CN113935981A - Flaw quantitative evaluation method based on AOI detection - Google Patents
Flaw quantitative evaluation method based on AOI detection Download PDFInfo
- Publication number
- CN113935981A CN113935981A CN202111246757.5A CN202111246757A CN113935981A CN 113935981 A CN113935981 A CN 113935981A CN 202111246757 A CN202111246757 A CN 202111246757A CN 113935981 A CN113935981 A CN 113935981A
- Authority
- CN
- China
- Prior art keywords
- flaw
- flaws
- calculating
- image
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000011158 quantitative evaluation Methods 0.000 title claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 230000007547 defect Effects 0.000 claims abstract description 15
- 238000010586 diagram Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000000926 separation method Methods 0.000 claims description 8
- 230000001788 irregular Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 230000004075 alteration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- 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
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of AOI flaw detection, and discloses a flaw quantitative evaluation method based on AOI detection, which comprises the following steps: s1, separating flaws, separating the flaws from the background picture by using image difference steps before and after noise removal, gray stretching, filtering and filtering according to the areas where the flaws are located on the detected flaw picture, calculating the minimum circumscribed rectangle width according to the flaw outline, and respectively storing the separated flaw picture and the circumscribed rectangle frame diagram where the flaws are located. The defect quantitative evaluation method based on AOI detection can realize the functions of appearance defect quantitative evaluation and automatic detection, does not need to rely on manual work to judge through subjective experience, avoids subjective factor interference as much as possible, not only improves the accuracy of defect detection results, but also improves the defect detection efficiency and reduces the labor intensity of workers.
Description
Technical Field
The invention relates to the technical field of AOI flaw detection, in particular to a flaw quantitative evaluation method based on AOI detection.
Background
AOI is called automatic optical inspection in Chinese, and is equipment for inspecting common defects encountered in welding production based on an optical principle.
At present, in the field of AOI flaw detection, the detected flaws have sizes, whether each flaw affects the function and performance of a product, and whether the corresponding flaw is within an acceptable range, a quantitative evaluation method does not exist at present, and whether the flaws can be accepted or not is judged manually through subjective experience.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a flaw quantitative evaluation method based on AOI detection, which can realize the functions of appearance flaw quantitative evaluation and automatic detection, does not need to rely on manual judgment through subjective experience, avoids the interference of subjective factors as much as possible, not only improves the accuracy of flaw detection results, but also improves the efficiency of flaw detection, reduces the labor intensity of workers, and solves the problems that the existing flaw detection through manual work is influenced by more interference factors, the accuracy of the flaw detection results is easily influenced, and the flaw detection efficiency is lower.
(II) technical scheme
In order to realize the purposes that the method has the functions of quantitative evaluation and automatic detection of the appearance flaws, does not need to rely on manual judgment through subjective experience, avoids interference of subjective factors as much as possible, not only improves the accuracy of flaw detection results, but also improves the flaw detection efficiency and reduces the labor intensity of workers, the invention provides the following technical scheme: a flaw quantitative evaluation method based on AOI detection comprises the following steps:
s1, separating flaws, separating the flaws from a background picture by using image difference steps before and after noise removal, gray stretching, filtering and filtering according to the areas where the flaws are located on the detected flaw picture, calculating the minimum circumscribed rectangle width according to the flaw outline, and respectively storing the separated flaw picture and the circumscribed rectangle block diagram where the flaws are located;
s2, calculating the Area of the flaw, wherein the Area of the flaw is expressed by the number of the pixel points of the flaw because most of the detected flaws are irregular, and the Area of the flaw acquired by the pixel points is calculated according to the flaw image separated in the step S1;
s3 calculating the length and height of the minimum bounding rectangle, and calculating the width W and height H of the minimum bounding rectangle according to the bounding rectangle where the flaw separated in the step S1 is located;
s4, calculating contrast information, calculating the average gray level of the flaw and the average gray level of the minimum circumscribed rectangular frame, and then calculating the difference value of 2 values as the contrast information CR;
s5, calculating a comprehensive evaluation score, namely calculating the comprehensive evaluation score Sreore according to a formula after obtaining the width W and the height H of a flaw external rectangular frame, the Area of the flaw and contrast information CR;
and S6, finishing the evaluation, finishing the statistics of the related data, and finishing the related data into chart information.
Preferably, the specific defect separation step in step S1 is as follows:
a. acquiring a product image containing a flaw by a camera;
b. removing noise to obtain image information only with flaw information;
c. the gray level dynamic range during image processing is improved through gray level stretching;
d. obtaining an image only containing background information through a low-pass filter;
e. and performing difference on the images before and after filtering to obtain a flaw image.
Preferably, the specific calculation formula of the contrast information CR in step S4 is as follows:
wherein n and m respectively represent the number of pixels of the flaw and the minimum circumscribed rectangle frame, GrayiAnd expressing the gray value of the ith pixel point.
Preferably, the calculation formula of the comprehensive evaluation score Sreore in step S5 is as follows:
score is α × W + β × H + δ × Area + ∈ × CR, where α, β, δ, and ∈respectivelydenote the weight of the width, height, Area, and contrast information in the quantitative evaluation model.
(III) advantageous effects
Compared with the prior art, the invention provides a flaw quantitative evaluation method based on AOI detection, which has the following beneficial effects:
the flaw quantitative evaluation method based on AOI detection comprises the steps of firstly carrying out flaw separation based on an AOI detection technology when in appearance flaw detection, then carrying out flaw Area calculation, minimum circumscribed rectangle frame length and height calculation, contrast information calculation and comprehensive evaluation score calculation, wherein on a detected flaw picture, according to the Area of the flaw, the flaw is separated from a background picture by using image aberration steps before and after noise removal, gray stretching, filtering and filtering, the width of the minimum circumscribed rectangle is calculated according to the flaw outline, the separated flaw picture and the circumscribed rectangle frame diagram where the flaw is located are respectively stored, meanwhile, as most of the detected flaws are irregular shapes, the Area of the flaw is expressed by the number of pixel points of the flaw, the Area Area of the flaw is obtained by calculating the pixel points of the flaw picture according to the flaw picture separated in the step, and the width W and the height H of the circumscribed rectangle frame diagram are calculated, the method comprises the steps of calculating the average gray level of a flaw and the average gray level of a minimum external rectangular frame, then calculating the difference value of 2 values as contrast information CR, then calculating a comprehensive evaluation Score Sreore according to a formula after obtaining the width W and the height H of the flaw external rectangular frame, the Area of the flaw and the contrast information CR, wherein the larger the value of the integral evaluation Score Score is, the larger the influence of the flaw is, the specific quantification of the flaw detected by the AOI is realized, and the AOI automatic detection is time-saving and labor-saving.
Drawings
FIG. 1 is a schematic diagram of an overall structure of a flaw quantitative evaluation method based on AOI detection according to the present invention;
FIG. 2 is a flowchart illustrating an overall method for quantitatively evaluating defects based on AOI detection according to the present invention;
FIG. 3 is a schematic diagram illustrating the effect of defect separation in the method for quantitatively evaluating defects based on AOI detection according to the present invention;
FIG. 4 is a flowchart illustrating the separation of specific defects in a method for quantitatively evaluating defects based on AOI detection according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-4, a method for quantitatively evaluating defects based on AOI detection includes the following steps:
s1, separating flaws, separating the flaws from a background picture by using image difference steps before and after noise removal, gray stretching, filtering and filtering according to the areas where the flaws are located on the detected flaw picture, calculating the minimum circumscribed rectangle width according to the flaw outline, and respectively storing the separated flaw picture and the circumscribed rectangle block diagram where the flaws are located;
s2, calculating the Area of the flaw, wherein the Area of the flaw is expressed by the number of the pixel points of the flaw because most of the detected flaws are irregular, and the Area of the flaw acquired by the pixel points is calculated according to the flaw image separated in the step S1;
s3 calculating the length and height of the minimum bounding rectangle, and calculating the width W and height H of the minimum bounding rectangle according to the bounding rectangle where the flaw separated in the step S1 is located;
s4, calculating contrast information, calculating the average gray level of the flaw and the average gray level of the minimum circumscribed rectangular frame, and then calculating the difference value of 2 values as the contrast information CR;
s5, calculating a comprehensive evaluation score, namely calculating the comprehensive evaluation score Sreore according to a formula after obtaining the width W and the height H of a flaw external rectangular frame, the Area of the flaw and contrast information CR;
and S6, finishing the evaluation, finishing the statistics of the related data, finishing the evaluation into chart information, and finishing the chart information to be convenient to watch.
The specific flaw separation step in step S1 is as follows:
a. acquiring a product image containing a flaw by a camera;
b. removing noise to obtain image information only with flaw information;
c. the gray level dynamic range during image processing is improved through gray level stretching;
d. obtaining an image only containing background information through a low-pass filter;
e. and performing subtraction on the images before and after filtering to obtain a flaw image, specifically quantifying the flaws detected by the AOI flaws through the steps, and automatically detecting the AOI flaws, wherein the detection process is time-saving and labor-saving.
The specific calculation formula of the contrast information CR in step S4 is as follows:
wherein n and m respectively represent the number of pixels of the flaw and the minimum circumscribed rectangle frame, GrayiAnd expressing the gray value of the ith pixel point.
The calculation formula of the comprehensive evaluation score Sreore in step S5 is as follows:
the Score is α × W + β × H + δ × Area + ∈ × CR, where α, β, δ, and ∈ respectively denote weights of width, height, Area, and contrast information in the quantitative evaluation model, and a larger value of the overall evaluation Score indicates a larger influence of flaws, and the weight of each value can be adjusted according to the actual condition of the product.
To sum up, the method for quantitatively evaluating the flaws based on AOI detection comprises the steps of flaw separation based on an AOI detection technology when the flaws are detected in appearance, flaw area calculation, minimum circumscribed rectangle frame length and height calculation, contrast information calculation and comprehensive evaluation score calculation, wherein on a detected flaw image, the flaws are separated from a background image by the steps of removing noise, gray stretching, filtering and image difference before and after filtering according to the area where the flaws are located, in the separation step, a product image containing the flaws is collected by a camera, then the noise is removed to obtain image information only containing flaw information, then the gray level dynamic range during image processing is improved by gray stretching, then an image only containing the background information is obtained by a low-pass filter, and finally the images before and after filtering are used for difference to obtain the flaw image, calculating the minimum external rectangle width according to the flaw outline, respectively storing the separated flaw image and the external rectangle block diagram where the flaws are located, simultaneously, because most detected flaws are irregular in shape, expressing the Area of the flaws by using the number of pixel points of the flaws, calculating the pixel points of the flaw image separated according to the steps to obtain the Area of the flaws, calculating the width W and the height H of the flaw image in the external rectangle block diagram, then calculating the average gray scale of the flaws and the average gray scale of the minimum external rectangle frame, then calculating the difference value of 2 values as contrast information CR, then calculating a comprehensive evaluation Score Sreore according to a formula after obtaining the width W and the height H of the flaw external rectangle frame, the Area of the flaws and the contrast information CR, wherein the larger the value of the overall evaluation Score indicates the larger the influence of the flaws, and realizing the specific quantification of the flaws detected by AOI flaws, the method can realize the functions of quantitative evaluation and automatic detection of the appearance flaws without manual judgment through subjective experience, avoids interference of subjective factors as much as possible, improves the accuracy of flaw detection results, improves flaw detection efficiency and reduces labor intensity of workers.
It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. A flaw quantitative evaluation method based on AOI detection is characterized by comprising the following steps:
s1, separating flaws, separating the flaws from a background picture by using image difference steps before and after noise removal, gray stretching, filtering and filtering according to the areas where the flaws are located on the detected flaw picture, calculating the minimum circumscribed rectangle width according to the flaw outline, and respectively storing the separated flaw picture and the circumscribed rectangle block diagram where the flaws are located;
s2, calculating the Area of the flaw, wherein the Area of the flaw is expressed by the number of the pixel points of the flaw because most of the detected flaws are irregular, and the Area of the flaw acquired by the pixel points is calculated according to the flaw image separated in the step S1;
s3 calculating the length and height of the minimum bounding rectangle, and calculating the width W and height H of the minimum bounding rectangle according to the bounding rectangle where the flaw separated in the step S1 is located;
s4, calculating contrast information, calculating the average gray level of the flaw and the average gray level of the minimum circumscribed rectangular frame, and then calculating the difference value of 2 values as the contrast information CR;
s5, calculating a comprehensive evaluation score, namely calculating the comprehensive evaluation score Sreore according to a formula after obtaining the width W and the height H of a flaw external rectangular frame, the Area of the flaw and contrast information CR;
and S6, finishing the evaluation, finishing the statistics of the related data, and finishing the related data into chart information.
2. The method for quantitatively evaluating the defects based on the AOI detection as claimed in claim 1, wherein the specific defect separation step in the step S1 is as follows:
a. acquiring a product image containing a flaw by a camera;
b. removing noise to obtain image information only with flaw information;
c. the gray level dynamic range during image processing is improved through gray level stretching;
d. obtaining an image only containing background information through a low-pass filter;
e. and performing difference on the images before and after filtering to obtain a flaw image.
4. The method according to claim 1, wherein the calculation formula of the comprehensive evaluation score Sreore in step S5 is as follows:
score is α × W + β × H + δ × Area + ∈ × CR, where α, β, δ, and ∈respectivelydenote the weight of the width, height, Area, and contrast information in the quantitative evaluation model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111246757.5A CN113935981A (en) | 2021-10-26 | 2021-10-26 | Flaw quantitative evaluation method based on AOI detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111246757.5A CN113935981A (en) | 2021-10-26 | 2021-10-26 | Flaw quantitative evaluation method based on AOI detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113935981A true CN113935981A (en) | 2022-01-14 |
Family
ID=79284396
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111246757.5A Pending CN113935981A (en) | 2021-10-26 | 2021-10-26 | Flaw quantitative evaluation method based on AOI detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113935981A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114637270A (en) * | 2022-05-17 | 2022-06-17 | 成都秦川物联网科技股份有限公司 | Intelligent manufacturing industry Internet of things based on distributed control and control method |
-
2021
- 2021-10-26 CN CN202111246757.5A patent/CN113935981A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114637270A (en) * | 2022-05-17 | 2022-06-17 | 成都秦川物联网科技股份有限公司 | Intelligent manufacturing industry Internet of things based on distributed control and control method |
CN114637270B (en) * | 2022-05-17 | 2022-08-23 | 成都秦川物联网科技股份有限公司 | Intelligent manufacturing industry Internet of things based on distributed control and control method |
US11681283B1 (en) | 2022-05-17 | 2023-06-20 | Chengdu Qinchuan Iot Technology Co., Ltd. | Intelligent manufacturing industrial Internet of Things based on distributed control, control methods and media thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20170004612A1 (en) | Optical film defect detection method and system thereof | |
CN108827181B (en) | Vision-based plate surface detection method | |
CN115457037B (en) | Raw material quality inspection method for donkey-hide gelatin product production | |
CN107490582B (en) | Assembly line workpiece detection system | |
CN116559183B (en) | Method and system for improving defect judging efficiency | |
CN111986195B (en) | Appearance defect detection method and system | |
CN111047655A (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
CN109064439B (en) | Partition-based single-side light-entering type light guide plate shadow defect extraction method | |
CN116309416A (en) | Visual inspection method for surface of part | |
CN113935981A (en) | Flaw quantitative evaluation method based on AOI detection | |
CN111462056B (en) | Workpiece surface defect detection method, device, equipment and storage medium | |
CN115690089A (en) | Image enhancement preprocessing method and system for weak defect detection | |
CN117115171B (en) | Slight bright point defect detection method applied to subway LCD display screen | |
US20220076021A1 (en) | System and method for automatic visual inspection with deep learning | |
CN114820597B (en) | Smelting product defect detection method, device and system based on artificial intelligence | |
CN114998254A (en) | Method and system for automatically grading center segregation of continuous casting slab | |
JPH07333197A (en) | Automatic surface flaw detector | |
JPH08145907A (en) | Inspection equipment of defect | |
JP4403036B2 (en) | Soot detection method and apparatus | |
JPH06116914A (en) | Film deterioration diagnostic method and device thereof | |
CN112070847A (en) | Wood floor color sorting method and device | |
JP4238074B2 (en) | Surface wrinkle inspection method | |
JPH08189902A (en) | Picture processing device | |
CN117058141B (en) | Glass edging defect detection method and terminal | |
CN118095971B (en) | AD calcium milk beverage processing technology assessment method, system and medium |
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 |