CN114612426B - A quality detection method for electric wires used to protect wild animals - Google Patents
A quality detection method for electric wires used to protect wild animals Download PDFInfo
- Publication number
- CN114612426B CN114612426B CN202210232940.8A CN202210232940A CN114612426B CN 114612426 B CN114612426 B CN 114612426B CN 202210232940 A CN202210232940 A CN 202210232940A CN 114612426 B CN114612426 B CN 114612426B
- Authority
- CN
- China
- Prior art keywords
- point
- image
- defining
- points
- bean
- 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
- 238000001514 detection method Methods 0.000 title abstract description 30
- 241001465754 Metazoa Species 0.000 title abstract description 16
- 244000046052 Phaseolus vulgaris Species 0.000 abstract description 23
- 235000010627 Phaseolus vulgaris Nutrition 0.000 abstract description 23
- 239000003292 glue Substances 0.000 abstract description 21
- 238000000926 separation method Methods 0.000 abstract description 8
- 238000000034 method Methods 0.000 abstract description 6
- 238000007781 pre-processing Methods 0.000 abstract description 5
- 229910003460 diamond Inorganic materials 0.000 description 10
- 239000010432 diamond Substances 0.000 description 10
- 238000007689 inspection Methods 0.000 description 9
- 102000001332 SRC Human genes 0.000 description 6
- 108060006706 SRC Proteins 0.000 description 6
- 238000012937 correction Methods 0.000 description 6
- 230000007797 corrosion Effects 0.000 description 6
- 238000005260 corrosion Methods 0.000 description 6
- 230000007812 deficiency Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000007547 defect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 244000068988 Glycine max Species 0.000 description 3
- 235000010469 Glycine max Nutrition 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 101100332287 Dictyostelium discoideum dst2 gene Proteins 0.000 description 2
- 101100332288 Dictyostelium discoideum dst3 gene Proteins 0.000 description 2
- 101100278585 Dictyostelium discoideum dst4 gene Proteins 0.000 description 2
- 101000912503 Homo sapiens Tyrosine-protein kinase Fgr Proteins 0.000 description 2
- 101100264226 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) XRN1 gene Proteins 0.000 description 2
- 102100026150 Tyrosine-protein kinase Fgr Human genes 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 101150090341 dst1 gene Proteins 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- UPBAOYRENQEPJO-UHFFFAOYSA-N n-[5-[[5-[(3-amino-3-iminopropyl)carbamoyl]-1-methylpyrrol-3-yl]carbamoyl]-1-methylpyrrol-3-yl]-4-formamido-1-methylpyrrole-2-carboxamide Chemical compound CN1C=C(NC=O)C=C1C(=O)NC1=CN(C)C(C(=O)NC2=CN(C)C(C(=O)NCCC(N)=N)=C2)=C1 UPBAOYRENQEPJO-UHFFFAOYSA-N 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种用于防护野生动物的通电网具的质量检测方法。属于计算机视觉目标检测领域。本发明包括图像预处理，得到目标图像集DST；分别对图像集DST中的每个图像DST进行BLOB检测，并进一步去除干扰点得到通电网交叉点集POINTS；中心校准,得到点集CaliPoints；基于校准前后的点集POINTS与CaliPoints点集进行溢胶判断；分列处理，得到分列后的列集ClasPoints；基于目标图像集DST与列集ClasPoints，使用缺豆识别算法进行缺豆判断。本用于防护野生动物的通电网具的质量检测方法，大大缩减通电网制网完整流程的时长，大大减小了人力成本，提高了企业制网效率。
The present invention discloses a quality detection method for an electric grid for protecting wild animals. The method belongs to the field of computer vision target detection. The present invention includes image preprocessing to obtain a target image set DST; performing BLOB detection on each image DST in the image set DST respectively, and further removing interference points to obtain an electric grid intersection point set POINTS; center calibration to obtain a point set CaliPoints; performing glue overflow judgment based on the point set POINTS and the CaliPoints point set before and after calibration; column separation to obtain a column set ClasPoints after separation; and using a bean shortage recognition algorithm to perform bean shortage judgment based on the target image set DST and the column set ClasPoints. The quality detection method for electric grid for protecting wild animals greatly shortens the duration of the complete process of electric grid making, greatly reduces labor costs, and improves the efficiency of enterprise net making.
Description
Technical Field
The invention belongs to the technical field of computer vision target detection, and relates to a power grid detection system, in particular to a quality detection method of an electrified netting gear for protecting wild animals.
Background
The electrified netting gear is often used for enclosing and protecting wild animals, and when the netting gear is used, fixed voltage is connected to two ends of the netting gear. In the manufacturing process, a machine is required to melt, weld and fix the cross part of the net wires by using plastic, and the volume of the glue points is stable. In the production process, the glue points are possibly too small or have no glue points due to certain reasons, and the situation is called 'bean shortage', and the situation is called 'glue overflow' due to the fact that the glue points overflow after the high-temperature pressurization of the machine due to more plastic injection. The lack of beans can cause the net to fail to achieve the expected effect, and the overflow of glue can cause the break of the electrified wires in the net.
The Chinese patent No. CN206627450U provides a fishing net quality inspection device, which comprises a net placing roller, a transmission roller, a net collecting roller, a baffle plate and a base, wherein the net placing roller, the transmission roller and the net collecting roller are arranged on the base, the baffle plate is positioned between the net placing roller and the net collecting roller, the surface of the baffle plate is black, the transmission roller is positioned above the baffle plate, and the net placing roller, the transmission roller and the net collecting roller are mutually parallel. According to the fishing net quality inspection device provided by the utility model, the black baffle is arranged below the transmission roller and is used as a background of the fishing net, so that the fishing net is strongly compared with the baffle. The quality inspection device for the fishing net can easily find whether the fishing net has defects or not when inspected, reduce the occurrence of missed inspection and false inspection, improve the quality inspection efficiency, reduce the direct light irradiation of the baffle plate, and effectively relieve the eye fatigue of the quality inspection personnel.
The invention discloses a machine vision-based three-dimensional network defect online detection system, which comprises a front light source, a front camera, a back position sensor, a back light source, a back camera, a photoelectric encoder, a first conveyor mechanism, a second conveyor mechanism, a frame, a control platform, an alarm indication module, a display module, a control button and a main control system, wherein the front position sensor, the front light source, the front camera, the back position sensor, the back light source, the back camera and the photoelectric encoder are all fixed on the frame, and the position sensor is higher than the upper plane of the first conveyor mechanism and the second conveyor mechanism.
Disclosure of Invention
Aiming at the defects, the invention provides a quality detection method for the electrified netting gear for protecting wild animals, which is used for carrying out defect detection on the electrified netting gear in real time after an image is input through a camera and is processed through an algorithm, so that manual errors are reduced, and the operation efficiency is improved.
The aim of the invention can be achieved by the following technical scheme:
A quality detection method for an energized netting gear for protecting wild animals, comprising the steps of:
S1, image preprocessing:
sequentially carrying out graying, opening operation, thresholding and corrosion expansion pretreatment operation on an original image set SRC of an input electrified netting gear to obtain a target image set DST;
s2, extracting a point set:
performing BLOB detection on each image DST in the image set DST, and further removing interference POINTS to obtain a power-on network cross point set POINTS;
s3, center calibration:
On the basis of the open operation image, carrying out center calibration on the point set POINTS by adopting a diamond shape fitting algorithm to obtain a point set CaliPoints after center calibration;
S4, judging glue overflow:
Glue overflow judgment is carried out based on point sets POINTS and CaliPoints point sets before and after calibration;
s5, column separation processing:
performing column separation processing on the CaliPoints point sets to obtain column sets ClasPoints after column separation;
S6, judging the bean shortage:
based on the target image set DST and the column set ClasPoints, a bean deficiency identification algorithm is used for bean deficiency judgment.
In the above method for detecting the quality of the electrified netting gear for protecting wild animals, in step S1, the data preprocessing operation for the input data includes the following steps:
Firstly, defining an input picture set SRC= { SRC1, SRC2, sre, SRC4}, a counter of i=1, corrosion times T1 and T2, dividing line coordinates x= { x1, x2, x3, x4}, a threshold balance factor thresh, a threshold T= { T1, T2, T3, T4}, a preprocessed target image set DST { DST1, DST2, DST3, DST4} variable gay, variable morphology, variable temp, variable threshold, variable left, variable right;
(1) Converting SRC into gray image gray, performing open operation on the gray by using an OpenCV library to obtain an image morphology, traversing all pixel points of the image morphology, calculating the average gray value and the minimum gray value of the image, and taking the average value of the average gray value and the minimum gray value to obtain temp;
(2) The threshold balance factors thresh and temp are summed to obtain a threshold t, then thresholding is carried out on the image morphology to obtain an image threshold1, and the threshold is cut and divided into an image left and right by using an OpenCV library with an abscissa x1 as a dividing line;
(3) Respectively carrying out corrosion operations with times of t1 and t2 on et and right, and then respectively carrying out expansion operations with the same times to obtain treated et and right;
(4) And transversely splicing the let and the right to obtain a preprocessed target image DST, and outputting a target image set DST.
In the above-mentioned quality detection method of the power-on net for protecting wild animals, in step S3, the performing of the center calibration operation on the preprocessed data includes the following processes:
center correction is carried out by using a diamond shape fitting algorithm, and the specific steps of obtaining the corrected point set CaliPoints are as follows:
(1) Firstly, defining a detection radius, defining a detection termination coordinate as (x, y), defining a calibrated point as cp, defining a coordinate as (cpx, cpy), defining a point gray value threshold pthresh, defining a calibrated point set as CaliPoints, wherein CaliPoints = { cp 1,cp2,…,cpn }, and defining a counter i=1;
(2) Defining a diamond with coordinates (pxi-radius,pyi),(pxi,pyi-radius),(pxi+radius,pyi),(pxi,pyi+radius) as vertexes, wherein all points on the edge of the diamond form a set { pt i1,pti2,…,ptim }, wherein the coordinate of the jth point is (ptx ij,ptyij), the gray value of the point is grey ptxik,ptyik, and defining a point counter k=1 on the edge point set;
(3) Under the combined action of the detector and the diamond fitting algorithm, the counter and gray value characteristics are compared, algorithm screening is carried out, and a calibrated point set CaliPoints is obtained.
In the above quality detection method of the power-on net for protecting wild animals, in step S4, the operation of determining glue overflow on data includes the following steps:
the specific steps for glue overflow judgment based on point sets POINTS and CaliPoints before and after correction are as follows:
(1) Defining a glue overflow threshold overThresh, defining a point counter as i=1, and calculating from point sets before and after correction respectively;
(cpxi-pxi)2+(cpyi-pyi)2≤overThresh
(2) The result is WrongType less than the threshold value being "flash" otherwise no "flash" problem is considered.
In the above quality detection method of the electrified netting gear for protecting wild animals, in step S6, the operation of determining the missing beans includes the following steps:
(1) Defining the column set identified in step S3 as ClasPoints = { col 1,col2,…,coln }, wherein col i＝{pointi1,pointi2,…,pointij }, the ordinate of sum i,pointik being py ik, defining the average distance as average, the total point sum, the short bean distance threshold thresh=1.3×average;
(2) Ordering all points in col from small to large by taking the ordinate as the reference, and recording the result as col;
(3) And judging whether the soybean is short according to the soybean shortage distance threshold value, judging WrongType to be ' short ' if empy-py i1 > thresh, and judging that the soybean is not short ' if not.
Compared with the prior art, the quality detection method for the electrified netting gear for protecting wild animals has the following beneficial effects:
The invention preprocesses the electrified netting gear image, solves the problem of netting wire interference in the acquired image and the problem of larger gray value difference of glue points caused by uneven illumination. And then performing BLOB detection and interference elimination treatment, and finally performing glue overflow and bean deficiency judgment on the image. Through such circular telegram netting gear quality detection step, reduce the duration of the complete flow of system net greatly, show to have reduced the human cost, avoid the overflow that the manual inspection error leads to or lack the beans, improved enterprise system net efficiency and precision.
Drawings
FIG. 1 is a flow chart of the operation of the method for detecting the quality of an energized netting gear for protecting wild animals.
Detailed Description
The following description of the embodiments of the invention will be given with reference to the accompanying drawings and examples:
the invention provides a comprehensive analysis and detection method, which is used for detecting the quality of an electrified net tool in real time, finding defects and timely sending information to a production line control system.
As shown in fig. 1, the quality detection method of the electrified netting gear for protecting wild animals comprises the following steps:
S1, image preprocessing:
sequentially carrying out graying, opening operation, thresholding and corrosion expansion pretreatment operation on an original image set SRC of an input electrified netting gear to obtain a target image set DST;
The data preprocessing operation for the input data comprises the following processes:
Firstly, defining an input picture set SRC= { SRC1, SRC2, sre, SRC4}, a counter of i=1, corrosion times T1 and T2, dividing line coordinates x= { x1, x2, x3, x4}, a threshold balance factor thresh, a threshold T= { T1, T2, T3, T4}, a preprocessed target image set DST { DST1, DST2, DST3, DST4} variable gay, variable morphology, variable temp, variable threshold, variable left, variable right;
(1) Converting SRC into gray image gray, performing open operation on the gray by using an OpenCV library to obtain an image morphology, traversing all pixel points of the image morphology, calculating the average gray value and the minimum gray value of the image, and taking the average value of the average gray value and the minimum gray value to obtain temp;
(2) The threshold balance factors thresh and temp are summed to obtain a threshold t, then thresholding is carried out on the image morphology to obtain an image threshold1, and the threshold is cut and divided into an image left and right by using an OpenCV library with an abscissa x1 as a dividing line;
(3) Respectively carrying out corrosion operations with times of t1 and t2 on et and right, and then respectively carrying out expansion operations with the same times to obtain treated et and right;
(4) And transversely splicing the let and the right to obtain a preprocessed target image DST, and outputting a target image set DST.
S2, extracting a point set:
and (3) performing BLOB detection on each image DST in the image set DST respectively, and further removing interference POINTS to obtain a power-on network cross point set POINTS.
S3, center calibration:
On the basis of the open operation image, carrying out center calibration on the point set POINTS by adopting a diamond shape fitting algorithm to obtain a point set CaliPoints after center calibration;
Performing a center calibration operation on the pre-processed data includes the following:
center correction is carried out by using a diamond shape fitting algorithm, and the specific steps of obtaining the corrected point set CaliPoints are as follows:
(1) Firstly, defining a detection radius, defining a detection termination coordinate as (x, y), defining a calibrated point as cp, defining a coordinate as (cpx, cpy), defining a point gray value threshold pthresh, defining a calibrated point set as CaliPoints, wherein CaliPoints = { cp 1,cp2,…,cpn }, and defining a counter i=1;
(2) Defining a diamond with coordinates (pxi-radius,pyi),(pxi,pyi-radius),(pxi+radius,pyi),(pxi,pyi+radius) as vertexes, wherein all points on the edge of the diamond form a set { pt i1,pti2,…,ptim }, wherein the coordinate of the jth point is (ptx ij,ptyij), the gray value of the point is grey ptxik,ptyik, and defining a point counter k=1 on the edge point set;
(3) Under the combined action of the detector and the diamond fitting algorithm, the counter and gray value characteristics are compared, algorithm screening is carried out, and a calibrated point set CaliPoints is obtained.
S4, judging glue overflow:
Glue overflow judgment is carried out based on point sets POINTS and CaliPoints point sets before and after calibration;
The glue overflow judging operation for the data comprises the following steps:
the specific steps for glue overflow judgment based on point sets POINTS and CaliPoints before and after correction are as follows:
(1) Defining a glue overflow threshold overThresh, defining a point counter as i=1, and calculating from point sets before and after correction respectively;
(cpxi-pxi)2+(cpyi-pyi)2≤overThresh
(2) The result is WrongType less than the threshold value being "flash" otherwise no "flash" problem is considered.
S5, column separation processing:
and carrying out column separation processing on the CaliPoints point sets to obtain column sets ClasPoints after column separation.
S6, judging the bean shortage:
based on the target image set DST and the column set ClasPoints, a bean deficiency identification algorithm is used for bean deficiency judgment.
The bean missing operation determined by the data comprises the following steps:
(1) Defining the column set identified in step S3 as ClasPoints = { col 1,col2,…,coln }, wherein col i＝{pointi1,pointi2,…,pointij }, the ordinate of sum i,pointik being py ik, defining the average distance as average, the total point sum, the short bean distance threshold thresh=1.3×average;
(2) Ordering all points in col from small to large by taking the ordinate as the reference, and recording the result as col;
(3) Also, judging whether the bean is short according to the threshold value of the distance between the bean and the bean, if empy-py i1 > thresh
Then decision WrongType is "lack beans", otherwise it is determined that there is no "lack beans" problem.
Compared with the prior art, the quality detection method for the electrified netting gear for protecting wild animals has the following beneficial effects:
The invention preprocesses the electrified netting gear image, solves the problem of netting wire interference in the acquired image and the problem of larger gray value difference of glue points caused by uneven illumination. And then performing BLOB detection and interference elimination treatment, and finally performing glue overflow and bean deficiency judgment on the image. Through such circular telegram netting gear quality detection step, reduce the duration of the complete flow of system net greatly, show to have reduced the human cost, avoid the overflow that the manual inspection error leads to or lack the beans, improved enterprise system net efficiency and precision.
It should be understood that the above description is not intended to limit the invention to the particular embodiments disclosed, but to limit the invention to the particular embodiments disclosed, and that the invention is not limited to the particular embodiments disclosed, but is intended to cover modifications, adaptations, additions and alternatives falling within the spirit and scope of the invention.
Claims (2)
1. A quality detection method for an energized netting gear for protecting wild animals, comprising the steps of:
S1, image preprocessing:
sequentially carrying out graying, opening operation, thresholding and corrosion expansion pretreatment operation on an original image set SRC of an input electrified netting gear to obtain a target image set DST;
s2, extracting a point set:
performing BLOB detection on each image DST in the image set DST, and further removing interference POINTS to obtain a power-on network cross point set POINTS;
s3, center calibration:
On the basis of the open operation image, carrying out center calibration on the point set POINTS by adopting a diamond shape fitting algorithm to obtain a point set CaliPoints after center calibration;
center correction is carried out by using a diamond shape fitting algorithm, and the specific steps of obtaining the corrected point set CaliPoints are as follows:
(1) Firstly, defining a detection radius, defining a calibrated point as cp, defining a point gray value threshold pthresh by using coordinates (cpx, cpy), defining a set of all calibrated points as CaliPoints, wherein CaliPoints = { cp 1,cp2,…,cpn }, and defining a counter i=1;
(2) Defining diamond with coordinates (pxi-radius,pyi),(pxi,pyi-radius),(pxi+radius,pyi),(pxi,pyi+radius) as vertexes, wherein all points on the edge of the diamond form a set { pt i1,pti2,…,ptim }, wherein the coordinate of the jth point is (ptx ij,ptyij), and the gray value of the point is Defining a point counter k=1 on the edge point set;
(3) Under the combined action of the detector and the diamond fitting algorithm, the counter and gray value characteristics are compared, algorithm screening is carried out, and a calibrated point set CaliPoints is obtained;
S4, judging glue overflow:
Glue overflow judgment is carried out based on point sets POINTS and CaliPoints point sets before and after calibration;
In step S4, the step of determining the overflow operation for the data includes the following steps:
the specific steps for glue overflow judgment based on point sets POINTS and CaliPoints before and after correction are as follows:
(1) Defining a glue overflow threshold overThresh, defining a point counter as i=1, and calculating from point sets before and after correction respectively;
(cpxi-pxi)2+(cpyi-pyi)2≤overThresh
(2) The result is WrongType less than the threshold is "glue overflow", otherwise, no "glue overflow" problem is considered;
s5, column separation processing:
performing column separation processing on the CaliPoints point sets to obtain column sets ClasPoints after column separation;
S6, judging the bean shortage:
Based on the target image set DST and the list set ClasPoints, carrying out bean deficiency judgment by using a bean deficiency identification algorithm;
the bean missing operation determined by the data comprises the following steps:
(1) Defining the column set identified in step S3 as ClasPoints = { col 1,col2,…,coln }, wherein col i＝{pointi1,pointi2,…,pointij }, the ordinate of sum i,pointik being py i,k, defining the average distance as average, the total point sum, the short bean distance threshold thresh=1.3×average;
(2) Ordering all points in col from small to large by taking the ordinate as the reference, and recording the result as col;
(3) Also, judging whether the bean is short according to the threshold value of the distance between the bean and the bean, if empy-py i1 > thresh
Then decision WrongType is "lack beans" or else it is determined that there is no "lack beans" problem,
For every two adjacent points in col i, if the difference between their ordinate satisfies py i,k+1-pyi,k > thresh, then it is determined WrongType to be a bean deficiency.
2. The method for detecting the quality of an energized netting gear for protecting wild animals according to claim 1, characterized in that in step S1, the data preprocessing operation of the input data comprises the following steps:
Firstly, defining an input picture set SRC= { SRC1, SRC2, sre, SRC4}, a counter of i=1, corrosion times T1 and T2, dividing line coordinates x= { x1, x2, x3, x4}, a threshold balance factor thresh, a threshold T= { T1, T2, T3, T4}, a preprocessed target image set DST { DST1, DST2, DST3, DST4} variable gay, variable morphology, variable temp, variable threshold, variable left, variable right;
(1) Converting SRC into gray image gray, performing open operation on the gray by using an OpenCV library to obtain an image morphology, traversing all pixel points of the image morphology, calculating the average gray value and the minimum gray value of the image, and taking the average value of the average gray value and the minimum gray value to obtain temp;
(2) The threshold balance factors thresh and temp are summed to obtain a threshold t, then thresholding is carried out on the image morphology to obtain an image threshold1, and the threshold is cut and divided into an image left and right by using an OpenCV library with an abscissa x1 as a dividing line;
(3) Respectively carrying out corrosion operations with times of t1 and t2 on left and right, and then respectively carrying out expansion operations with the same times to obtain treated left and right;
(4) Transversely splicing left and right to obtain a preprocessed target image DST, and outputting a target image set DST.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210232940.8A CN114612426B (en) | 2022-03-09 | 2022-03-09 | A quality detection method for electric wires used to protect wild animals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210232940.8A CN114612426B (en) | 2022-03-09 | 2022-03-09 | A quality detection method for electric wires used to protect wild animals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114612426A CN114612426A (en) | 2022-06-10 |
| CN114612426B true CN114612426B (en) | 2024-12-10 |
Family
ID=81860384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210232940.8A Active CN114612426B (en) | 2022-03-09 | 2022-03-09 | A quality detection method for electric wires used to protect wild animals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114612426B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358597A (en) * | 2017-05-24 | 2017-11-17 | 上海视马艾智能科技有限公司 | A kind of glue point method of inspection and device |
| CN112666180A (en) * | 2020-12-23 | 2021-04-16 | 浙江大学 | Automatic dispensing detection method and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170147991A1 (en) * | 2015-11-23 | 2017-05-25 | CSI Holdings I LLC | Vehicle damage report |
| CN110021012B (en) * | 2019-03-27 | 2023-09-26 | 安徽皓视光电科技有限公司 | Mobile phone lens window glass defect detection method based on machine vision technology |
| CN112950604B (en) * | 2021-03-12 | 2022-04-19 | 深圳市鑫路远电子设备有限公司 | Information processing method and system for precise dispensing |
| CN113192061B (en) * | 2021-05-25 | 2023-08-29 | 安徽睿微信息科技有限公司 | Extraction method and device of LED package appearance detection image, electronic equipment and storage medium |
| CN113628161B (en) * | 2021-07-06 | 2024-09-06 | 深圳市格灵精睿视觉有限公司 | Defect detection method, device and computer readable storage medium |
| CN114018946B (en) * | 2021-10-20 | 2023-02-03 | 武汉理工大学 | A detection method for highly reflective bottle cap defects based on OpenCV |
-
2022
- 2022-03-09 CN CN202210232940.8A patent/CN114612426B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358597A (en) * | 2017-05-24 | 2017-11-17 | 上海视马艾智能科技有限公司 | A kind of glue point method of inspection and device |
| CN112666180A (en) * | 2020-12-23 | 2021-04-16 | 浙江大学 | Automatic dispensing detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114612426A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492291B (en) | CNN segmentation-based solar photovoltaic silicon wafer defect detection system and method | |
| CN118608504A (en) | A method and system for detecting component surface quality based on machine vision | |
| CN106568783A (en) | Hardware part defect detecting system and method | |
| CN113608378A (en) | Full-automatic defect detection method and system based on LCD (liquid crystal display) process | |
| CN111310826A (en) | Method and device for detecting labeling abnormity of sample set and electronic equipment | |
| CN113012157B (en) | Visual detection method and system for equipment defects | |
| CN116385353B (en) | A camera module anomaly detection method | |
| CN114627122A (en) | Defect detection method and device | |
| CN114612426B (en) | A quality detection method for electric wires used to protect wild animals | |
| CN112329845B (en) | Method and device for changing paper money, terminal equipment and computer readable storage medium | |
| CN118570648A (en) | Cotton grading detection method and system based on machine vision | |
| CN118822940A (en) | Defect detection methods, devices, media, products and equipment | |
| CN111047550A (en) | Product abnormity detection method, device and equipment based on machine vision | |
| CN105427295A (en) | Welding seam based image identification method and image identification system | |
| CN117853434A (en) | Fiber prepreg crack defect detection method and system based on OpenCV | |
| CN112686851B (en) | Image detection method, device and storage medium | |
| JP2022187282A (en) | Inspection device, inspection method, glass plate manufacturing method, and inspection program | |
| CN117420152B (en) | Visual inspection method, visual inspection device, computer equipment and computer readable storage medium | |
| TW202222030A (en) | Method, computer program, and computer readable medium of using electroluminescence images to identify defect of photovoltaic module based on deep learning technology | |
| CN117409332B (en) | Long wood shaving appearance data detection system and method based on big data processing | |
| CN119228791B (en) | Board detection method and system based on visual recognition | |
| CN117817211B (en) | Welding automation control method and system based on machine vision | |
| CN118096751B (en) | Injection molding appearance defect detection method and device, electronic equipment and storage medium | |
| CN119671981A (en) | Medicine logistics management device and method based on machine vision | |
| CN118735875A (en) | AI visual inspection method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |