CN114519704A - Method for detecting scratch defects on surfaces of metal parts of communication electrical appliances - Google Patents
Method for detecting scratch defects on surfaces of metal parts of communication electrical appliances Download PDFInfo
- Publication number
- CN114519704A CN114519704A CN202210129987.1A CN202210129987A CN114519704A CN 114519704 A CN114519704 A CN 114519704A CN 202210129987 A CN202210129987 A CN 202210129987A CN 114519704 A CN114519704 A CN 114519704A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- scratch
- scanning
- detection
- 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
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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B5/00—Cleaning by methods involving the use of air flow or gas flow
- B08B5/02—Cleaning by the force of jets, e.g. blowing-out cavities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method for detecting the surface scratch defects of metal parts of communication electrical appliances, which comprises the following steps: s1: scanning sample construction: a sample of a part to be detected is found and scanned to establish various detection requirements of the part to be detected of the specification, including a detection position and the characteristics of the part to be detected; s2: placing a detection component: stably placing the part to be detected on a detection station to be detected according to requirements; s3: surface cleaning: the outer surface of the part to be detected is cleaned in a non-contact manner by using a fan, so that the surface of the part to be detected is not affected by floating ash during detection; s4: and (3) scanning image processing: the part to be detected is scanned into a picture, and the scanned picture is processed, so that picture information can be better extracted; s5: analyzing scratch defects; s6: and (6) displaying the result. The method for detecting the scratch defects on the surfaces of the metal parts of the communication electrical appliances, disclosed by the invention, has the technical effect of further ensuring the accuracy of the detection result.
Description
Technical Field
The invention relates to the technical field of metal accessory production detection, in particular to a method for detecting surface scratch defects of metal parts of communication appliances.
Background
The production and manufacturing process of the communication electric appliance relates to the assembly and treatment of a large number of metal parts, and the parts are circulated and installed, so that scratch defects can be generated on the surfaces of the parts in the manufacturing and assembling process, the defects need to be detected and treated in time, and the performance of the communication electric appliance is prevented from being influenced.
Machine vision has wide application in the fields of national economy, scientific research, national defense construction and the like. Its biggest advantage is contactless measurement, compares with other methods and all has very big advantage in security, reliability, detection precision, detection speed, detection cost. In the detection of metal parts and components using machine vision, the detection range is generally controlled to be a general area, but some other factors may interfere in the area, so that the detection result is inaccurate.
Disclosure of Invention
The invention discloses a method for detecting the surface scratch defects of metal parts of communication electrical appliances, and aims to solve the technical problem of inaccurate detection results caused by interference of other factors.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for detecting the scratch defects on the surfaces of metal parts of communication electrical appliances comprises the following specific steps:
s1: scanning sample construction: a sample of a part to be detected is found and scanned to establish various detection requirements of the part to be detected of the specification, including a detection position and the characteristics of the part to be detected;
s2: placing a detection component: stably placing the part to be detected on a detection station to be detected according to requirements;
s3: surface cleaning: the outer surface of the part to be detected is cleaned in a non-contact manner by using a fan, so that the surface of the part to be detected is not affected by floating ash during detection;
s4: and (3) scanning image processing: the part to be detected is scanned into a picture, and the scanned picture is processed, so that picture information can be better extracted;
s5: and (3) scratch defect analysis: identifying and analyzing whether the surface has the scratch defect according to the image processed by the scanning image, and if so, further analyzing the scanned scratch defect;
s6: the results show that: and displaying the scanned scratch defect of the surface of the part and various data of the scratch defect on a display screen, and giving a corresponding processing scheme according to the data.
The surface cleaning is arranged, floating dust possibly existing on the part to be detected is blown away by non-contact cleaning, the cleanliness of the surface of the part is guaranteed, the profile characteristics of a constructed sample are constructed by scanning the sample, modeling is formed, the part to be detected is matched with the modeling in scanning image processing, so that the peripheral profile of the detection surface is accurately controlled, the detection is only carried out on the detection surface when the detection is carried out, the detection result is prevented from being influenced by factors such as a transmission belt or a fixed panel in the detection process, and the accuracy of the detection result is guaranteed.
In a preferred embodiment, in S1, the scan sample construction specifically includes the following steps:
s11: sample scanning: a sample of a part to be detected is found, and three-dimensional scanning is carried out on a plurality of directions of the sample so as to obtain images of all directions of the sample for analysis;
s12: image feature extraction: extracting meaningful features in the image by utilizing an image segmentation technology according to the image scanned in the sample scanning, and modeling according to the features;
s13: selecting a detection surface: manually selecting the three-dimensional image scanned from the sample, selecting one or more specific surfaces for scanning analysis, and storing the selected specific surfaces as the basis for subsequent detection of the large-volume parts;
s14: image array segmentation: selecting a formed specific surface image according to sample scanning and detection surfaces and combining the image with data extracted in image feature extraction, segmenting the image of the surface to be detected according to equal parts, and storing segmentation positions as the basis of subsequent detection parts in large goods;
in S12, the significant features in the image feature extraction include the outer contour of the image and different edges of the scanning surface, so as to prepare for subsequent detection and positioning;
in S4, the scan image processing specifically includes the following steps:
s41: scanning the surface of the part: scanning a component to be detected to form a scanned image;
s42: image feature comparison: comparing the modeling of the sample with the part to be detected according to the steps of image feature extraction and detection surface selection;
s43: secondary image array segmentation: dividing the surface image of the component to be detected according to the division position stored in the image array division, and dividing the whole surface treatment into different array small area treatments;
s44: image enhancement: enhancing the image subjected to the secondary image array segmentation processing, strengthening the high-frequency component of the image, improving the definition of the image and emphasizing the salient details in the image;
in S42, the specific comparison method in the image feature comparison is to perform coincidence with the edge profile of the to-be-detected part according to the model in the image feature extraction, and if there is a little difference, the position of the sample model is corrected in the system, so that the model can coincide with the to-be-detected part, and then the detection surface is positioned according to the specific detection surface selected in the detection surface selection.
By setting image array segmentation, secondary image array segmentation and image characteristic comparison, firstly modeling is carried out on a sample, then an image of a surface to be detected is segmented according to equal parts, segmentation positions are stored as the basis of subsequent detection, and then the overall surface is processed and segmented into different array small areas for analysis and processing by comparing the segmentation positions of the image array segmentation through the secondary image array segmentation, so that the calculated amount can be greatly reduced, the detection speed is accelerated, a more effective detection effect can be obtained, and the detection quality is enhanced.
In a preferred embodiment, the result display in S6 specifically includes the following steps:
s61: and (3) data measurement: measuring various data of the scratch by scratch identification and three-dimensional depth scanning;
s62: patterning: the scanning surface is patterned according to the scanning image processing and the scratch defect analysis, and the scanning surface outline and the scratch shape and position are formed only by lines in the image;
s63: labeling: marking the measured various data in the composition in detail through a data measuring step;
s64: and (4) alarming: alarming and reminding are carried out by sound, and the problem that the scratch defect exists on the surface of the part is prompted to a worker;
s65: analysis of treatment protocol: analyzing different processing schemes including grinding, filling or re-melting and remanufacturing according to the measured scratch data;
in S61, the various data measured in the data measurement include the length, depth, number and position of the scratch.
Through being provided with data measurement, composition of picture, mark and processing scheme analysis, constitute scanning surface profile and mar shape and position with the lines through the composition of picture, the rethread marks various data that data measurement measured on the composition of picture, make the staff can more audio-visual multinomial data of observing the mar to the processing scheme that supplementary processing scheme analysis was given enables the staff more timely to the parts that have problems carry out the categorised storage to different processing schemes, do benefit to and unify the processing to the parts that have problems, strengthen work efficiency.
Therefore, the method for detecting the scratch defects on the surfaces of the metal parts of the communication electrical appliances comprises the following specific steps:
s1: scanning sample construction: a sample of a part to be detected is found and scanned to establish various detection requirements of the part to be detected of the specification, including a detection position and the characteristics of the part to be detected;
s2: placing detection components: stably placing the part to be detected on a detection station to be detected according to requirements;
s3: surface cleaning: the surface of the part to be detected is cleaned in a non-contact manner by using a fan, so that the surface of the part to be detected is not affected by floating ash during detection;
s4: and (3) scanning image processing: the part to be detected is scanned into a picture, and the scanned picture is processed, so that picture information can be better extracted;
s5: and (3) scratch defect analysis: identifying and analyzing whether the surface has the scratch defects according to the image processed by the scanning image, and if so, further analyzing the scanned scratch defects;
s6: the results show that: and displaying the scanned scratch defect of the surface of the part and various data of the scratch defect on a display screen, and giving a corresponding processing scheme according to the data. The method for detecting the scratch defects on the surfaces of the metal parts of the communication electrical appliances has the technical effect of further ensuring the accuracy of the detection result.
Drawings
FIG. 1 is a general flowchart of a method for detecting the scratch defect on the surface of a metal component of a communication appliance according to the present invention.
Fig. 2 is a flow chart of a scanning sample construction of the method for detecting the surface scratch defect of the metal component of the communication appliance according to the present invention.
FIG. 3 is a flowchart of a scanning image processing method for detecting the scratch defect on the surface of the metal component of the communication apparatus according to the present invention.
Fig. 4 is a flow chart of the scratch defect analysis of the method for detecting the scratch defect on the surface of the metal component of the communication electrical appliance according to the present invention.
FIG. 5 is a flowchart showing the result of the method for detecting the scratch defect on the surface of the metal component of the communication apparatus according to 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.
The invention discloses a method for detecting the surface scratch defects of metal parts of a communication electrical appliance, which is mainly applied to scenes for detecting accessories of the communication electrical appliance.
Referring to fig. 1, a method for detecting the scratch defect on the surface of a metal part of a communication electrical appliance comprises the following specific steps:
s1: scanning sample construction: a sample of a part to be detected is found and scanned to establish various detection requirements of the part to be detected of the specification, including a detection position and the characteristics of the part to be detected;
s2: placing a detection component: stably placing the part to be detected on a detection station to be detected according to requirements;
s3: surface cleaning: the outer surface of the part to be detected is cleaned in a non-contact manner by using a fan, so that the surface of the part to be detected is not affected by floating ash during detection;
s4: scanning image processing: the part to be detected is scanned into a picture, and the scanned picture is processed, so that picture information can be better extracted;
s5: and (3) scratch defect analysis: identifying and analyzing whether the surface has the scratch defect according to the image processed by the scanning image, and if so, further analyzing the scanned scratch defect;
s6: the results show that: and displaying the scanned scratch defect of the surface of the part and various data of the scratch defect on a display screen, and giving a corresponding processing scheme according to the data.
Referring to fig. 2 and 3, in a preferred embodiment, in S1, the scan sample construction specifically includes the following steps:
s11: sample scanning: a sample of a part to be detected is found, and three-dimensional scanning is carried out on a plurality of directions of the sample so as to obtain images of all directions of the sample for analysis;
s12: image feature extraction: extracting meaningful features in the image by utilizing an image segmentation technology according to the image scanned in the sample scanning, and modeling according to the features;
s13: selecting a detection surface: manually selecting the three-dimensional image scanned from the sample, selecting one or more specific surfaces for scanning analysis, and storing the selected specific surfaces as the basis for subsequent detection of the large-volume parts;
s14: image array segmentation: selecting a formed specific surface image according to sample scanning and detection surfaces and combining the image with data extracted in image feature extraction, segmenting the image of the surface to be detected according to equal parts, and storing segmentation positions as the basis of subsequent detection parts in large goods;
in S12, meaningful features in image feature extraction comprise the external outline of an image and different scanning surface edges, and preparation is made for subsequent detection and positioning;
in S4, the scan image processing specifically includes the steps of:
s41: scanning the surface of the part: scanning a component to be detected to form a scanned image;
s42: image feature comparison: comparing the modeling of the sample with the part to be detected according to the steps of image feature extraction and detection surface selection;
s43: and (3) secondary image array segmentation: dividing the surface image of the component to be detected according to the division position stored in the image array division, and dividing the whole surface treatment into different array small area treatments;
s44: image enhancement: enhancing the image subjected to the secondary image array segmentation processing, strengthening the high-frequency component of the image, improving the definition of the image and emphasizing the salient details in the image;
in S42, the specific comparison method in the image feature comparison is to perform coincidence with the edge profile of the to-be-detected part according to the model in the image feature extraction, and if there is a little difference, the position of the sample model is corrected in the system, so that the model can coincide with the to-be-detected part, and then the detection surface is positioned according to the specific detection surface selected in the detection surface selection.
Referring to fig. 4, in a preferred embodiment, in S5, the scratch defect analysis specifically includes the following steps:
s51: and (3) identifying scratches: identifying the image after the secondary image array segmentation and the image enhancement, and distinguishing whether the surface has scratch defects;
s52: releasing: if the scratch defects are not distinguished in the scratch identification, the surface of the part is not scratched, and the part is immediately released and collected;
s53: array combinatorial analysis: if the scratches are identified on the surface of the part and span two or more divided array small areas, the scratches in different array small areas are automatically spliced to form a complete scratch defect;
s54: positioning scratches: positioning on the component scan surface according to the identified scratches;
s55: three-dimensional depth scanning; the laser scanning is directly carried out on the positioned scratch in the scratch positioning, and the specific depth of the scratch is detected.
Referring to fig. 5, in a preferred embodiment, in S6, the result display specifically includes the following steps:
s61: and (3) data measurement: measuring various data of the scratch by scratch identification and three-dimensional depth scanning;
s62: patterning: the scanning surface is patterned according to the scanning image processing and the scratch defect analysis, and the scanning surface outline and the scratch shape and position are formed only by lines in the image;
s63: labeling: marking the measured various data in the composition in detail through a data measuring step;
s64: and (4) alarming: alarming and reminding are carried out by sound, and the problem that the scratch defect exists on the surface of the part is prompted to a worker;
s65: analysis of treatment protocol: analyzing different processing schemes including grinding, filling or re-melting and remanufacturing according to the measured scratch data;
in S61, the various data measured in the data measurement include the length, depth, number and position of the scratch.
The working principle is as follows: when the device is used, floating dust possibly existing on a part to be detected is blown away by non-contact cleaning in the surface cleaning step, the surface cleanliness of the part is ensured, the profile characteristics of a constructed sample are constructed by scanning the sample, modeling is formed, the part to be detected is overlapped with the edge profile matched with the modeling in the scanning image processing, if a little difference exists, the position of sample modeling is corrected in the system, the modeling can be overlapped with the part to be detected, so that the peripheral profile of the detection surface is accurately controlled, the detection surface is positioned according to the specific detection surface selected in the detection surface selection, and the detection is only carried out aiming at the detection surface in the detection process, so that the inaccuracy of the detection result caused by the interference of other factors in the detection process can be avoided, and the accuracy of the detection result is ensured.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (8)
1. A method for detecting the scratch defects on the surfaces of metal parts of communication electrical appliances is characterized by comprising the following specific steps:
s1: scanning sample construction: a sample of a part to be detected is found and scanned to establish various detection requirements of the part to be detected of the specification, including a detection position and the characteristics of the part to be detected;
s2: placing a detection component: stably placing the part to be detected on a detection station to be detected according to requirements;
s3: surface cleaning: the outer surface of the part to be detected is cleaned in a non-contact manner by using a fan, so that the surface of the part to be detected is not affected by floating ash during detection;
s4: and (3) scanning image processing: the part to be detected is scanned into a picture, and the scanned picture is processed, so that picture information can be better extracted;
s5: and (3) scratch defect analysis: identifying and analyzing whether the surface has the scratch defect according to the image processed by the scanning image, and if so, further analyzing the scanned scratch defect;
s6: the results show that: and displaying the scanned scratch defect of the surface of the part and various data of the scratch defect on a display screen, and giving a corresponding processing scheme according to the data.
2. The method for detecting the scratch defects on the surface of the metal part of the communication electrical appliance according to claim 1, wherein in the step S1, the step of scanning the sample construction specifically comprises the following steps:
s11: sample scanning: the method comprises the following steps of (1) finding a sample of a part to be detected, and carrying out three-dimensional scanning on a plurality of directions of the sample to obtain images of all directions of the sample to be detected for analysis;
s12: image feature extraction: extracting meaningful features in the image by utilizing an image segmentation technology according to the image scanned in the sample scanning, and modeling according to the features;
s13: selecting a detection surface: manually selecting the three-dimensional image scanned from the sample, selecting one or more specific surfaces for scanning analysis, and storing the selected specific surfaces as the basis for subsequent detection of the large-volume parts;
s14: image array segmentation: and selecting the formed specific surface image according to the sample scanning and the detection surface and combining the specific surface image with the data extracted in the image characteristic extraction, segmenting the image of the surface to be detected according to equal parts, and storing the segmentation position as the basis of subsequent detection parts in large goods.
3. The method as claimed in claim 2, wherein in step S12, the meaningful features in the image feature extraction include the outer contour of the image and different scanned surface edges, so as to prepare for subsequent detection and positioning.
4. The method as claimed in claim 3, wherein in step S4, the scanning image processing comprises the following steps:
s41: scanning the surface of the part: scanning a component to be detected to form a scanned image;
s42: image feature comparison: comparing the modeling of the sample with the part to be detected according to the steps of image feature extraction and detection surface selection;
s43: and (3) secondary image array segmentation: dividing the surface image of the component to be detected according to the division position stored in the image array division, and dividing the whole surface treatment into different array small area treatments;
s44: image enhancement: and enhancing the image subjected to the secondary image array segmentation processing, strengthening the high-frequency component of the image, improving the definition of the image and emphasizing the salient details in the image.
5. The method as claimed in claim 4, wherein in step S42, the image feature comparison is performed in such a way that the model extracted from the image feature is overlapped with the edge profile of the component to be detected, if there is a slight difference, the model position of the sample is corrected in the system so that the model can be overlapped with the component to be detected, and then the detection surface is positioned according to the specific detection surface selected from the detection surface selection.
6. The method as claimed in claim 5, wherein in step S5, the scratch defect analysis comprises the following steps:
s51: and (3) identifying scratches: identifying the image after the secondary image array segmentation and the image enhancement, and distinguishing whether the surface has scratch defects;
s52: releasing: if the scratch defects are not distinguished in the scratch identification, the surface of the part is not scratched, and the part is immediately released and collected;
s53: array combinatorial analysis: if the scratches are identified on the surface of the part and span two or more divided array small areas, the scratches in different array small areas are automatically spliced to form a complete scratch defect;
s54: positioning scratches: positioning on the component scan surface according to the identified scratches;
s55: three-dimensional depth scanning; the laser scanning is directly carried out on the positioned scratch in the scratch positioning, and the specific depth of the scratch is detected.
7. The method as claimed in claim 6, wherein the step of S6, the result display includes the following steps:
s61: and (3) data measurement: measuring various data of the scratch by scratch identification and three-dimensional depth scanning;
s62: patterning: the scanning surface is patterned according to the scanning image processing and the scratch defect analysis, and the scanning surface outline and the scratch shape and position are formed only by lines in the image;
s63: labeling: marking the measured various data in the composition in detail through a data measuring step;
s64: and (4) alarming: alarming and reminding are carried out by sound, and the problem that the scratch defect exists on the surface of the part is prompted to a worker;
s65: analysis of treatment protocol: different treatment schemes, including grinding, filling or re-melting are analyzed according to the measured scratch data.
8. The method as claimed in claim 7, wherein in step S61, the measured data includes length, depth, number and position of the scratch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129987.1A CN114519704A (en) | 2022-02-11 | 2022-02-11 | Method for detecting scratch defects on surfaces of metal parts of communication electrical appliances |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129987.1A CN114519704A (en) | 2022-02-11 | 2022-02-11 | Method for detecting scratch defects on surfaces of metal parts of communication electrical appliances |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114519704A true CN114519704A (en) | 2022-05-20 |
Family
ID=81596305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210129987.1A Pending CN114519704A (en) | 2022-02-11 | 2022-02-11 | Method for detecting scratch defects on surfaces of metal parts of communication electrical appliances |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114519704A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116952958A (en) * | 2023-09-18 | 2023-10-27 | 杭州百子尖科技股份有限公司 | Defect detection method, device, electronic equipment and storage medium |
-
2022
- 2022-02-11 CN CN202210129987.1A patent/CN114519704A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116952958A (en) * | 2023-09-18 | 2023-10-27 | 杭州百子尖科技股份有限公司 | Defect detection method, device, electronic equipment and storage medium |
| CN116952958B (en) * | 2023-09-18 | 2023-12-29 | 杭州百子尖科技股份有限公司 | Defect detection method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107543828B (en) | Workpiece surface defect detection method and system | |
| CN109801267B (en) | Inspection target defect detection method based on feature point detection and SVM classifier | |
| CN114140679B (en) | Defect fusion method, device, recognition system and storage medium | |
| CN104897062A (en) | Visual measurement method and device for shape and position deviation of part non-coplanar parallel holes | |
| JP2001505299A (en) | Automatic sorter / scrutinizer by enlarged optical inspection of semiconductor wafer | |
| CN113781486B (en) | IC card image defect detection method | |
| CN107102009A (en) | A kind of method of the cylinder spool quality testing based on machine vision | |
| CN116993744B (en) | Weld defect detection method based on threshold segmentation | |
| WO2024002187A1 (en) | Defect detection method, defect detection device, and storage medium | |
| CN113850749A (en) | Method for training defect detector | |
| CN114519704A (en) | Method for detecting scratch defects on surfaces of metal parts of communication electrical appliances | |
| CN115035092A (en) | Image-based bottle detection method, device, equipment and storage medium | |
| JP2004259114A (en) | Object identification method, object identification device, and object identification program | |
| CN103245667A (en) | Method and system for automatically detecting mechanical scratches | |
| CN110426395B (en) | Method and device for detecting surface of solar EL battery silicon wafer | |
| CN110672620B (en) | Chip defect detection method and system | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN109015632A (en) | A kind of robot hand end localization method | |
| CN107516329B (en) | Positioning method for oil holes of speed reducer | |
| TW419634B (en) | Automatic detection system and method using bar code positioning | |
| CN109934800A (en) | A kind of localization method and system of cigarette packet paperboard | |
| CN111707672A (en) | Method for detecting surface defects of wind power rotary supporting piece | |
| CN109991232B (en) | Chip edge breakage defect detection method | |
| CN111046878B (en) | Data processing method and device, computer storage medium and computer | |
| CN114187269A (en) | Method for rapidly detecting surface defect edge of small-sized device |
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 |