CN107833222B - Nonmetal part surplus detection device and method - Google Patents
Nonmetal part surplus detection device and method Download PDFInfo
- Publication number
- CN107833222B CN107833222B CN201711309363.3A CN201711309363A CN107833222B CN 107833222 B CN107833222 B CN 107833222B CN 201711309363 A CN201711309363 A CN 201711309363A CN 107833222 B CN107833222 B CN 107833222B
- Authority
- CN
- China
- Prior art keywords
- detected
- workpiece
- detection
- sorting air
- light source
- 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 claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 16
- 229910052755 nonmetal Inorganic materials 0.000 title claims description 15
- 238000003708 edge detection Methods 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 5
- 230000005764 inhibitory process Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000013139 quantization Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 2
- 239000000463 material Substances 0.000 abstract description 6
- 238000010923 batch production Methods 0.000 abstract description 4
- 239000005337 ground glass Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000005338 frosted glass Substances 0.000 description 2
- 239000004642 Polyimide Substances 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920001721 polyimide Polymers 0.000 description 1
- -1 polytetrafluoroethylene Polymers 0.000 description 1
- 229920001343 polytetrafluoroethylene Polymers 0.000 description 1
- 239000004810 polytetrafluoroethylene Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000007 visual effect 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
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention discloses a nonmetallic part surplus detection device and a nonmetallic part surplus detection method, which mainly comprise a detection platform, a bracket, a camera, a light source, a sorting air tap and a computer; firstly, acquiring part images through a camera, carrying out part edge identification by utilizing an edge detection algorithm for small-size nonmetallic parts, then determining whether the detected parts carry surplus or not through identification comparison of an edge surplus judgment algorithm of the parts, giving out a judgment result of whether the detected parts are qualified or not, and starting a sorting air tap according to the judgment result to realize sorting; the detection efficiency and the detection precision can be greatly improved, so that the method is more suitable for the requirements of batch production. The invention aims at detecting and identifying the redundant materials of the small-size nonmetallic parts, can greatly improve the detection efficiency and the detection precision, effectively reduces the labor intensity of operators, improves the working efficiency and is more suitable for the requirements of batch production.
Description
Technical Field
The invention relates to the technical field of relay manufacture, in particular to a non-metal part surplus detection device and method.
Background
In the production process of electromagnetic relay, some nonmetallic parts such as washers, gaskets, skeletons, etc. (the size of the parts is generally smaller than 5 mm) are needed, and the materials are mainly polytetrafluoroethylene and polyimide nonmetallic. These nonmetallic parts are mainly formed by blanking, and because the separation process of the nonmetallic parts and the scrap is always kept in plastic deformation in the forming process, the brittle tearing belt formed in the blanking process of the metallic parts is difficult to be like, and the filiform burrs are easy to be generated. At present, in view of the small size of the parts, burrs on the nonmetallic parts need to be screened one by one through an operator under a visual microscope, and the problems of high labor intensity, high subjectivity, extremely low efficiency and incapability of meeting the requirement of batch production exist.
Disclosure of Invention
The invention aims to solve the problems of detecting non-metal part residues by a microscope manual screening method, and provides a non-metal part residue detection device and a non-metal part residue detection method.
In order to solve the problems, the invention is realized by the following technical scheme:
the non-metal part superfluous matter detection device mainly comprises a detection platform, a bracket, a camera, a light source, a sorting air tap and a computer;
placing a workpiece to be detected on a detection platform; the camera is arranged right above the detection platform through the bracket, and the lens of the camera faces to the workpiece to be detected; the data output end of the camera is connected with the input end of the computer;
the light source comprises an upper light source and a lower light source; the upper light source is positioned right above the workpiece to be detected, the lower light source is positioned right below the workpiece to be detected, and the light emitting directions of the upper light source and the lower light source face the workpiece to be detected;
the sorting air nozzles comprise qualified sorting air nozzles and unqualified sorting air nozzles; the qualified sorting air tap is positioned on one side of the workpiece to be detected, the unqualified sorting air tap is positioned on the other side of the workpiece to be detected, and air outlets of the qualified sorting air tap and the unqualified sorting air tap face towards the workpiece to be detected; the output end of the computer is connected with the control ends of the qualified sorting air nozzles and the unqualified sorting air nozzles.
In the scheme, ground glass is arranged between the workpiece to be detected and the lower light source and/or between the workpiece to be detected and the upper light source.
In the scheme, the upper light source and the lower light source are annular light sources.
The method for detecting the non-metal part surplus comprises the following steps:
step 1, placing a workpiece to be detected in an identification area of a detection platform, and starting a light source;
step 2, the camera collects images of the workpiece to be detected, and the images are sent into a computer for processing;
step 3, preprocessing an image acquired by a camera by a computer to obtain a gray level image of the image;
step 4, carrying out edge detection on the gray level image by adopting a Canny algorithm;
step 4.1, performing Gaussian filtering treatment on the gray level image;
step 4.2, carrying out gradient calculation on the gray level diagram after the filtering treatment, and carrying out non-maximum value inhibition treatment on the gradient amplitude;
step 4.3, thresholding the gradient amplitude by traversing the gradient amplitude by adopting a high threshold TH and a low threshold TL respectively to obtain a high-edge image IH and a low-edge image IL; connecting edges into contours in the high-edge image IH, namely, when the high-edge image IH reaches an endpoint, adopting a neighborhood to search edge points at corresponding positions in the low-edge image IL to connect discontinuous edges in the high-edge image IH, thereby completing edge detection;
step 5, according to the edge detection result, carrying out segmentation processing and quantization calculation of more than 2 given dimensions on the gray level map with the edge bulge to obtain the characteristic attribute of the redundant sample;
step 6, carrying out weight calculation on the quantized values of each dimension of the redundant sample characteristic attribute to obtain a comprehensive result, comparing the comprehensive result with a predetermined threshold value, and when the comprehensive result is larger than the predetermined threshold value, determining that the workpiece to be detected is unqualified; otherwise, the workpiece to be detected is qualified;
step 7, the computer starts a sorting air tap according to the detection result, namely, when the workpiece to be detected is qualified, a qualified sorting air tap is started, and the qualified workpiece to be detected is blown into a qualified collecting area; when the workpiece to be detected is unqualified, an unqualified sorting air nozzle is started, and the qualified workpiece to be detected is blown into an unqualified collecting area.
In the step 4, median filtering is required to be performed on the gray level image according to a given filtering window, and then the Canny algorithm is adopted to perform edge detection on the gray level image.
In the step 7, the method further includes a step of displaying the detection result by a computer.
Compared with the prior art, the invention constructs a non-metal part surplus detection device to automatically detect non-metal parts in the electromagnetic relay production process; firstly, acquiring part images through a camera, carrying out part edge identification by utilizing an edge detection algorithm for small-size nonmetallic parts, then determining whether the detected parts carry surplus or not through identification comparison of an edge surplus judgment algorithm of the parts, giving out a judgment result of whether the detected parts are qualified or not, and starting a sorting air tap according to the judgment result to realize sorting. The invention aims at detecting and identifying the redundant materials of the small-size nonmetallic parts, can greatly improve the detection efficiency and the detection precision, effectively reduces the labor intensity of operators, improves the working efficiency and is more suitable for the requirements of batch production.
Drawings
FIG. 1 is a schematic diagram of a non-metallic part redundancy detection apparatus.
FIG. 2 is a flow chart of a method for detecting the redundant material of a nonmetallic part.
Reference numerals in the drawings: 1. a workpiece to be inspected; 2. a detection platform; 3. a bracket; 4. a camera; 5. a lens; 6. a top light source; 7. a lower light source; 8. disqualified sorting air nozzles; 9. qualified sorting air nozzles; 10. frosted glass.
Detailed Description
The invention will be further described in detail below with reference to specific examples and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the invention more apparent. In the examples, directional terms such as "upper", "lower", "middle", "left", "right", "front", "rear", and the like are merely directions with reference to the drawings. Accordingly, the directions of use are merely illustrative and not intended to limit the scope of the invention.
A non-metal part superfluous matter detection device is shown in fig. 1, and consists of a detection platform 2, a bracket 3, a camera 4, a light source, a sorting air tap, ground glass 10 and a computer.
The workpiece 1 to be inspected is placed on the inspection platform 2. The camera 4 is arranged right above the detection platform 2 through the bracket 3, and the lens 5 of the camera 4 faces the workpiece 1 to be detected. The data output of the camera 4 is connected to the input of the computer.
The light source comprises an upper light source 6 and a lower light source 7. The upper light source 6 is located right above the workpiece 1 to be inspected, the lower light source 7 is located right below the workpiece 1 to be inspected, and the light emitting directions of the upper light source 6 and the lower light source 7 face the workpiece 1 to be inspected. The light source can effectively improve the precision of image acquisition and prevent noise from affecting the detection result. In the preferred implementation of the invention, the upper light source 6 and the lower light source 7 are annular light sources, and the annular light sources can uniformly emit to the workpiece 1 to be detected from the periphery, thereby effectively preventing the interference of shadows on the detection result.
In order to avoid interference of strong light of the light source on image acquisition and detection results, ground glass 10 is preferably arranged between the workpiece 1 to be detected and the lower light source 7 and/or between the workpiece 1 to be detected and the upper light source 6. In view of the small interference of the upper light source 6 with the image acquisition, in the preferred embodiment of the present invention, a frosted glass 10 is provided only between the workpiece 1 to be inspected and the lower light source 7. The light source can be started manually or connected with a computer to realize automatic starting.
The sorting air nozzles comprise a qualified sorting air nozzle 9 and a disqualified sorting air nozzle 8. The qualified sorting air tap 9 is located on the left side of the workpiece 1 to be detected, the unqualified sorting air tap 8 is located on the right side of the workpiece 1 to be detected, and air outlets of the qualified sorting air tap 9 and the unqualified sorting air tap 8 face the workpiece 1 to be detected. The output end of the computer is connected with the control ends of the qualified sorting air tap 9 and the unqualified sorting air tap 8. The sorting air tap is used for sorting the workpieces 1 to be detected according to the detection result of the computer, wherein the qualified workpieces 1 to be detected are blown into the qualified collecting area, and the unqualified workpieces 1 to be detected are blown into the unqualified collecting area.
The operator puts the workpiece 1 to be detected into the recognition area of the recognition and detection platform 2, the computer recognizes and detects the workpiece 1 to be detected according to the image of the workpiece 1 to be detected acquired by the camera 4, and the judgment of whether the workpiece 1 to be detected has residues or not is given. After the judgment is completed, the computer displays the detection result to an operator in real time, and starts the sorting air tap to automatically sort the workpiece 1 to be detected into a designated collecting area.
The method for detecting the redundant objects of the nonmetallic part, which is realized by the device, is shown in fig. 2, and comprises the following steps:
step 1, placing a workpiece 1 to be detected in an identification area of a detection platform 2, and starting a light source;
step 2, the camera 4 collects images of the workpiece 1 to be detected, and the images are sent into a computer for processing;
step 3, the computer preprocesses the image acquired by the camera 4 to obtain a gray level image of the image;
step 4, counting the gray level diagram and the gray level histogram, selecting boundary gray level values, selecting a 3×3 filter window to perform median filtering on the gray level diagram, and completing noise reduction treatment, thereby facilitating edge detection;
step 5, carrying out edge detection on the gray level image by adopting a Canny algorithm;
step 5.1, carrying out Gaussian filtering treatment on the gray level image, and reducing the influence of noise on a Canny algorithm;
step 5.2, carrying out gradient calculation on the gray level image after the filtering treatment, carrying out non-maximum value inhibition treatment on the gradient amplitude value, and eliminating most non-edge points;
step 5.3, adopting a double-threshold method to reduce false edges: thresholding the gradient amplitude by traversing the gradient amplitude by adopting a high threshold TH and a low threshold TL to obtain a high-edge image IH and a low-edge image IL; since for IH there are few false edges due to the larger TH, but the resulting image edges may not be closed, thus connecting edges into contours in the high-edge image IH, when an endpoint is reached, then connecting intermittent edges in the high-edge image IH by using neighborhood search edge points at corresponding positions in the low-edge image IL, thereby completing edge detection;
step 6, detecting the surplus attached to the edge of the non-metal part as a part of the edge of the part, and displaying the part as a raised part of the edge on the image, so as to divide the gray level graph with the raised edge according to the detection result of the edge detection, and carrying out quantitative calculation of multiple dimensions such as area, roundness, rectangularity, convexity, straightness and angle to obtain the characteristic attribute of the sample of the surplus;
step 7, carrying out weight calculation on the quantized values of each dimension of the redundant sample characteristic attribute to obtain a comprehensive result, comparing the comprehensive result with a predetermined threshold value, and when the comprehensive result is larger than the predetermined threshold value, determining that the workpiece 1 to be detected is unqualified; otherwise, the workpiece 1 to be detected is qualified;
step 8, displaying the detection result by the computer, and starting a sorting air tap according to the detection result, namely starting a qualified sorting air tap 9 when the workpiece 1 to be detected is qualified, and blowing the qualified workpiece 1 to be detected into a qualified collecting area; when the workpiece 1 to be detected is unqualified, the unqualified sorting air tap 8 is started, and the qualified workpiece 1 to be detected is blown into an unqualified collecting area, so that a sorting function is realized.
The invention realizes detection and identification of the redundant materials of the nonmetal parts with small size through the combined operation of hardware and software parts, reduces the labor intensity of operators, improves the accuracy of identifying the redundant materials of the nonmetal parts and improves the working efficiency.
It should be noted that, although the examples described above are illustrative, this is not a limitation of the present invention, and thus the present invention is not limited to the above-described specific embodiments. Other embodiments, which are apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein, are considered to be within the scope of the invention as claimed.
Claims (3)
1. The utility model provides a non-metal part unnecessary object detection method, its realizing device mainly comprises testing platform (2), support (3), camera (4), light source, letter sorting air cock and computer; the workpiece (1) to be detected is placed on the detection platform (2); the camera (4) is arranged right above the detection platform (2) through the bracket (3), and a lens (5) of the camera (4) faces to the workpiece (1) to be detected; the data output end of the camera (4) is connected with the input end of the computer; the light source comprises an upper light source (6) and a lower light source (7); the upper light source (6) is positioned right above the workpiece (1) to be detected, the lower light source (7) is positioned right below the workpiece (1) to be detected, and the light emitting directions of the upper light source (6) and the lower light source (7) face the workpiece (1) to be detected; the sorting air nozzle comprises a qualified sorting air nozzle (9) and a disqualified sorting air nozzle (8); the qualified sorting air tap (9) is positioned on one side of the workpiece (1) to be detected, the unqualified sorting air tap (8) is positioned on the other side of the workpiece (1) to be detected, and air outlets of the qualified sorting air tap (9) and the unqualified sorting air tap (8) face the workpiece (1) to be detected; the output end of the computer is connected with the control ends of the qualified sorting air tap (9) and the unqualified sorting air tap (8); the method is characterized by comprising the following steps:
step 1, placing a workpiece (1) to be detected in an identification area of a detection platform (2), and starting a light source;
step 2, a camera (4) collects images of the workpiece (1) to be detected, and the images are sent into a computer for processing;
step 3, preprocessing the image acquired by the camera (4) by a computer to obtain a gray level image of the image;
step 4, carrying out edge detection on the gray level image by adopting a Canny algorithm;
step 4.1, performing Gaussian filtering treatment on the gray level image;
step 4.2, carrying out gradient calculation on the gray level diagram after the filtering treatment, and carrying out non-maximum value inhibition treatment on the gradient amplitude;
step 4.3, thresholding the gradient amplitude by traversing the gradient amplitude by adopting a high threshold TH and a low threshold TL respectively to obtain a high-edge image IH and a low-edge image IL; connecting edges into contours in the high-edge image IH, namely, when the high-edge image IH reaches an endpoint, adopting a neighborhood to search edge points at corresponding positions in the low-edge image IL to connect discontinuous edges in the high-edge image IH, thereby completing edge detection;
step 5, according to the detection result of edge detection, carrying out segmentation processing and quantization calculation of more than 2 given dimensions on the gray level map with the edge bulge to obtain the characteristic attribute of the redundant sample;
step 6, carrying out weight calculation on quantized values of each dimension of the redundant sample characteristic attribute to obtain a comprehensive result, comparing the comprehensive result with a predetermined threshold value, and when the comprehensive result is larger than the predetermined threshold value, determining that the workpiece (1) to be detected is unqualified; otherwise, the workpiece (1) to be detected is qualified;
step 7, the computer starts a sorting air tap according to the detection result, namely, when the workpiece (1) to be detected is qualified, a qualified sorting air tap (9) is started, and the qualified workpiece (1) to be detected is blown into a qualified collecting area; when the workpiece (1) to be detected is unqualified, an unqualified sorting air nozzle (8) is started, and the qualified workpiece (1) to be detected is blown into an unqualified collecting area.
2. The method for detecting the redundant substances of the nonmetallic part according to claim 1, wherein in the step 4, median filtering is needed to be carried out on a gray scale image according to a given filtering window, and then a Canny algorithm is adopted to carry out edge detection on the gray scale image.
3. The method for detecting the redundant substances of the nonmetallic part according to claim 1, wherein in the step 7, the method further comprises the step of displaying the detection result by a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711309363.3A CN107833222B (en) | 2017-12-11 | 2017-12-11 | Nonmetal part surplus detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711309363.3A CN107833222B (en) | 2017-12-11 | 2017-12-11 | Nonmetal part surplus detection device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107833222A CN107833222A (en) | 2018-03-23 |
| CN107833222B true CN107833222B (en) | 2023-12-22 |
Family
ID=61642849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711309363.3A Active CN107833222B (en) | 2017-12-11 | 2017-12-11 | Nonmetal part surplus detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107833222B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109724533A (en) * | 2018-12-29 | 2019-05-07 | 中核北方核燃料元件有限公司 | A kind of ceramic pellet surface size, defect full-automatic detection apparatus and method |
| CN115330791A (en) * | 2022-10-13 | 2022-11-11 | 江苏东晨机械科技有限公司 | Part burr detection method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000157937A (en) * | 1998-11-26 | 2000-06-13 | Nkk Corp | High speed sorting device |
| JP2011100341A (en) * | 2009-11-06 | 2011-05-19 | Kanto Auto Works Ltd | Method of detecting edge and image processing apparatus |
| CN103785627A (en) * | 2014-01-27 | 2014-05-14 | 河南科技大学 | On-line lithium battery pole piece surface defect detection sorting system and method |
| CN107044986A (en) * | 2017-03-22 | 2017-08-15 | 深圳市伟鸿科科技有限公司 | Backlight finished product detection device and detection method |
| CN207503283U (en) * | 2017-12-11 | 2018-06-15 | 桂林航天电子有限公司 | A kind of non-metal workpiece fifth wheel detection device |
-
2017
- 2017-12-11 CN CN201711309363.3A patent/CN107833222B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000157937A (en) * | 1998-11-26 | 2000-06-13 | Nkk Corp | High speed sorting device |
| JP2011100341A (en) * | 2009-11-06 | 2011-05-19 | Kanto Auto Works Ltd | Method of detecting edge and image processing apparatus |
| CN103785627A (en) * | 2014-01-27 | 2014-05-14 | 河南科技大学 | On-line lithium battery pole piece surface defect detection sorting system and method |
| CN107044986A (en) * | 2017-03-22 | 2017-08-15 | 深圳市伟鸿科科技有限公司 | Backlight finished product detection device and detection method |
| CN207503283U (en) * | 2017-12-11 | 2018-06-15 | 桂林航天电子有限公司 | A kind of non-metal workpiece fifth wheel detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107833222A (en) | 2018-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148130B (en) | Method and device for detecting part defects | |
| CN111693534B (en) | Surface defect detection method, model training method, device, equipment and medium | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN108230324B (en) | Visual detection method for microdefect on surface of magnetic shoe | |
| CN111127402A (en) | Visual detection method for welding quality of robot | |
| CN105158268A (en) | Intelligent online detection method, system and device for defects of fine-blanked parts | |
| CN103175844A (en) | Detection method for scratches and defects on surfaces of metal components | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN107610085A (en) | A kind of welding point defect detecting system based on computer vision | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| CN110288584A (en) | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision | |
| CN112614062A (en) | Bacterial colony counting method and device and computer storage medium | |
| CN109584215A (en) | A kind of online vision detection system of circuit board | |
| CN107345916B (en) | Plane appearance detection method based on fixed contour | |
| CN110717909A (en) | Metal surface scratch detection method and device | |
| Fan et al. | Development of auto defect classification system on porosity powder metallurgy products | |
| CN107833222B (en) | Nonmetal part surplus detection device and method | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN114705686A (en) | Method and system for detecting surface defects of cylindrical pot, controller and industrial personal computer | |
| CN108020554A (en) | A kind of steel strip surface defect recognition detection method | |
| CN107153067A (en) | A kind of surface defects of parts detection method based on MATLAB | |
| CN109557104A (en) | A kind of timber based on deep learning preferably saws intelligent detecting method | |
| CN113588656A (en) | Novel bolt appearance size detection method | |
| CN112102278A (en) | Metal workpiece machining surface defect detection method based on computer vision | |
| CN111693535A (en) | Touch screen defect detection equipment and method based on machine vision analysis |
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 |