CN111915607A - Metal film resistor surface strip defect detection method based on machine vision - Google Patents

Metal film resistor surface strip defect detection method based on machine vision Download PDF

Info

Publication number
CN111915607A
CN111915607A CN202010897767.4A CN202010897767A CN111915607A CN 111915607 A CN111915607 A CN 111915607A CN 202010897767 A CN202010897767 A CN 202010897767A CN 111915607 A CN111915607 A CN 111915607A
Authority
CN
China
Prior art keywords
strip
metal film
film resistor
machine vision
image
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
Application number
CN202010897767.4A
Other languages
Chinese (zh)
Inventor
杨海东
王华龙
宋秋云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute
Foshan Guangdong University CNC Equipment Technology Development Co. Ltd
Original Assignee
Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute
Foshan Guangdong University CNC Equipment Technology Development Co. Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute, Foshan Guangdong University CNC Equipment Technology Development Co. Ltd filed Critical Foshan Nanhai Guangdong Technology University CNC Equipment Cooperative Innovation Institute
Priority to CN202010897767.4A priority Critical patent/CN111915607A/en
Publication of CN111915607A publication Critical patent/CN111915607A/en
Pending legal-status Critical Current

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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/8901—Optical details; Scanning details
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
    • G01N21/8921—Streaks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/952—Inspecting the exterior surface of cylindrical bodies or wires
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration by the use of histogram techniques
    • G06T5/70—
    • 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
    • G06T7/10—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
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N2021/845—Objects on a conveyor
    • G01N2021/8455—Objects on a conveyor and using position detectors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/8901—Optical details; Scanning details
    • G01N2021/8908—Strip illuminator, e.g. light tube
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details
    • 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

Abstract

The invention discloses a method for detecting the surface strip defects of a metal film resistor based on machine vision, which comprises the following steps: s01: when the metal film resistor moves to the sight line range of the camera, the camera continuously shoots at least three images; wherein the metal film resistor is positioned on the movable track and can rotate around a lead in the middle of the metal film resistor in a self-rotating mode; the metal film resistor rotates exactly for a circle within the sight range of the camera; s02: carrying out denoising pretreatment on the shot image; s03: segmenting the image subjected to denoising pretreatment; s04: and identifying the number of strip outlines and the number of times of change of pixels in the strip outlines on the segmented image so as to judge the strip defects on the surface of the metal film resistor. The method for detecting the defects of the metal film resistor surface strips based on the machine vision improves the detection efficiency and reduces the detection cost.

Description

Metal film resistor surface strip defect detection method based on machine vision
Technical Field
The invention relates to the field of metal film resistor defect detection, in particular to a machine vision-based metal film resistor surface strip defect detection method.
Background
Detecting the strip on the resistor is an important indicator for judging whether the resistor is qualified, and the identification of the strip is directly related to the checking and replacing of the resistor. Currently, the strips on the resistors also require visual inspection for defects, which is labor intensive and inefficient. In addition, visual inspection by the naked eye is also affected by workers and some defects are not correctly identified. Due to the small size of the resistor, visual fatigue is likely to occur after a long time operation, which increases an unreliable factor of inspection accuracy. Therefore, applying a surface defect inspection system instead of visual inspection can make up for the deficiencies of conventional inspection methods.
The Machine Vision System (MVS) is the intelligence to translate a target object into an image and transmit it to a dedicated image processing system. And the MVS processes the signal to obtain target characteristics, and then controls the motion of the user-defined equipment according to the judgment result. The machine vision technology is widely applied to the industrial fields of automatic detection, nondestructive detection, precise metering and the like. The purpose of MVS is to use such a machine instead of the human eye for judgment. In foreign countries, machine vision is widely used in Printed Circuit Boards (PCBs), classification and identification of agricultural products, strip width measurement of stainless steel, and edge detection. Currently, MVS is mainly used to identify defects on a flat surface, while relatively few studies have been made on the surface of small cylindrical products. Particularly, the maximum diameter of the metal film resistor is only 2.5mm aiming at the defect detection of the surface of the metal film resistor. Because it is a cylinder, the camera cannot capture the entire surface at once. Therefore, the key technology is how to collect complete surface defects and accurately identify the surface defects. A lot of existing metal film resistors are military products, need to be checked one by one, cannot be subjected to sampling inspection, and increase the workload of detection. The surface defects of the metal film resistor are mainly concentrated on the strips, and comprise three defects of strip loss, strip insufficiency and strip combination. If a machine vision system can be adopted to detect the defects of the metal film resistor surface strips, the detection efficiency can be greatly improved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a method for detecting the defects of the surface strips of the metal film resistor based on machine vision, so that the detection efficiency is improved, and the detection cost is reduced.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for detecting defects of metal film resistor surface strips based on machine vision comprises the following steps:
s01: when the metal film resistor moves to the sight line range of the camera, the camera continuously shoots at least three images; wherein the metal film resistor is positioned on the movable track and can rotate around a lead in the middle of the metal film resistor in a self-rotating mode; the metal film resistor rotates exactly for a circle within the sight range of the camera;
s02: carrying out denoising pretreatment on the shot image;
s03: segmenting the image subjected to denoising pretreatment;
s04: and identifying the number of strip outlines and the number of times of change of pixels in the strip outlines on the segmented image so as to judge the strip defects on the surface of the metal film resistor.
Further, in the step S01, during the camera shooting process, a ring-shaped LED lamp is used as a light source.
Further, in step S01, polarizers are respectively disposed on the camera lens and the LED lamp.
Further, in step S02, the image is preprocessed by histogram equalization and median filtering.
Further, the camera captures images in black and white.
Further, in step S03, the image is segmented by using a global threshold segmentation method.
Further, the step S01 further includes: the processing center merges the at least three images into a profile.
Further, the step S04 specifically includes:
s041: determining the orientation and the shape of a strip in the metal film resistor, finding out the position of a left end point or a right end point of the strip in the side view, and intercepting a strip-shaped graph by taking the end point as a starting point to form a strip profile, wherein the number of the strip profiles is N1;
s042: judging whether a strip pixel area is included besides the strip outline or not, if so, restoring the strip outline according to the strip pixel area and the direction and the shape of the strip, and judging that the strip is incomplete, wherein the number of the strip outlines is N; if the number of the strip outlines is N smaller than the threshold value, judging that the strip on the surface of the metal film resistor is missing;
s043: judging whether the strip defects exist according to the pixel change times T in each strip outline; if the number of times T of pixel change in the strip outline is greater than 0, the strip is not complete.
Further, if the gap between the two adjacent stripe profiles is equal to 0, the two stripes are judged to be merged.
The invention has the beneficial effects that: the rotating metal film resistor is continuously shot to form a complete metal film resistor surface image, the image processing such as denoising and segmentation is carried out on the image, and then the strip recognition is carried out. The method can detect three resistors in one period, and has accurate defect identification and high detection speed. The method is particularly suitable for cylindrical products, can effectively utilize one camera to capture the full-surface image of the cylindrical product, and reduces the detection cost.
Drawings
FIG. 1 is a flow chart of a method for detecting defects of a metal film resistor surface strip based on machine vision.
Detailed Description
The invention will be further described with reference to the accompanying drawings and the detailed description below:
as shown in the attached figure 1, the invention provides a method for detecting the defects of the metal film resistor surface strips based on machine vision, which comprises the following steps:
s01: when the metal film resistor moves to the sight line range of the camera, the camera continuously shoots at least three images; the metal film resistor is positioned on the movable track and can rotate around a lead in the middle of the metal film resistor in a self-rotating mode; the metal film resistor rotates exactly one circle when in the sight range of the camera.
The performance of the illumination system is critical to the machine vision system. It not only acts as a lighting. More importantly, a significant difference is created between the detection area and the background, avoiding reflections. Therefore, the good illumination system can reduce the difficulty of image processing and improve the detection precision. The illumination system adopts the annular LED lamp as a light source. LED lamps are commonly used as illumination sources for MVSs due to their low power consumption, long life, and excellent optical properties. The annular lamp is beneficial to the research object (metal film resistor) to obtain uniformly distributed light. Since the detection surface of the metal film resistor is irregular and a large number of metal areas are distributed on the surface, reflection is inevitable in the illumination engineering. How to eliminate reflection is also the key point of the illumination system in the present invention, and it is not limited to add a polarizer to the camera lens and the light source respectively.
Because the metal film resistor is cylindrical, a plurality of strips are distributed on the side surface of the cylindrical metal film resistor and are used for representing the performance and indexes of the metal film resistor. One camera cannot photograph the entire side surface of the cylindrical metal film resistor at one time. In order to solve the problem, the metal film resistors are sequentially arranged on the moving track, and the moving track can drive the metal film resistors to uniformly advance. The metal film resistor on the moving track can rotate around the lead, and the lead penetrates through the center of the cylindrical metal film resistor. The camera is arranged on one side of the moving track, the sensor is arranged at a position, close to the metal film resistor, of the camera in the direction, when the sensor senses that the metal film resistor comes, the camera starts to continuously capture at least three images, and the metal film resistor just rotates for a circle within the shooting time of the three images. For subsequent uniform processing of the images, the processing center can merge at least three images into a profile.
According to the invention, by setting the shooting frame rate of the camera and the rotating speed of the metal film resistor, if three continuous images need to be shot, the camera just finishes three-frame image shooting when the metal film resistor rotates for one circle through the setting. The shot image for each metal film resistor is not too much or too little, and if the shot image is too large, the complexity of merging images in a processing center is increased; if the number of captured images is too small, the composite image does not sufficiently reflect the cylindrical metal film resistance profile.
S02: carrying out denoising pretreatment on the shot image; the image may be pre-processed by histogram equalization and median filtering. The central idea of the histogram equalization process is to change the gray level histogram of the original image from a certain gray level interval in the comparison set to a uniform distribution in the whole gray level range. Histogram equalization is the non-linear stretching of an image to reassign image pixel values so that the number of pixels within a certain gray scale range is approximately the same. Histogram equalization is the change of the histogram distribution of a given image to a "uniform" distribution histogram distribution.
The median filtering method is a non-linear smoothing technique, and sets the gray value of each pixel point as the median of all the gray values of the pixel points in a certain neighborhood window of the point. The median filtering is a nonlinear signal processing technology which is based on the ordering statistical theory and can effectively inhibit noise, and the basic principle of the median filtering is to replace the value of one point in a digital image or a digital sequence by the median of all point values in a neighborhood of the point, so that the surrounding pixel values are close to the true values, and isolated noise points are eliminated. The method is to sort the pixels in the plate according to the size of the pixel value by using a two-dimensional sliding template with a certain structure, and generate a monotonously ascending (or descending) two-dimensional data sequence.
Due to the fact that the pixel difference between the strip and the metal is large, noise interference can be removed through the processing, and the strip pixels can be further highlighted in the image.
S03: segmenting the image subjected to denoising pretreatment; the image acquired in the invention is preferably a black-and-white image, so that the image is segmented by adopting a global threshold segmentation method and is used for distinguishing a strip from other areas.
S04: and identifying the number of strip outlines and the number of times of change of pixels in the strip outlines on the segmented image so as to judge the strip defects on the surface of the metal film resistor. The strips on the surface of the metal film resistor are generally distributed annularly by taking the conducting wire as a center, namely the strips are rectangular in a side view. In the invention, the lack of stripes refers to the lack of one stripe as a whole, the lack of stripes refers to the lack of one stripe as a part, and the combination of stripes refers to the combination of at least two stripes, namely the space between at least two stripes is equal to 0.
S041: the orientation and shape of the strip in the metal film resistor is determined, i.e. the approximate orientation and shape of its corresponding strip is determined according to the model and batch of the metal film resistor on the moving guide, assuming that the strip shape is spread out as a rectangle in the side image. Finding out the position of the left end point or the right end point of the strip in the side view, and intercepting a rectangular frame with a fixed size by taking the end point as a starting point, wherein the rectangular frame is a strip profile, and the number of the strip profiles (the number of the rectangular frames) is N1;
s042: judging whether a stripe pixel area is included besides the stripe outline or not, wherein the step is mainly to confirm that the stripe exists but the endpoint of the stripe is missing, and the number of the rectangular boxes in the step S041 only represents the number of the stripes with intact endpoints; if the end of the band is missing, it is not identified in the above step.
If a band pixel area exists besides the band outline, the judgment is mainly carried out according to pixels in the segmented image, the band outline is restored according to the direction and the shape of the band pixel area and the band, the band is not complete, and the band is at least short of the area where the end point is located. The number of the strip profiles is N; note that: if there is no band pixel area outside the band contour, N is equal to N1. If the number of the strip outlines is N smaller than the threshold value, judging that the strip on the surface of the metal film resistor is missing; the threshold herein refers to the number of strips that should be provided for the metal film resistor of the model or batch.
In this step, if the gap between the two adjacent strip profiles is equal to 0, it is determined that the two strips are merged, i.e. the strips on the surface of the metal film resistor coincide.
S043: judging whether the strip defects exist according to the pixel change times T in each strip outline; if the number of times T of pixel change in the strip outline is greater than 0, the strip is not complete. This is because the pixel values in the band contour should be substantially the same in the side view, and if the pixel value change is larger than the difference threshold, it can be considered that the pixel value change area is a boundary between the band and the metal, that is, a gap occurs in the band, and it is determined that the band is not complete.
The rotating metal film resistor is continuously shot to form a complete metal film resistor surface image, the image processing such as denoising and segmentation is carried out on the image, and then the strip recognition is carried out. The method can detect three resistors in one period, and has accurate defect identification and high detection speed. The method is particularly suitable for cylindrical products, can effectively utilize one camera to capture the full-surface image of the cylindrical product, and reduces the detection cost.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.

Claims (9)

1. A method for detecting defects of metal film resistor surface strips based on machine vision is characterized by comprising the following steps:
s01: when the metal film resistor moves to the sight line range of the camera, the camera continuously shoots at least three images; wherein the metal film resistor is positioned on the movable track and can rotate around a lead in the middle of the metal film resistor in a self-rotating mode; the metal film resistor rotates exactly for a circle within the sight range of the camera;
s02: carrying out denoising pretreatment on the shot image;
s03: segmenting the image subjected to denoising pretreatment;
s04: and identifying the number of strip outlines and the number of times of change of pixels in the strip outlines on the segmented image so as to judge the strip defects on the surface of the metal film resistor.
2. The method for detecting defects of metal film resistor surface strips based on machine vision as claimed in claim 1, wherein in the camera shooting process in step S01, a ring-shaped LED lamp is used as a light source.
3. The method for detecting defects on metal film resistor surface strips based on machine vision as claimed in claim 2, wherein in step S01, polarizers are respectively disposed on the camera lens and the LED lamp.
4. The method for detecting defects on surface strips of metal film resistor based on machine vision as claimed in claim 1, wherein histogram equalization and median filtering are used to preprocess the image in step S02.
5. The method for detecting the defects of the metal film resistor surface strips based on the machine vision as claimed in claim 1, wherein the camera takes the black and white image.
6. The method for detecting defects of metal film resistor surface strips based on machine vision as claimed in claim 5, wherein the image is segmented by global threshold segmentation in step S03.
7. The method for detecting defects on metal film resistor surface strips based on machine vision as claimed in claim 1, wherein said step S01 further comprises: the processing center merges the at least three images into a profile.
8. The method according to claim 7, wherein the step S04 specifically includes:
s041: determining the orientation and the shape of a strip in the metal film resistor, finding out the position of a left end point or a right end point of the strip in the side view, and intercepting a strip-shaped graph by taking the end point as a starting point to form a strip profile, wherein the number of the strip profiles is N1;
s042: judging whether a strip pixel area is included besides the strip outline or not, if so, restoring the strip outline according to the strip pixel area and the direction and the shape of the strip, and judging that the strip is incomplete, wherein the number of the strip outlines is N; if the number of the strip outlines is N smaller than the threshold value, judging that the strip on the surface of the metal film resistor is missing;
s043: judging whether the strip defects exist according to the pixel change times T in each strip outline; if the number of times T of pixel change in the strip outline is greater than 0, the strip is not complete.
9. The method of claim 8, wherein if the gap between the contour of two adjacent strips is equal to 0, the two strips are determined to merge.
CN202010897767.4A 2020-08-31 2020-08-31 Metal film resistor surface strip defect detection method based on machine vision Pending CN111915607A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010897767.4A CN111915607A (en) 2020-08-31 2020-08-31 Metal film resistor surface strip defect detection method based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010897767.4A CN111915607A (en) 2020-08-31 2020-08-31 Metal film resistor surface strip defect detection method based on machine vision

Publications (1)

Publication Number Publication Date
CN111915607A true CN111915607A (en) 2020-11-10

Family

ID=73266411

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010897767.4A Pending CN111915607A (en) 2020-08-31 2020-08-31 Metal film resistor surface strip defect detection method based on machine vision

Country Status (1)

Country Link
CN (1) CN111915607A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1148457A (en) * 1997-08-07 1999-02-23 Dainippon Printing Co Ltd Method and apparatus for inspecting stripe like defect
US6778694B1 (en) * 1997-03-28 2004-08-17 Sollac Method for examining doubtful zones on the surface of an unwinding strip by image segmentation
CN101477065A (en) * 2009-01-08 2009-07-08 西安电子科技大学 IC defect classification method based on defect boundary value change frequency
CN105067629A (en) * 2015-07-24 2015-11-18 北京理工大学 Color ring resistor appearance defect and resistance value integration detection method
CN105357433A (en) * 2015-10-13 2016-02-24 哈尔滨工程大学 High-speed rotating focal length self-adaptive panoramic imaging method
CN105784713A (en) * 2016-03-11 2016-07-20 南京理工大学 Sealing ring surface defect detection method based on machine vision
CN106780473A (en) * 2016-12-23 2017-05-31 西安交通大学 A kind of magnet ring defect multi-vision visual detection method and system
CN107328781A (en) * 2017-05-23 2017-11-07 镇江苏仪德科技有限公司 A kind of columnar product detection method of surface flaw and device based on machine vision

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6778694B1 (en) * 1997-03-28 2004-08-17 Sollac Method for examining doubtful zones on the surface of an unwinding strip by image segmentation
JPH1148457A (en) * 1997-08-07 1999-02-23 Dainippon Printing Co Ltd Method and apparatus for inspecting stripe like defect
CN101477065A (en) * 2009-01-08 2009-07-08 西安电子科技大学 IC defect classification method based on defect boundary value change frequency
CN105067629A (en) * 2015-07-24 2015-11-18 北京理工大学 Color ring resistor appearance defect and resistance value integration detection method
CN105357433A (en) * 2015-10-13 2016-02-24 哈尔滨工程大学 High-speed rotating focal length self-adaptive panoramic imaging method
CN105784713A (en) * 2016-03-11 2016-07-20 南京理工大学 Sealing ring surface defect detection method based on machine vision
CN106780473A (en) * 2016-12-23 2017-05-31 西安交通大学 A kind of magnet ring defect multi-vision visual detection method and system
CN107328781A (en) * 2017-05-23 2017-11-07 镇江苏仪德科技有限公司 A kind of columnar product detection method of surface flaw and device based on machine vision

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KIYOSHI NIKAWA 等: "Novel Method for Defect Detection in AI Stripes by Means of Laser Beam Heating and Detection of Changes in Electrical Resistance", 《JAPANESE JOURNAL OF APPLIED PHYSICS》, pages 2260 - 2265 *
李存荣;王东升;: "大型齿环齿形检测的机器视觉系统", 《机械设计与制造》, no. 09, pages 83 - 85 *
毛林威: "轴向色环电阻质量自动检测系统的设计", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 138 - 7179 *

Similar Documents

Publication Publication Date Title
CN110596129B (en) Sheet glass edge flaw detection system based on image acquisition
CN109816678B (en) Automatic nozzle atomization angle detection system and method based on vision
CN108760747A (en) A kind of 3D printing model surface defect visible detection method
CN113109348B (en) Paddle image transfer printing defect identification method based on machine vision
CN102175692A (en) System and method for detecting defects of fabric gray cloth quickly
CN107895362B (en) Machine vision method for detecting quality of miniature wiring terminal
Liu et al. Automatic detection technology of surface defects on plastic products based on machine vision
CN109900719B (en) Visual detection method for blade surface knife lines
CN108257171A (en) Car radar assembling aperture detection method based on light vision
CN114881915A (en) Symmetry-based mobile phone glass cover plate window area defect detection method
CN115184359A (en) Surface defect detection system and method capable of automatically adjusting parameters
CN111665251A (en) Visual detection method for surface defects
CN113177924A (en) Industrial production line product flaw detection method
CN112819844A (en) Image edge detection method and device
CN111487192A (en) Machine vision surface defect detection device and method based on artificial intelligence
CN114723668A (en) Cathode copper quality detection method and system based on area-array camera
CN110516725B (en) Machine vision-based wood board stripe spacing and color detection method
CN110044919A (en) A kind of detection device and its detection method for mirror surfaces scratch
CN114359155A (en) Film laminating method and system
CN109387524A (en) Thread defect detection method and device based on linearly polarized photon
CN114577805A (en) MiniLED backlight panel defect detection method and device
CN106370673A (en) Automatic lens flaw detection method
CN111833350A (en) Machine vision detection method and system
CN111915607A (en) Metal film resistor surface strip defect detection method based on machine vision
CN109584239B (en) High-light object surface defect detection system and method based on reflected light

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