of the packaging bag.
When the vacuum generator is placed, the vacuum generator rapidly releases negative pressure (or is switched into positive pressure blowing), and the sucker can be instantaneously separated from the packaging bag, so that rapid and reliable release is realized, the pick-and-place cycle time is obviously shortened, and the overall efficiency is improved.
And, the vacuum chuck may be provided in plurality. And at least two vacuum chucks are arranged at intervals along a straight line to form chuck groups, a plurality of chuck groups are arranged, and the chuck groups are arranged in parallel.
A plurality of vacuum chucks form a chuck group after being arranged at intervals along a straight line, so that the multi-point adsorption pick-up is formed on the packaging bag, and the adsorption stability is ensured.
Under the structure that a plurality of sucking disc groups set up side by side, can adsorb a plurality of wrapping bags simultaneously and pick up to promote detection efficiency.
Specifically, in this embodiment, vacuum chuck totally four, every two form a sucking disc group and are used for adsorbing to pick up a wrapping bag, and two sucking disc groups can adsorb to pick up two wrapping bags simultaneously, have promoted detection efficiency.
In this embodiment, the detection platform 100 is made of high-transmittance glass.
The conveying device 400 is in direct transmission connection with the detection platform 100 to drive the detection platform 100 to move along the arrangement direction of the first sub-light source and the second sub-light source, so that the first detection piece and the second detection piece can sequentially detect the top surface and the bottom surface of the packaging bag on the detection platform 100.
At the same time, the flatness and optical uniformity of the high-transmittance glass help to maintain the stability and uniformity of the "dome-shaped light" field formed by the second sub-light source and the second detection member. The glass surface is smooth, unnecessary diffuse reflection can be reduced, so that arched light can be more intensively and regularly irradiated on the sealing area of the bottom surface of the packaging bag, defect characteristics are further highlighted, the sensitivity and reliability of bottom surface detection are improved, and a clear and undistorted optical channel is provided for bottom surface detection (especially key arched light imaging).
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
In addition, in the description of embodiments of the present invention, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, mechanically connected, electrically connected, directly connected, indirectly connected via an intermediate medium, or in communication between two elements. The specific meaning of the above terms in the present invention will be understood by those skilled in the art in specific cases.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
It should be noted that the foregoing embodiments are merely illustrative embodiments of the present invention, and not restrictive, and the scope of the invention is not limited to the foregoing embodiments, but it should be understood by those skilled in the art that any modification, variation or substitution of some technical features described in the foregoing embodiments may be easily made within the scope of the present invention without departing from the spirit and scope of the technical solutions of the embodiments. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511658696.1A CN121113402B (en) | 2025-11-13 | 2025-11-13 | Seal detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511658696.1A CN121113402B (en) | 2025-11-13 | 2025-11-13 | Seal detection method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN121113402A CN121113402A (en) | 2025-12-12 |
| CN121113402B true CN121113402B (en) | 2026-01-27 |
Family
ID=97936497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511658696.1A Active CN121113402B (en) | 2025-11-13 | 2025-11-13 | Seal detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN121113402B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958124A (en) * | 2023-09-12 | 2023-10-27 | 地立(苏州)智能装备有限公司 | Automatic packagine machine anomaly monitoring system |
| CN119579565A (en) * | 2024-11-29 | 2025-03-07 | 歌尔光学科技有限公司 | Linear defect detection method, defect detection equipment, storage medium and product |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103029892A (en) * | 2012-12-17 | 2013-04-10 | 上海艾尔贝包装科技发展有限公司 | Exhaust bag and manufacture method thereof |
| JP2016217760A (en) * | 2015-05-15 | 2016-12-22 | 大日本印刷株式会社 | Inspection system, inspection method |
| CN106353051A (en) * | 2016-08-12 | 2017-01-25 | 湖北周黑鸭食品工业园有限公司 | Sealing detecting equipment and method |
| KR102031101B1 (en) * | 2019-06-11 | 2019-11-08 | (주)케이테크놀로지 | Inspection method for slope type corner seal line of flat-panel display cell |
| US11626202B2 (en) * | 2020-01-17 | 2023-04-11 | Jordan Jacek deHaan | Medical testing apparatus |
| CN114055855A (en) * | 2020-07-30 | 2022-02-18 | 四川卡库机器人科技有限公司 | Automatic detection system and method for defects of large edge and small edge of packaging bag |
-
2025
- 2025-11-13 CN CN202511658696.1A patent/CN121113402B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958124A (en) * | 2023-09-12 | 2023-10-27 | 地立(苏州)智能装备有限公司 | Automatic packagine machine anomaly monitoring system |
| CN119579565A (en) * | 2024-11-29 | 2025-03-07 | 歌尔光学科技有限公司 | Linear defect detection method, defect detection equipment, storage medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN121113402A (en) | 2025-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5670915B2 (en) | Appearance inspection device | |
| EP1277042B1 (en) | Directional lighting and method to distinguish three dimensional information | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN113418933B (en) | Flying shooting visual imaging detection system and method for detecting large-size object | |
| CN101464418A (en) | Flaw detection method and apparatus | |
| CN101796399A (en) | Observation device and observation method and inspection device and inspection method | |
| JP5654486B2 (en) | Appearance inspection device | |
| US20100053790A1 (en) | Hard disk inspection apparatus and method, as well as program | |
| CN116148277B (en) | Three-dimensional detection method, device and equipment for defects of transparent body and storage medium | |
| CN112730424A (en) | Aviation plug pin defect detection device and method | |
| CN115713491B (en) | Methods, apparatus and electronic equipment for detecting defects in liquid crystal display panels | |
| JP2017040600A (en) | Inspection method, inspection device, image processor, program and record medium | |
| CN217857436U (en) | Contour dimension detection device | |
| CN214638332U (en) | Detection device for detecting defects on bottle cap | |
| CN121113402B (en) | Seal detection method, device and system | |
| CN117929280A (en) | Battery blue film coating system and battery blue film coating detection method | |
| KR102766273B1 (en) | Apparatus and method for inspecting nozzles using a rotating method | |
| JP2003215055A (en) | Inspection device | |
| CN120873966A (en) | PCB defect recognition method and system based on image recognition | |
| JP4747313B2 (en) | Inspection method and inspection equipment for thin plate parts | |
| CN220542797U (en) | Defect detection device | |
| JPH11312725A (en) | Substrate loading / unloading device | |
| TW201925725A (en) | Method for inspecting sensor package structure, inspection apparatus, and focus assistant loader of inspection apparatus | |
| JP2005300174A (en) | Apparatus and method for inspecting package | |
| CN100504333C (en) | Method for detecting automatic transposition of lens |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |