CN113516610A - Workpiece detection counting method based on industrial vision - Google Patents
Workpiece detection counting method based on industrial vision Download PDFInfo
- Publication number
- CN113516610A CN113516610A CN202010232257.5A CN202010232257A CN113516610A CN 113516610 A CN113516610 A CN 113516610A CN 202010232257 A CN202010232257 A CN 202010232257A CN 113516610 A CN113516610 A CN 113516610A
- Authority
- CN
- China
- Prior art keywords
- image
- counting
- detection
- workpiece
- workpieces
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000010191 image analysis Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000007547 defect Effects 0.000 claims description 17
- 230000002950 deficient Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 230000000717 retained effect Effects 0.000 claims description 4
- 230000035939 shock Effects 0.000 claims description 3
- 241000282414 Homo sapiens Species 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
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
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
- G06T2207/30242—Counting objects in image
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
The invention discloses a workpiece detection counting method based on industrial vision in the technical field of workpiece detection, which comprises a standard detection image input detection system, a counting module and a counting module, wherein workpieces to be detected are divided into a plurality of groups and are placed on an automatic detection line in a non-overlapping manner; the automatic detection line conveys the workpiece group to be detected to a first image acquisition position, and a first industrial camera acquires a workpiece group detection image; the detection image is preprocessed by an image processing module of the detection system and then analyzed by an image analysis module to obtain a result, and a detection system execution module rejects or retains the workpieces in the workpiece group according to the detection result; conveying the reserved workpieces to a second image acquisition position through an automatic detection line, and acquiring counting images by a second industrial camera; the collected counting image is processed by a counting system to obtain the number of workpieces, and the number is accumulated on the generated numerical value; the counted workpieces are conveyed to the next process by the automatic detection line, the detection precision and speed are improved, the counting is automatic, and the counting is accurate and rapid.
Description
Technical Field
The invention relates to the technical field of workpiece detection, in particular to a workpiece detection counting method based on industrial vision.
Background
Industrial product detection is a key link in quality control of industrial products. At present, product detection mainly depends on a manual detection method, however, the method is low in production efficiency, and the consistency of detection results is poor due to factors such as human visual fatigue and subjective judgment. Especially, with the continuous improvement of the automation degree of the production process, the manual detection can not meet the requirements of the current industrial field on efficiency, precision and the like. The industrial product quality detection based on the machine vision technology has the advantages of high detection speed, low cost, reliable detection result and the like, so that the method is widely applied to the industrial product quality detection. In modern industrial mass production, many emerging industries place higher demands on detection. For example, inspection of parts in an industrial production line, inspection of product package printing, real-time image monitoring, inspection of semiconductor chip packaging, positioning of printed circuit boards, and the like. In these applications, it has been difficult to meet the needs of productive life using traditional manual detection methods, which has limited the development and improvement of productivity levels. On the one hand, due to the nature of human beings, fatigue is easy to generate after long-time work, and high detection accuracy cannot be guaranteed. On the other hand, it is difficult to improve the speed, accuracy, and the like due to the physiological limit of human eyes. In the production of industrial enterprises, the components of a production line need to be automatically counted in real time, and the counting precision is required to reach one hundred percent in some occasions. At present, many enterprises still adopt manual counting, and the counting mode is not only complicated in task and low in working efficiency, but also easily causes counting errors due to human fatigue and other factors.
Based on the technical scheme, the invention designs a workpiece detection and counting method based on industrial vision to solve the problems.
Disclosure of Invention
The invention aims to provide a workpiece detecting and counting method based on industrial vision, which aims to solve the problems that the manual work in the background art is easy to generate fatigue, the high detection accuracy cannot be ensured, and the speed, the precision and the like are difficult to improve.
In order to achieve the purpose, the invention provides the following technical scheme:
a workpiece detection counting method based on industrial vision comprises the following steps:
s1: zeroing a counting system, inputting a standard detection image into a detection system, dividing the workpieces to be detected into a plurality of groups, and placing the groups on an automatic detection line in a non-overlapping manner;
s2: the automatic detection line conveys the workpiece group to be detected to a first image acquisition position, and a first industrial camera acquires a workpiece group detection image;
s3: the detection image is preprocessed by an image processing module of the detection system and then analyzed by an image analysis module to obtain a result, and a detection system execution module rejects or retains the workpieces in the workpiece group according to the detection result;
s4: conveying the reserved workpieces to a second image acquisition position through an automatic detection line, and acquiring counting images by a second industrial camera;
s5: the collected counting image is processed by a counting system to obtain the number of workpieces, and the number is accumulated on the generated numerical value;
s6: and conveying the counted workpieces to the next process by the automatic detection line.
Preferably, in S1, the workpieces to be detected are manually or mechanically divided into the same number of workpiece groups to be detected, and are placed in the conveying box without overlapping and conveyed to the next process by the automatic detection line.
Preferably, in S2, the detection image is an image of a workpiece group to be detected, and the first industrial camera is a CCD or a CMOS.
Preferably, in S3, the image processing module preprocesses the image, including image denoising, image enhancement and object segmentation, wherein the object segmentation is to segment a single workpiece image into a plurality of images.
Preferably, in S3, the image analysis module performs image analysis including feature extraction, feature selection, feature comparison and defect target identification, where the feature comparison is a comparison between the selected features and the standard detection image, so as to obtain a workpiece with a defect target identified, the workpiece is rejected by the execution module and classified as a defective product, and the workpiece without the defect target identified is retained in the original workpiece group.
Preferably, in S4, the counting image is a retained image of the workpiece group to be detected, and the second industrial camera is a CCD or a CMOS.
Preferably, in S5, the counting image is subjected to a counting system graying process, image segmentation, counting recognition of the counting image, and the result is accumulated on the generated value. A
Preferably, first image acquisition department and second image acquisition department all are equipped with the light filling device, first industry camera and second industry camera all are equipped with shock attenuation anti-shake device.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, smaller workpieces are grouped in advance, non-overlapping tools are placed on the automatic detection line, batch detection and counting are carried out, and the efficiency is improved. The image of the workpiece group is acquired through the first industrial camera, after the image is processed by the detection system, if the workpiece with the defect target is identified, the workpiece is rejected through the execution module and classified as a defective product, and the workpiece without the defect target is remained in the original workpiece group, so that the workpiece with the defect can be automatically detected, the workpiece with the defect can be rejected, and the detection precision and speed can be improved. The counting images are collected through the second industrial camera, counting recognition results are obtained after the counting images are processed by the counting system and are accumulated on the generated numerical values, the counted workpieces are conveyed to the next process through the automatic detection line, automatic counting is achieved, accuracy and rapidness are achieved, and human errors are avoided.
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 diagram of an automatic detection line according to the present invention;
FIG. 2 is a schematic view of the detection process of the present invention.
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. 1-2, the present invention provides a technical solution:
a workpiece detection counting method based on industrial vision comprises the following steps:
s1: zeroing a counting system, inputting a standard detection image into a detection system, dividing the workpieces to be detected into a plurality of groups, and placing the groups on an automatic detection line in a non-overlapping manner;
s2: the automatic detection line conveys the workpiece group to be detected to a first image acquisition position, and a first industrial camera acquires a workpiece group detection image;
s3: the detection image is preprocessed by an image processing module of the detection system and then analyzed by an image analysis module to obtain a result, and a detection system execution module rejects or retains the workpieces in the workpiece group according to the detection result;
s4: conveying the reserved workpieces to a second image acquisition position through an automatic detection line, and acquiring counting images by a second industrial camera;
s5: the collected counting image is processed by a counting system to obtain the number of workpieces, and the number is accumulated on the generated numerical value;
s6: and conveying the counted workpieces to the next process by the automatic detection line.
In S1, the workpieces to be detected are manually or mechanically divided into the same number of workpiece groups to be detected, and the workpieces are placed in the conveying boxes without overlapping and conveyed to the next process by the automatic detection line. In S3, the image processing module preprocesses the image including image denoising, image enhancement, and object segmentation, the object segmentation is to segment a single workpiece image as an object into a plurality of images, the image analysis module analyzes the image including feature extraction, feature selection, feature comparison, and defective object identification, the feature comparison is a comparison between the selected features and a standard detection image, the workpiece with the defective object identified is obtained and removed by the execution module, and is classified as a defective product, and the workpiece without the defective object identified is retained in the original workpiece group. In S5, the counting image is subjected to a counting system graying process and image segmentation, and then the counting image is counted and identified to obtain a result, which is then accumulated on the generated value.
In S2, the detection image is an image of a workpiece group to be detected, and the first industrial camera is a CCD or a CMOS. In S4, the counting image is the image of the workpiece group to be detected that remains, and the second industrial camera is a CCD or a CMOS. First image acquisition department and second image acquisition department all are equipped with the light filling device, first industry camera and second industry camera all are equipped with shock attenuation anti-shake device.
One specific application of this embodiment is: the invention returns the counting system to zero, inputs the standard detection image into the detection system, manually or mechanically divides the smaller workpieces to be detected into the workpiece groups with the same number, detects and counts in batches, improves the efficiency, places the workpieces in the workpiece groups to be detected in a non-overlapping way in a conveying box, conveys the workpiece groups to be detected to the next process by an automatic detection line, conveys the workpiece groups to be detected to a first image acquisition part by the automatic detection line, acquires the images of the workpiece groups to be detected by a first industrial camera, the detection images are subjected to image de-noising and image enhancement by an image processing module of the detection system, purposefully emphasizes the local characteristics of the images, expands the differences among different object characteristics in the images, improves the image quality, enriches the information content and enhances the image interpretation and recognition effects, and after the target division is divided into a plurality of images by taking a single workpiece image as a target, the image analysis module is subjected to characteristic extraction analysis by Fourier transform filtering and the PC or ICA algorithm to carry out the characteristic analysis After selection, the selected characteristics are compared with standard detection images through a target identification algorithm, if the workpiece with the defect target is identified, the workpiece is rejected through an execution module and classified as a defective product, the workpiece without the defect target is remained in an original workpiece group, the workpiece with the defect target can be automatically detected, the defective workpiece is rejected, and the detection precision and speed are improved.
The reserved workpieces are conveyed to a second image acquisition position through an automatic detection line, a counting image is acquired by a second industrial camera, the counting image is subjected to gray processing and image segmentation through a counting system, a self-adaptive matching template is constructed according to average radius characteristics based on a template matching algorithm of a two-dimensional local extreme value, point-by-point scanning images are matched, a correlation coefficient matrix is calculated, a two-dimensional local maximum value is obtained, next-best-point filtering is carried out according to Euclidean distance, an optimal matching position is determined, a counting identification result is obtained and accumulated on a generated numerical value, the counted workpieces are conveyed to the next process through the automatic detection line, automatic counting is achieved, accuracy and rapidness are achieved, and human errors are avoided.
According to the invention, smaller workpieces are grouped in advance, non-overlapping tools are placed on the automatic detection line, batch detection and counting are carried out, and the efficiency is improved. The image of the workpiece group is acquired through the first industrial camera, after the image is processed by the detection system, if the workpiece with the defect target is identified, the workpiece is rejected through the execution module and classified as a defective product, and the workpiece without the defect target is remained in the original workpiece group, so that the workpiece with the defect can be automatically detected, the workpiece with the defect can be rejected, and the detection precision and speed can be improved. The counting images are collected through the second industrial camera, counting recognition results are obtained after the counting images are processed by the counting system and are accumulated on the generated numerical values, the counted workpieces are conveyed to the next process through the automatic detection line, automatic counting is achieved, accuracy and rapidness are achieved, and human errors are avoided.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
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. A workpiece detection counting method based on industrial vision comprises the following steps:
s1: zeroing a counting system, inputting a standard detection image into a detection system, dividing the workpieces to be detected into a plurality of groups, and placing the groups on an automatic detection line in a non-overlapping manner;
s2: the automatic detection line conveys the workpiece group to be detected to a first image acquisition position, and a first industrial camera acquires a workpiece group detection image;
s3: the detection image is preprocessed by an image processing module of the detection system and then analyzed by an image analysis module to obtain a result, and a detection system execution module rejects or retains the workpieces in the workpiece group according to the detection result;
s4: conveying the reserved workpieces to a second image acquisition position through an automatic detection line, and acquiring counting images by a second industrial camera;
s5: the collected counting image is processed by a counting system to obtain the number of workpieces, and the number is accumulated on the generated numerical value;
s6: and conveying the counted workpieces to the next process by the automatic detection line.
2. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: at S1, the workpieces to be detected are manually or mechanically divided into the same number of groups of workpieces to be detected, and the groups are placed in the conveying box without overlapping and conveyed to the next process by the automatic detection line.
3. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: in S2, the detection image is an image of a workpiece group to be detected, and the first industrial camera is a CCD or a CMOS.
4. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: in S3, the image processing module preprocesses the image including image denoising, image enhancement and object segmentation, wherein the object segmentation is to segment a single workpiece image into a plurality of images.
5. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: in S3, the image analysis module performs image analysis including feature extraction, feature selection, feature comparison and defect target identification, the feature comparison is a comparison between the selected features and the standard detection image, and the workpieces with the defect targets identified are rejected by the execution module and classified as defective products, and the workpieces without the defect targets identified are retained in the original workpiece group.
6. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: in S4, the counting image is the image of the workpiece group to be detected that remains, and the second industrial camera is a CCD or a CMOS.
7. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: in S5, the counting image is subjected to a counting system graying process and image segmentation, and then the counting image is counted and identified to obtain a result, which is then accumulated on the generated value.
8. The workpiece detecting and counting method based on industrial vision as claimed in claim 1, characterized in that: first image acquisition department and second image acquisition department all are equipped with the light filling device, first industry camera and second industry camera all are equipped with shock attenuation anti-shake device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010232257.5A CN113516610A (en) | 2020-03-27 | 2020-03-27 | Workpiece detection counting method based on industrial vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010232257.5A CN113516610A (en) | 2020-03-27 | 2020-03-27 | Workpiece detection counting method based on industrial vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113516610A true CN113516610A (en) | 2021-10-19 |
Family
ID=78060013
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010232257.5A Pending CN113516610A (en) | 2020-03-27 | 2020-03-27 | Workpiece detection counting method based on industrial vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113516610A (en) |
-
2020
- 2020-03-27 CN CN202010232257.5A patent/CN113516610A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107328787A (en) | A kind of metal plate and belt surface defects detection system based on depth convolutional neural networks | |
CN105478529B (en) | Full-automatic stamping line products surface quality on-line detecting system and method | |
CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
CN106780437B (en) | A kind of quick QFN chip plastic packaging image obtains and amplification method | |
Yunardi | Contour-based object detection in Automatic Sorting System for a parcel boxes | |
CN112150439A (en) | Automatic sorting equipment and sorting method for injection molding parts | |
CN114235837A (en) | LED packaging surface defect detection method, device, medium and equipment based on machine vision | |
CN115035092A (en) | Image-based bottle detection method, device, equipment and storage medium | |
Charan et al. | The future of machine vision in industries-a systematic review | |
CN113516619A (en) | Product surface flaw identification method based on image processing technology | |
CN113281115B (en) | Control method for intelligent tobacco leaf shearing | |
CN111251296B (en) | Visual detection system suitable for pile up neatly electric motor rotor | |
Hicham et al. | Inspection of machining defects on mechanical parts using a computer vision system | |
CN114986520B (en) | Four-axis parallel robot sorting system and method based on machine vision | |
CN117409005A (en) | Defective product detection system and method for plate receiving machine based on image | |
CN113516610A (en) | Workpiece detection counting method based on industrial vision | |
CN117611571A (en) | Strip steel surface defect detection method based on improved YOLO model | |
CN115532620B (en) | Pulp molding product quality inspection device and method | |
Zhou et al. | Automated detection of surface defects on sphere parts using laser and CDD measurements | |
CN113160154B (en) | Method and system for detecting paint spraying defects of five-star feet based on machine vision | |
EP4184434A1 (en) | Method for providing learning data for an ai system and processing system | |
Lei | A machine vision system for inspecting bearing-diameter | |
CN116563194A (en) | Visual inspection system for defect detection | |
CN114331944A (en) | Artificial intelligence flaw image classification 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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211019 |
|
WD01 | Invention patent application deemed withdrawn after publication |