CN111982924A - Vacuum food bulge detection device based on multi-line laser and detection algorithm thereof - Google Patents
Vacuum food bulge detection device based on multi-line laser and detection algorithm thereof Download PDFInfo
- Publication number
- CN111982924A CN111982924A CN202010893713.0A CN202010893713A CN111982924A CN 111982924 A CN111982924 A CN 111982924A CN 202010893713 A CN202010893713 A CN 202010893713A CN 111982924 A CN111982924 A CN 111982924A
- Authority
- CN
- China
- Prior art keywords
- laser
- line
- food
- vacuum food
- bulge
- 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.)
- Withdrawn
Links
- 235000013305 food Nutrition 0.000 title claims abstract description 77
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 238000004806 packaging method and process Methods 0.000 claims abstract description 28
- 238000001914 filtration Methods 0.000 claims description 22
- 230000005484 gravity Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 230000037303 wrinkles Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 4
- 238000009461 vacuum packaging Methods 0.000 description 4
- 239000010794 food waste Substances 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012856 packing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000287828 Gallus gallus Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000015278 beef Nutrition 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000008373 pickled product Nutrition 0.000 description 1
- 235000021110 pickles Nutrition 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 235000013580 sausages Nutrition 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N2021/8924—Dents; Relief flaws
Landscapes
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Textile Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a vacuum food bulge detection device based on multi-line laser and a detection algorithm thereof, and relates to the technical field of optical detection. The invention comprises a frame, a laser adjusting plate and a laser adjusting column, wherein the frame is erected above a conveyor belt; the upper surface of the n-shaped frame is provided with a chute; the surface of the laser adjusting plate is provided with a plurality of through grooves; the plurality of through grooves are arranged according to a preset included angle and are distributed in a fan shape; the upper half part of one side surface of the laser adjusting column is provided with a roller; the roller is matched with the through groove on the surface of the laser adjusting plate; a laser is fixedly arranged on the lower end face of the laser adjusting column; the clamping groove is clamped on one side wall of the sliding groove. The device and the intelligent detection method replace the traditional manual detection, the curvature of the laser line irradiated on the food packaging bag by the parallel laser lamp is judged by utilizing the vacuum food bulge algorithm to judge whether the packaging bag contains the bubble bulge, the detection efficiency is high, the cost is reduced, and the waste of food is avoided.
Description
Technical Field
The invention belongs to the technical field of optical detection, and particularly relates to a vacuum food bulge detection device based on multi-line laser and a detection algorithm thereof.
Background
With the continuous improvement of living standard of people, various foods appear in the market, and food packaging bags and packaging cans with different shapes and colors appear. With the social progress, people pay more and more attention to the food safety problem, and in the food vacuum packaging, food is filled into a packaging bag, air in the packaging bag is pumped out, and the sealing process is completed after the vacuum degree in the packaging bag reaches a preset vacuum degree. In the food industry, vacuum packaging is very common, and various cooked products such as chicken legs, ham, sausage, grilled fish slices, beef jerky and the like, and various pickled products such as various pickles, bean products, preserved fruits and the like which need to be preserved are increasingly subjected to vacuum packaging. The food after vacuum packaging has long shelf life, and the shelf life of the food is greatly prolonged.
However, the condition that the vacuum degree in the packaging bag does not reach the established requirement often appears after the current packagine machine finishes packing, and this needs the workman to select unqualified packing article with the inspection table, and the inspection table commonly used at present is provided with the lamp house of taking the fluorescent tube, places the packaging bag in on the lamp house, upwards shines through the fluorescent tube in the lamp house, and whether the workman of being convenient for looks over the bag has the bubble in. However, the manual inspection method is often poor in irradiation intensity, easy to be seen, and high in missing inspection rate. If the intensity of the irradiating light is enhanced, a brighter lamp tube must be replaced, and if the brightness of the lamp tube is too high, the eyes of workers are greatly damaged, which is not beneficial to safety production; the detection method has high cost and low efficiency, and the packaging bag with the bulge cannot be found in time, thereby influencing the product quality and simultaneously causing the waste of food.
Therefore, traditional manual detection is replaced through equipment and an intelligent detection method, the food bag with the bulge bubbles is found quickly, the food bag is recycled and processed and packaged again in time, cost is reduced while detection efficiency is high, and food waste is avoided.
Disclosure of Invention
The invention aims to provide a vacuum food bulge detection device based on multi-line laser and a detection algorithm thereof, which replace the traditional manual detection by equipment and an intelligent detection method, judge the curvature of a laser line irradiated on a food packaging bag by a parallel laser lamp by using the vacuum food bulge algorithm, and judge whether the packaging bag contains a bubble bulge or not, thereby solving the problems of easy omission and low efficiency and high cost of the manual detection of the existing vacuum food packaging bag.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a vacuum food bulge detection device based on multi-line laser, which comprises a rack, a laser adjusting plate and a laser adjusting column, wherein the rack is erected above a conveyor belt; the n-shaped frame consists of an upper transverse plate, a vertical plate and a bottom plate; the upper surface of the upper transverse plate is provided with a chute; upright columns are arranged at two ends of the sliding chute; through holes are formed in two ends of the laser adjusting plate; the laser adjusting plate is sleeved on the upright post in a sliding manner through the through hole; the surface of the laser adjusting plate is provided with a plurality of through grooves; the through grooves are arranged according to a preset included angle and are distributed in a fan shape; the upper half part of one side surface of the laser adjusting column is provided with a roller; the roller is matched with the through groove in the surface of the laser adjusting plate; the lower half part of the opposite side surface of the laser adjusting column is provided with a clamping groove; a laser is fixedly arranged on the lower end face of the laser adjusting column; the clamping groove is clamped on one side wall of the sliding groove.
Preferably, the top ends of the vertical plates are respectively fixed on two sides of the upper transverse plate; a bottom plate is arranged at the bottom of the vertical plate; the bottom plate is fixed on two sides of the conveyor belt through bolts; the upper transverse plate spans over the conveyor belt.
Preferably, a high-speed camera is mounted on the inner wall of the vertical plate; the high-speed camera is connected with the control terminal through a data line; the control terminal is connected with the computer through a data line and is used for setting parameters of the high-speed camera and controlling shooting, image acquisition and storage of the high-speed camera through the computer terminal; the computer is used for extracting laser lines according to the collected pictures, rapidly judging whether the surface of the food packaging bag contains bubbles or bulges according to a vacuum food bulge algorithm, and timely informing the sound-light alarm device to give an alarm if the surface of the food packaging bag contains the bubbles or bulges.
Preferably, a graduated scale is arranged on the front side of the sliding chute.
Preferably, the number of the through grooves is odd, the middle through groove is vertically arranged, and the rest through grooves are symmetrically arranged at two sides of the middle through groove.
The invention relates to a vacuum food bulge detection algorithm based on multi-line laser, which comprises the following steps:
step S1: moving the laser adjusting plate up and down to adjust the distance among the plurality of lasers, the distance among the laser lines and the distance among the laser lines;
step S2: the control terminal sets the lens aperture size, the exposure time, the acquisition period and the acquisition frame rate of the high-speed camera;
step S3: the high-speed camera collects images of the vacuum food transported on the lower conveying belt and sends the collected images to the computer;
step S4: the computer quickly extracts the picture information acquired by the high-speed camera and starts a vacuum food bulging algorithm;
step S5: once the vacuum food is detected to have the bulge information, the audible and visual alarm gives an alarm.
Preferably, in step S4, a threshold and a sensitivity need to be set for the high-speed camera, the influence of wrinkles and calculation errors on the food packaging tape is eliminated, the target laser line is selected, an algorithm is started, and the curvature change of the plurality of laser lines in the picture is calculated to determine whether the surface of the food package is bulged.
Preferably, the vacuum food bulging algorithm comprises the following specific steps:
step G1, acquiring an image: acquiring a laser line image in a shot image;
step G2, image filtering: performing median filtering, mean filtering and boundary processing on the laser line image;
step G3, centerline extraction: calculating the light bands line by line, and taking the light band gray scale gravity center coordinate calculated by each line as the center coordinate to obtain the gray scale gravity center of the line;
step G4, calculating curvature radius: obtaining coordinates of a fixed point on the central line, and calculating the curvature radius of the point through a curvature radius formula;
step G5, final judgment: and obtaining the concave-convex condition of the surface of the vacuum food bag according to a preset reference table by the calculated curvature radius so as to judge whether the bulge exists or not.
The invention has the following beneficial effects:
(1) according to the invention, the bulge detection device is erected above the conveyor belt for transporting the food packaging bag, and the fan-shaped through groove group formed on the laser adjusting plate is matched with the roller of the laser adjusting column to lift the laser adjusting plate to change the intervals among the laser adjusting columns, so that the laser lines irradiated by the laser lamp on the food packaging bag are the same in interval, and the intervals of the laser lines on the food packaging bag can be rapidly adjusted aiming at the food packaging bags with different sizes, so that more laser lines are irradiated on the packaging bag, omission caused by too small bubbles in the packaging bag is avoided, and the detection quality is improved;
(2) according to the food packaging bag detection device, the pictures of the food packaging bag shot by the high-speed camera are collected and uploaded to the computer, the computer extracts a plurality of laser lines from the collected pictures, the curvature radius is calculated according to the extracted laser lines, if the laser lines are parallel, bubble bulge does not exist, if the calculated curvature radius exceeds a threshold value, the bubble bulge is proved to exist, an alarm is sent out through the audible and visual alarm in time, a worker is reminded to recover, process and package again, the detection efficiency is high, the cost is reduced, and food waste is avoided.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural view of a vacuum food bulge detection device based on multi-line laser according to the present invention;
FIG. 2 is a front view of FIG. 1;
FIG. 3 is a rear view of FIG. 1;
FIG. 4 is a schematic view of the laser adjustment plate in the raised state;
FIG. 5 is a front view of FIG. 4;
FIG. 6 is a schematic view of a laser adjustment plate;
FIG. 7 is a schematic view of a laser tuning post structure;
FIG. 8 is a diagram of steps of a vacuum food bulge detection algorithm based on multi-line laser;
FIG. 9 is a diagram of the steps of the vacuum food bulging algorithm;
FIG. 10 is laser line information collected by the high speed camera extracted by the computer under normal conditions;
FIG. 11 is laser line information collected by a high speed camera extracted by a computer in a bulge state;
FIG. 12 is a neighborhood graph after median filtering in the embodiment;
FIG. 13 is a neighborhood graph after the mean filtering process in the embodiment.
In the drawings, the components represented by the respective reference numerals are listed below:
1-conveyor belt, 2-model frame, 3-laser adjusting plate, 4-sliding chute, 5-upright post, 6-laser adjusting post, 7-high-speed camera, 8-graduated scale, 201-upper transverse plate, 202-vertical plate, 203-bottom plate, 301-through hole, 302-through groove, 601-roller, 602-clamping groove and 603-laser.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, the present invention relates to a vacuum food bulge detecting device based on multi-line laser, which comprises a frame 2 arranged above a conveyor belt 1, a laser adjusting plate 3 and a laser adjusting column 6,
the frame 2 is composed of an upper transverse plate 201, a vertical plate 202 and a bottom plate 203; the upper surface of the upper transverse plate 201 is provided with a chute 4; the two ends of the sliding groove 4 are provided with upright posts 5;
through holes 301 are formed at two ends of the laser adjusting plate 3; the laser adjusting plate 3 is sleeved on the upright post 5 in a sliding way through the through hole 301; the surface of the laser adjusting plate 3 is provided with a plurality of through grooves 302; the through grooves 302 are arranged at a preset included angle and are distributed in a fan shape;
the lift laser regulating plate 3 changes the interval between a plurality of laser regulating posts 6 to make laser 603 shine on food package bag laser line interval the same, and can adjust the interval of laser line on food package bag to the food package bag snap-on of equidimension not, make more laser lines shine on the wrapping bag, avoid in the wrapping bag because of the bubble is too little and omit, improved detection quality.
The upper half part of one side surface of the laser adjusting column 6 is provided with a roller 601; the roller 601 is matched with the through groove 302 on the surface of the laser adjusting plate 3; the lower half part of the opposite side surface of the laser adjusting column 6 is provided with a clamping groove 602; a laser 603 is fixedly arranged on the lower end face of the laser adjusting column 6; draw-in groove 602 joint is at a lateral wall of spout 4, at the in-process that laser adjusting plate 3 reciprocated, because gyro wheel 601 can with link up groove 302 and mutually support, utilize draw-in groove 602 joint at a lateral wall of spout 4, lead to laser to adjust post 6 and can not reciprocate, slide in link up groove 302 along with gyro wheel 601, laser is adjusted post 6 and can transversely remove in spout 4, thereby realize that the lateral motion of laser adjustment post 6 just keeps the interval between every laser adjustment post 6 the same all the time.
Wherein, the top ends of the vertical plates 202 are respectively fixed on both sides of the upper transverse plate 201; the bottom of the vertical plate 202 is provided with a bottom plate 203; the bottom plate 203 is fixed on both sides of the conveyor belt 1 through bolts; the upper cross plate 201 spans directly above the conveyor belt 1.
Wherein, a high-speed camera 7 is arranged on the inner wall of the vertical plate 202, the high-speed camera 7 is over against the irradiation area of the laser lamp, a certain shooting angle is formed at the same time, and after repeated tests, when the included angle between the high-speed camera 7 and the laser line is 45 degrees, the shooting effect is best, and the extracted laser line is clearest; the high-speed camera 7 is connected with the control terminal through a data line; the control terminal is connected with the computer through a data line and is used for setting parameters of the high-speed camera and controlling shooting, image acquisition and storage of the high-speed camera through the computer terminal; the computer is used for extracting laser lines according to the collected pictures, rapidly judging whether the surface of the food packaging bag contains bubbles or bulges according to a vacuum food bulge algorithm, and timely informing the sound-light alarm device to give an alarm if the surface of the food packaging bag contains the bubbles or bulges.
Wherein, the spout 4 front side is provided with scale 8, and scale 8 is used for measuring the distance between two laser regulation posts 6.
The number of the through grooves 302 is odd, the middle through groove is vertically arranged, the rest through grooves are symmetrically arranged on two sides of the middle through groove, the positions of the laser adjusting columns 6 in the middle through groove are always unchanged, but the laser adjusting columns 6 on two sides can move left and right along with the lifting of the laser adjusting plate 3, and the distance between every two laser adjusting columns 6 is ensured to be the same.
Referring to fig. 1-7, the present invention relates to a vacuum food bulge detection algorithm based on multi-line laser, comprising the following steps:
step S1: moving the laser adjusting plate up and down to adjust the distance among the plurality of lasers, the distance among the laser lines and the distance among the laser lines;
step S2: the control terminal sets the lens aperture size, the exposure time, the acquisition period and the acquisition frame rate of the high-speed camera;
step S3: the high-speed camera collects images of the vacuum food transported on the lower conveying belt and sends the collected images to the computer;
step S4: the computer quickly extracts the picture information acquired by the high-speed camera and starts a vacuum food bulging algorithm;
step S5: once the vacuum food is detected to have the bulge information, the audible and visual alarm gives an alarm.
In step S1, when the ambient light is strong, the laser line brightness of the laser may be adjusted to prevent the extracted laser line from being unclear.
In step S2, the capturing cycle of the high-speed camera is adjusted according to the transportation speed of the conveyor and the size of the food bag to be detected, so as to ensure that a picture is taken every time a food bag passes.
In step S4, a threshold and sensitivity need to be set for the high-speed camera, the influence of wrinkles and calculation errors on the food packaging tape is eliminated, a target laser line is selected, an algorithm is started, and curvature changes of a plurality of laser lines in a picture are calculated to determine whether bulges occur on the surface of the food package.
The vacuum food bulging algorithm comprises the following specific steps:
step G1, acquiring an image: acquiring a laser line image in a shot image;
step G2, image filtering: performing median filtering, mean filtering and boundary processing on the laser line image;
step G3, centerline extraction: calculating the light bands line by line, and taking the light band gray scale gravity center coordinate calculated by each line as the center coordinate to obtain the gray scale gravity center of the line;
step G4, calculating curvature radius: obtaining coordinates of a fixed point on the central line, and calculating the curvature radius of the point through a curvature radius formula;
step G5, final judgment: and obtaining the concave-convex condition of the surface of the vacuum food bag according to a preset reference table by the calculated curvature radius so as to judge whether the bulge exists or not.
One specific application of this embodiment is:
step G1: as shown in fig. 10 and 11, a laser image in the shot image is acquired;
step G2: performing median filtering, mean filtering and boundary processing on the laser line image;
the median filtering processing is a nonlinear smoothing technology, and the pixel value of each pixel point is set as the median of all pixel point pixel values in a certain neighborhood window of the point;
defining a domain window of a certain point (x, y) as I x j (generally, I is j and I is an odd number), arranging pixel values I (I, j) corresponding to each point in the neighborhood window in an ascending order or a descending order, calculating a median value of the neighborhood window, and replacing the value of a center point G (x, y) of the neighborhood window with the median value;
G(x,y)＝median[I(i,j)]；
as shown in fig. 12, the neighborhood size is 3 × 3, and the data is sorted in ascending order as follows: 144. 145, 146, 148, 150, 151, 250, the median value being 150, the value of the window center point being replaced by 150 for 250.
The mean filtering process is a linear filtering process, and the basic principle is to set the pixel value of each pixel point as the mean value of a certain neighborhood window at the point.
Defining a domain window of a certain point (x, y) as i x j (generally, i is j and i is an odd number), calculating the average value of all pixel values of the neighborhood window, and replacing the value of the center point G (x, y) of the neighborhood window with the average value;
as shown in fig. 13, the original data in fig. 12 are the same, and the mean value thereof is 159.44, and the value is rounded to 159 and replaces the window center point.
No matter which method is used for image filtering, a boundary is lack of a neighborhood. There are currently four methods for border handling:
1. no boundary processing is performed: the image boundary is not processed, namely the filter is not applied to the periphery of the image when the image is filtered, so that the periphery of the image is not changed;
2. filling 0: expanding the image boundary, and filling 0 in the expanded boundary;
3. fill in the most recent pixel value: similar to fill 0, except that the place filled with 0 is filled with the pixel value of the nearest pixel;
4. pixel values filling the other side: similar to the first two fills, the existing dots are copied to the corresponding locations on the other side when filling the data.
Step G3, centerline extraction: the time gray scale gravity center method adopted by the existing center line extraction is to calculate the light band line by line and take the coordinate of the gray scale gravity center of the light band calculated by each line as the coordinate of the center.
The light band in the image is arranged in the horizontal direction and the x-th row coordinate of the image is set to be (x, y) along the direction perpendicular to the light band (corresponding to the vertical direction of the image)i) The gray value corresponding to each point coordinate in the column is f (x, y)i) Where the variable i 1, 2.., M represents the column width. Let the threshold be T, all satisfy f (x, y)i) The set of i values > T is denoted as ROI; let the gray scale center of gravity of the column be (x, y)k)，ykThe calculation method of (c) is as follows:
the threshold T can be set in two ways, one is a fixed threshold, and the other is a dynamic threshold. The fixed threshold is a fixed value in which T is set to 0 to 255, and may be set to 50 in general. The dynamic threshold is to find the maximum gray value I of the kth columnkmaxIs shown bykmax80% (which can be adjusted according to actual needs) of the column is taken as a threshold value of the column, and is marked as Tk. If TkWhen the value is less than a preset value (the value is between 0 and 255), the gray scale gravity center of the row can be directly obtained; otherwise, the gray center of gravity of this column needs to be calculated.
It may also be processed after centerline extraction, i.e. the centerline is filtered. Centerline filtering currently provides two modes: mean filtering and median filtering. The principle of the two filtering modes is basically the same as that of image filtering, except that the size of a neighborhood window of a certain point (x, y) on a central line is set to be i x 1, and the original y is replaced by the mean value or the median value of the ordinate of the i points.
G3, calculating a curvature radius; after obtaining the coordinates of the surface center line of the vacuum food bag, fitting the coordinates into a one-dimensional quadratic equation:
Y＝a*X2+b*X+c；
parameters a, b, c are obtained.
Coordinate values at fixed points on the curve (depending on the shooting angle using Xmax, or Ymax) are acquired, and by a curvature radius formula:
the curvature radius of the point is calculated, the curvature radius reflects the concave-convex condition of the surface of the vacuum food bag, and the curvature radius can be used as a judgment basis for judging whether the bubble bulge exists or not.
The calculated curvature radius of the point judges whether a gas bulge exists or not, if the calculated curvature radius exceeds a threshold value, the bubble bulge does not exist, if the calculated curvature radius exceeds the threshold value, the bubble bulge is proved to exist, an alarm is given out through an audible and visual alarm in time, a worker is reminded to recover, process and pack again, the detection efficiency is high, meanwhile, the cost is reduced, and food waste is avoided.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. The utility model provides a vacuum food bulge detection device based on multi-thread laser, includes several types of frame (2), laser adjusting plate (3) and laser adjusting post (6) of erectting in conveyer belt (1) top, its characterized in that:
the n-shaped frame (2) is composed of an upper transverse plate (201), a vertical plate (202) and a bottom plate (203); the upper surface of the upper transverse plate (201) is provided with a sliding chute (4); upright posts (5) are arranged at two ends of the sliding chute (4);
through holes (301) are formed in two ends of the laser adjusting plate (3); the laser adjusting plate (3) is sleeved on the upright post (5) in a sliding manner through the through hole (301); the surface of the laser adjusting plate (3) is provided with a plurality of through grooves (302); the through grooves (302) are arranged according to a preset included angle and are distributed in a fan shape;
the upper half part of one side surface of the laser adjusting column (6) is provided with a roller (601); the roller (601) is matched with a through groove (302) on the surface of the laser adjusting plate (3); the lower half part of the opposite side surface of the laser adjusting column (6) is provided with a clamping groove (602); a laser (603) is fixedly arranged on the lower end face of the laser adjusting column (6); the clamping groove (602) is clamped on one side wall of the sliding groove (4).
2. The vacuum food bulge detection device based on the multi-line laser as claimed in claim 1, wherein the top ends of the vertical plates (202) are respectively fixed on two sides of the upper transverse plate (201); the bottom of the vertical plate (202) is provided with a bottom plate (203); the bottom plate (203) is fixed on two sides of the conveyor belt (1) through bolts; the upper transverse plate (201) spans over the conveyor belt (1).
3. The vacuum food bulge detection device based on the multi-line laser as claimed in claim 1, wherein the inner wall of the vertical plate (202) is provided with a high-speed camera (7); the high-speed camera (7) is connected with the control terminal through a data line; and the control terminal is connected with the computer through a data line.
4. Vacuum food bulge detection device based on multi-line laser according to claim 1, characterized in that a scale (8) is arranged at the front side of the chute (4).
5. The vacuum food bulge detection device based on the multi-line laser as claimed in claim 1, wherein the number of the through slots (302) is odd, and the middle through slot is vertically arranged.
6. A vacuum food bulge detection algorithm based on multi-line laser is characterized by comprising the following steps:
step S1: moving the laser adjusting plate up and down to adjust the distance among the plurality of lasers, the distance among the laser lines and the distance among the laser lines;
step S2: the control terminal sets the lens aperture size, the exposure time, the acquisition period and the acquisition frame rate of the high-speed camera;
step S3: the high-speed camera collects images of the vacuum food transported on the lower conveying belt and sends the collected images to the computer;
step S4: the computer quickly extracts the picture information acquired by the high-speed camera and starts a vacuum food bulging algorithm;
step S5: once the vacuum food is detected to have the bulge information, the audible and visual alarm gives an alarm.
7. The multi-line laser-based vacuum food bulge detection device algorithm as claimed in claim 6, wherein in step S4, threshold and sensitivity are required to be set for the high-speed camera, the effects of wrinkles and calculation errors on the food packaging tape are eliminated, the target laser line is selected, the algorithm is started, and the curvature change of the multiple laser lines in the picture is calculated to determine whether a bulge occurs on the surface of the food package.
8. The multi-line laser-based vacuum food bulge detection algorithm as claimed in claim 6 or 7, wherein the vacuum food bulge detection algorithm comprises the following specific steps:
step G1, acquiring an image: acquiring a laser line image in a shot image;
step G2, image filtering: performing median filtering, mean filtering and boundary processing on the laser line image;
step G3, centerline extraction: calculating the light bands line by line, and taking the light band gray scale gravity center coordinate calculated by each line as the center coordinate to obtain the gray scale gravity center of the line;
step G4, calculating curvature radius: obtaining coordinates of a fixed point on the central line, and calculating the curvature radius of the point through a curvature radius formula;
step G5, final judgment: and obtaining the concave-convex condition of the surface of the vacuum food bag according to a preset reference table by the calculated curvature radius so as to judge whether the bulge exists or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010893713.0A CN111982924A (en) | 2020-08-31 | 2020-08-31 | Vacuum food bulge detection device based on multi-line laser and detection algorithm thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010893713.0A CN111982924A (en) | 2020-08-31 | 2020-08-31 | Vacuum food bulge detection device based on multi-line laser and detection algorithm thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111982924A true CN111982924A (en) | 2020-11-24 |
Family
ID=73440405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010893713.0A Withdrawn CN111982924A (en) | 2020-08-31 | 2020-08-31 | Vacuum food bulge detection device based on multi-line laser and detection algorithm thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111982924A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116529590A (en) * | 2021-11-30 | 2023-08-01 | 宁德时代新能源科技股份有限公司 | Machine vision detection method, detection device and detection system thereof |
| CN120008512A (en) * | 2025-04-22 | 2025-05-16 | 杭州非白三维科技有限公司 | An automated detection method and system based on multi-line laser fusion |
-
2020
- 2020-08-31 CN CN202010893713.0A patent/CN111982924A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116529590A (en) * | 2021-11-30 | 2023-08-01 | 宁德时代新能源科技股份有限公司 | Machine vision detection method, detection device and detection system thereof |
| US12437461B2 (en) | 2021-11-30 | 2025-10-07 | Contemporary Amperex Technology (Hong Kong) Limited | Machine vision detection method, detection device thereof, and detection system thereof |
| CN120008512A (en) * | 2025-04-22 | 2025-05-16 | 杭州非白三维科技有限公司 | An automated detection method and system based on multi-line laser fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111982924A (en) | Vacuum food bulge detection device based on multi-line laser and detection algorithm thereof | |
| CN105548201B (en) | A kind of battery welding cap visible detection method | |
| CN110935644A (en) | A machine vision-based bearing needle roller size detection system and method | |
| KR101703542B1 (en) | Automatic sorting method of sea-squirt using feature measurement and HSV color model | |
| CN111545483A (en) | A chopsticks sorting detection device and its detection algorithm | |
| CN207071548U (en) | The hierarchical detection equipment and fruit grading system of fruit | |
| CN113426693B (en) | A kind of fruit multi-stage screening device and screening method | |
| CN210534021U (en) | Inductance outward appearance detecting system | |
| Tran et al. | Physical characteristics estimation for irregularly shaped fruit using two cameras | |
| CN108020564A (en) | Pulp goods detection method of surface flaw | |
| CN206778968U (en) | A kind of detection of bubble-cap capsule board containing capsule and rejecting machine | |
| CN109596620A (en) | Product surface shape defect detection method and system based on machine vision | |
| CN111562260A (en) | Lotus root mud hole detection method and device based on machine vision | |
| CN115471455A (en) | A method and device for detecting pipe defects based on backlight images | |
| CN212568453U (en) | Fruit maturity detection device | |
| CN117934459B (en) | Food material encapsulation opening defect detection method | |
| CN118172359B (en) | Visual detection method and system for food package air tightness | |
| CN116735122B (en) | Packaging bag air tightness detection equipment and detection method thereof | |
| CN114082675A (en) | Automatic grading device for waxberry quality detection and grading method thereof | |
| CN106586135B (en) | A kind of product packing box date of manufacture spray printing defective products elimination method | |
| CN114082676A (en) | An automatic screening device for fried products based on visual sensing detection function | |
| CN114792369B (en) | Cigarette carton filling state detection method and system based on light projection | |
| CN215664336U (en) | Shrimp tail size separation device | |
| CN110624842B (en) | Dual-camera knitting needle vision detection system | |
| CN220843266U (en) | Automatic sorting line piece tobacco strip missing removing system |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201124 |
|
| WW01 | Invention patent application withdrawn after publication |