CN108802051B - System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate - Google Patents
System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate Download PDFInfo
- Publication number
- CN108802051B CN108802051B CN201810749681.XA CN201810749681A CN108802051B CN 108802051 B CN108802051 B CN 108802051B CN 201810749681 A CN201810749681 A CN 201810749681A CN 108802051 B CN108802051 B CN 108802051B
- Authority
- CN
- China
- Prior art keywords
- defect
- area
- flexible substrate
- image
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G01N21/8851—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
Abstract
The invention discloses a system and a method for detecting bubble and crease defects of a linear circuit of a flexible IC substrate. The method comprises the following steps: 1) the image acquisition subsystem controls the microscope to carry out positioning shooting on the flexible substrate; 2) ensuring that the input image is a linear circuit part of the film-covered flexible substrate through an input image protection mechanism; 3) extracting a film-covered flexible substrate defect suspicion area; 4) removing salt and pepper noise, eliminating convex interference points and filling small holes in the area of the binary image through morphological processing; 5) calculating a multi-feature value for the flexible substrate pattern determined to contain defects; 6) and judging the category of the defects in the flexible substrate pattern, and marking the defect area in the original image. The invention can better avoid the false defect report of the flexible substrate imaging detection under different illumination intensities, and has higher accuracy rate for the simultaneous detection of various defects of the film-coated substrate.
Description
Technical Field
The invention belongs to the technical field of defect detection, and relates to a system and a method for detecting bubble and crease defects of a linear circuit of a flexible IC substrate.
Background
With the increase of usage rate and quality requirement of FICS, people pay more and more attention to FICS surface quality detection. From the initial determination of the existence of defects, the determination of scratches and edge damage of an IC wafer, the determination of defects of IC pins and residual glue, the measurement of line width and line distance and aperture size of FICS and the determination of short circuit and open circuit, the detection of FICS is a trend from the rough determination of the existence of defects to the specific determination of defect types. The quality inspection of finished filmed FICS products has been more focused on the inspection of defects such as oxidation, bubbles, creases, foreign matter, etc. However, at present, there are few detection algorithms or papers for these two types of defects of the film-coated circuit, and especially the bubble type defects are often found on the detection of other fields such as glass products, pills and the like. The system and the method not only realize simultaneous detection of various defects, but also can better avoid the defect false alarm of imaging detection of the linear line part of the laminated flexible substrate under different illumination intensities, and can adapt to the field requirements of factories in terms of accuracy and working efficiency.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a system and a method for detecting bubble and crease defects of a linear circuit of a flexible IC substrate.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention relates to a flexible IC substrate linear line bubble and crease defect detection system, which comprises an image acquisition subsystem, a defect detection module and a data analysis module;
the image acquisition subsystem is used for controlling the microscope to carry out positioning shooting on the flexible substrate placed on the loading platform, and the target position is the position of the area where the film covering linear line is located;
the defect detection module is used for extracting a binary image of an input pattern of the flexible substrate, judging the certainty of the defect in the binary image, extracting a defect area of the flexible substrate pattern with the defect, and calculating a multi-feature numerical value;
and the data analysis module is used for judging the defect type of the linear circuit part of the substrate and marking the defect area.
As a preferred technical scheme, the image acquisition subsystem comprises a motion control module and an image acquisition module;
the motion control module controls the loading platform to move to a target position by using a pulse signal so as to enable the camera to take a picture;
the image acquisition module controls the microscope to photograph the flexible IC substrate placed on the loading platform.
The invention also provides a detection method of the detection system for the bubble and crease defects of the linear circuit of the flexible IC substrate, which comprises the following steps:
s1, the image acquisition subsystem controls the microscope to carry out positioning shooting on the flexible substrate placed on the loading platform, and the target position is the position of the area where the film covering linear line is located;
s2, ensuring that an input image of the defect detection method is a linear circuit part of the laminated flexible substrate through an input image protection mechanism, and otherwise, popping a window to warn and quit the detection process;
the input image protection mechanism aims to prevent the input of a linear line position pattern of a non-film-coated flexible substrate from causing a detection process to run and causing unnecessary influence on a system and even a hardware machine;
s3, extracting the suspected defect area of the film-coated flexible substrate, namely setting the area representing the suspected defect in the binary image as 1 and setting the rest areas as 0;
s4, removing salt and pepper noise, eliminating convex interference points and filling small holes in the area of the binary image through morphological processing;
s5, according to the requirement of the defect detection module, firstly judging the certainty of the defects in the binary image, and then calculating a multi-feature numerical value of the flexible substrate pattern with the defects;
and S6, judging the category to which the defect in the flexible substrate pattern belongs based on the multi-feature combined analysis according to the requirement of the data analysis module, and labeling the defect area in the original image.
Preferably, the step S1 includes:
s1.1, performing precision detection on defects of linear line parts of a film-coated flexible substrate, so that target acquisition patterns are concentrated on the linear line parts, and non-linear line parts are not subjected to image acquisition operation treatment;
s1.2, template data information of flexible substrates produced in batch on site is filed, and a template database of the linear line part of the film-coated flexible substrate can be established by dividing the area of each type of flexible substrate where the linear line is located and storing all positioning coordinate information into a system database;
and S1.3, converting the linear line coordinate position of the corresponding target substrate in the database into a pulse signal, and controlling the loading platform to move to the target position for image acquisition.
Preferably, the step S2 includes:
s2.1, an input image protection mechanism ensures that only the input image is the object of the system, the defect detection can be carried out, and otherwise, the system warns to pop up the window and quits the detection program;
s2.2, counting a smooth histogram of the input image, if the two peak values in the histogram are both at the low gray value and are not far away from each other, determining that the input image is legal, continuing the detection process, and if not, stopping the detection and performing pop-up warning;
s2.3, retrieving the central point position of each straight line from top to bottom at the half-width position of the image, and drawing straight lines at intervals of 10 degrees from 0 degrees by taking each central point as the center for linear detection;
and S2.4, linear detection refers to the length ratio of the target area falling on a straight line, if the ratio obtained by the linear detection is larger than a set threshold value, the input image is considered to be legal, the detection process is continued, and otherwise, the detection is stopped and a popup alarm is given.
Preferably, the step S3 includes the following steps:
s3.1, extracting and segmenting the bubble or crease defect region based on adaptive threshold segmentation of three times of the size of a higher peak value in a smooth histogram of the input image;
s3.2, smoothing a histogram based on an interpolation method, setting a step length, and calculating a smoothed value temp of a certain point x on the histogram f according to the following formula:
s3.3, setting a gray scale image of the coated flexible substrate as I1, setting a binary image of a defect suspected area as I2, and setting a threshold value T as a value three times the gray scale value of a higher peak in a gray smooth histogram, wherein a conversion formula of the binary image and the gray scale image is as follows:
I2＝(I1)≥T。
preferably, the step S4 includes:
s4.1, aiming at the binary image, adopting a median filter with the size of 3 x 3 templates to ensure that interference points similar to salt and pepper noise in the binary image are eliminated as far as possible while ensuring that the pattern details are input into a substrate;
s4.2, performing closing operation, firstly expanding and then corroding, closing narrow gaps and slender gullies, eliminating small cavities and filling up fractures in the contour lines;
s4.3 the information in the binary image to be transmitted into the subsequent detection method consists of two parts: the white area represents the defect suspected area, and the rest areas represent irrelevant information.
As a preferred technical solution, in the step S4.2, the adopted cross-shaped structural element can better fill up the fine holes in the target area of the filtered binary image.
Preferably, the step S5 includes:
s5.1, extracting contours from the binary image, calculating the area contained in each contour, and if the area is smaller than a set threshold, determining the contour as interference instead of defect processing without performing subsequent feature calculation processing;
s5.2, calculating the numerical values of the three types of characteristics of the pictures with the determined defects, wherein the numerical values comprise the number of defect areas, the rectangular degree and the circular degree;
s5.3, the rectangular degree represents the area proportion of the two-dimensional object to the minimum circumscribed rectangle, and the area proportion is defined as R ═ S0/SMERIn which S is0Is the area of the object, SMERIs the area of its smallest circumscribed rectangle;
s5.4, the circularity is the approximation degree of a standard circle starting from the irregularity degree of a two-dimensional space, and the calculation formula is as follows, wherein A represents the area of an imaging region of the object in a binary image of the object, C represents the perimeter of the imaging region of the object in the image, and R represents the circularity:
preferably, the step S6 includes:
s6.1, aiming at a single feature, by observing the numerical rule of different defect types under the feature, setting a threshold classification rule;
s6.2, calculating and inputting classification judgment results of the laminated flexible substrate pattern under different characteristics, taking the category with large quantity as a final returned classification result, and recording the classification result into a system database;
s6.3, calculating and analyzing the defect type of the linear line part of the film-coated flexible substrate, and labeling the defect part on an input original image for an engineer or a field operator to observe.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the system and the method for detecting the bubble and crease defects of the linear circuit of the flexible IC substrate perform simultaneous detection of the bubble and crease defects on the flexible IC substrate on the field working platform, emphasize detection by using rules, can better avoid false alarm of the defects of imaging detection of the linear circuit part of the coated flexible substrate under different illumination intensities, and can adapt to the field requirements of factories in terms of accuracy and working efficiency.
Drawings
Fig. 1 is a schematic flow chart illustrating a method for detecting bubble and crease defects in a linear circuit of a flexible IC substrate according to an embodiment of the present invention.
Fig. 2 is a block diagram of a system for detecting bubble and crease defects in a linear circuit of a flexible IC substrate according to an embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating an effect of identifying bubble defects at a linear circuit portion of a flexible IC substrate according to an embodiment of the present invention.
Fig. 4 is a schematic diagram illustrating an effect of identifying a crease defect at a linear circuit portion of a flexible IC substrate according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Examples
As shown in fig. 1, the method for detecting bubble and crease defects in a linear circuit of a flexible IC substrate of the present embodiment includes the following steps:
s1, the image acquisition subsystem controls the microscope to carry out positioning shooting on the flexible substrate placed on the loading platform, and the target position is the position of the area where the film covering linear line is located;
s2, ensuring that an input image of the defect detection algorithm is a linear circuit part of the laminated flexible substrate through an input image protection mechanism, and otherwise, popping a window to warn and exiting the algorithm flow;
s3, extracting the suspected defect area of the film-coated flexible substrate, namely setting the area representing the suspected defect in the binary image as 1 and setting the rest areas as 0;
s4, removing salt and pepper noise, eliminating convex interference points and filling small holes in the area of the binary image through morphological processing;
s5, according to the requirement of the defect detection module, firstly judging the certainty of the defects in the binary image, and then calculating a multi-feature numerical value of the flexible substrate pattern with the defects;
and S6, judging the category to which the defect in the flexible substrate pattern belongs based on the multi-feature combined analysis according to the requirement of the data analysis module, and labeling the defect area in the original image.
The "input image protection mechanism" in step S2 aims to prevent the algorithm from running short due to the input of the linear circuit pattern of the non-film-covered flexible substrate, which may cause unnecessary impact on the system and thus the hardware machine.
The image acquisition process described in step S1 can be understood as:
1) the system and the method carry out precision detection on defects of linear line parts of the film-coated flexible substrate, so that target collection patterns are concentrated on the linear line parts, and non-linear line parts are not subjected to pattern collection operation treatment;
2) template data information of flexible substrates produced in batch on site is filed, and a template database of the linear line part of the flexible substrate to be coated can be established by dividing the area of the linear line in each type of flexible substrate and storing all positioning coordinate information into a system database;
3) converting the linear line coordinate position of the corresponding target substrate in the database into a pulse signal, and controlling the loading platform to move to the target position for image acquisition.
The "input image protection mechanism" described in step S2 may be understood as:
1) an input image protection mechanism for ensuring that algorithm detection can be carried out only if the input image is the object (straight line) by the system algorithm, otherwise, the algorithm program is warned by popping the window and quitted;
2) counting a smooth histogram of the input image, if the two peak values in the histogram are both at the low gray scale value and are not far away from each other, determining that the input image is legal, continuing the algorithm flow, and otherwise, stopping detection and performing pop-up warning;
3) searching the position of the central point of each straight line from top to bottom at the position of half width of the image, and drawing straight lines at intervals of 10 degrees from 0 degrees by taking each central point as the center for linear detection;
4) and linear detection refers to the length ratio of a target area falling on a straight line, if the ratio obtained by linear detection is greater than the set threshold value of the system, the input image is considered to be legal, the algorithm flow is continued, and otherwise, the detection is stopped and a pop-up warning is given.
The step S3 of extracting the suspected defect area of the flexible substrate may be:
1) the extraction and segmentation of bubble or crease defect regions can be realized based on the adaptive threshold segmentation of three times the size of a higher peak value in a smooth histogram of an input image;
2) the histogram smoothing based on interpolation is adopted, step is set, and the smoothed value temp of a certain point x on the histogram f is calculated according to the following formula:
3) if the gray scale image of the coated flexible substrate is I1, the binary image of the defect suspected region is I2, and the threshold T is a value three times the gray scale value of the higher peak in the gray scale smooth histogram, then the conversion formula of the binary image and the gray scale image is as follows:
I2＝(I1)≥T
the morphological processing on the binary map in step S4 includes:
1) a median filter with the size of a 3-by-3 template is adopted for the binary image, so that interference points similar to salt and pepper noise in the binary image are eliminated as far as possible while the pattern details are input to the substrate;
2) closing operation, firstly expanding and then corroding, closing narrow gaps and slender gullies, eliminating small cavities, and filling fractures in the contour lines, wherein the cross-shaped structural elements adopted by the system can well fill fine cavities in the target area of the filtered binary image;
3) to this end, the information within the binary image that will be passed into the subsequent algorithm consists of two parts: the white area represents the defect suspected area, and the rest areas represent irrelevant information.
Step S5 is to calculate a multi-feature value for the flexible substrate pattern determined to contain defects, specifically:
1) extracting outlines from the binary image, calculating the area contained in each outline, and if the area is smaller than a certain set threshold value, determining the area as interference instead of defect processing without performing subsequent feature calculation processing;
2) calculating the numerical values of three types of characteristics of the pictures with the determined defects, wherein the numerical values comprise the number of defect areas, the rectangular degree and the circular degree;
3) the rectangular degree represents the proportion of the area of the two-dimensional object in the minimum circumscribed rectangle, and is defined as R ═ S0/SMERIn which S is0Is the area of the object, SMERIs the area of its smallest circumscribed rectangle;
4) the circularity is an approximation degree of a standard circle starting from an irregularity degree in a two-dimensional space, and is calculated by the following formula, wherein a represents an imaging region area of an object in a binary image thereof, C represents an imaging region perimeter of the object in an image, and R represents a circularity:
step S6 is to determine which category the defect in the flexible substrate pattern belongs to based on the multi-feature joint analysis, specifically:
1) setting a threshold classification rule by observing the numerical rule of different defect types under the characteristic aiming at the single characteristic, such as the rule that the numerical value of the bubble defect is higher under the characteristic of circularity and the numerical value of the crease defect is lower under the characteristic of circularity;
2) calculating classification judgment results of the patterns of the film-coated flexible substrate under different characteristics, taking the category with large number as a final returned classification result, and recording the classification result into a system database;
3) except for calculating and analyzing the defect type of the linear line part of the laminated flexible substrate, the system can label the defect part on an input original image for an engineer or a field operator to observe.
As shown in fig. 2, the system for detecting bubble and crease defects in a linear circuit of a flexible IC substrate of the present embodiment includes an image capturing subsystem (including a motion control module and an image capturing module), a defect detecting module and a data analyzing module, wherein:
the image acquisition subsystem for the flexible substrate that control microscope placed on to the objective platform is fixed a position and is shot, and the target location is tectorial membrane straight line circuit place regional position, includes:
1) the motion control module controls the loading platform to move to a target position by using a pulse signal so as to enable the camera to take a picture;
2) and the image acquisition module is used for controlling the microscope to photograph the flexible IC substrate placed on the loading platform.
The defect detection module is used for extracting a binary image of an input pattern of the flexible substrate, judging the certainty of the defects in the binary image, extracting a defect area of the flexible substrate pattern with the defects, and calculating a multi-feature numerical value;
and the data analysis module is used for judging the defect type of the linear circuit part of the substrate and marking the defect area.
As shown in fig. 3, the linear line bubble and crease defect detecting system of the flexible IC substrate of the present embodiment successfully identifies and circles the detected bubble defect existence area.
As shown in fig. 4, the flexible IC substrate linear track bubble and crease defect detection system of the present embodiment successfully identifies and draws the detected crease defect existence region.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by using a program to instruct the relevant hardware, and the corresponding program may be stored in a computer-readable storage medium, such as a ROM, a magnetic disk, an optical disk, or the like.
In summary, the system and the method for detecting bubble and crease defects of the linear circuit of the flexible IC substrate perform simultaneous detection of bubble and crease defects on the flexible IC substrate on the field working platform, and emphasize the detection by using the rule, so that the defect false report of the imaging detection of the linear circuit part of the coated flexible substrate under different illumination intensities can be better avoided, and the system and the method can meet the field requirements of a factory in terms of accuracy and working efficiency.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (8)
1. A detection method of a flexible IC substrate linear line bubble and crease defect detection system is characterized in that the system comprises an image acquisition subsystem, a defect detection module and a data analysis module;
the image acquisition subsystem is used for controlling the microscope to carry out positioning shooting on the flexible substrate placed on the loading platform, and the target position is the position of the area where the film covering linear line is located;
the defect detection module is used for extracting a binary image of an input pattern of the flexible substrate, judging the certainty of the defect in the binary image, extracting a defect area of the flexible substrate pattern with the defect, and calculating a multi-feature numerical value;
the data analysis module is used for judging the defect type of the linear circuit part of the substrate and marking a defect area;
the method comprises the following steps:
s1, the image acquisition subsystem controls the microscope to carry out positioning shooting on the flexible substrate placed on the loading platform, and the target position is the position of the area where the film covering linear line is located;
s2, ensuring that an input image of the defect detection method is a linear circuit part of the laminated flexible substrate through an input image protection mechanism, and otherwise, popping a window to warn and quit the detection process;
the input image protection mechanism aims to prevent the detection process from collapsing due to the input of a non-film-coated flexible substrate linear line part pattern, and unnecessary influences are caused on a system and even a hardware machine;
the step S2 includes:
s2.1, an input image protection mechanism ensures that only the input image is the object of the system, the defect detection can be carried out, and otherwise, the system warns to pop up the window and quits the detection program;
s2.2, counting a smooth histogram of the input image, if the two peak values in the histogram are both at the low gray value and are not far away from each other, determining that the input image is legal, continuing the detection process, and if not, stopping the detection and performing pop-up warning;
s2.3, retrieving the central point position of each straight line from top to bottom at the half-width position of the image, and drawing straight lines at intervals of 10 degrees from 0 degrees by taking each central point as the center for linear detection;
s2.4, linear detection refers to the length ratio of the target area falling on a straight line, if the ratio value obtained by the linear detection is larger than a set threshold value, the input image is considered to be legal, the detection process is continued, and otherwise, the detection is stopped and a popup alarm is given;
s3, extracting the suspected defect area of the film-coated flexible substrate, namely setting the area representing the suspected defect in the binary image as 1 and setting the rest areas as 0;
s4, removing salt and pepper noise, eliminating convex interference points and filling small holes in the area of the binary image through morphological processing;
s5, according to the requirement of the defect detection module, firstly judging the certainty of the defects in the binary image, and then calculating a multi-feature numerical value of the flexible substrate pattern with the defects;
and S6, judging the category to which the defect in the flexible substrate pattern belongs based on the multi-feature combined analysis according to the requirement of the data analysis module, and labeling the defect area in the original image.
2. The method as claimed in claim 1, wherein the step S1 includes:
s1.1, performing precision detection on defects of linear line parts of a film-coated flexible substrate, so that target acquisition patterns are concentrated on the linear line parts, and non-linear line parts are not subjected to image acquisition operation treatment;
s1.2, template data information of flexible substrates produced in batch on site is filed, and a template database of the linear line part of the film-coated flexible substrate can be established by dividing the area of each type of flexible substrate where the linear line is located and storing all positioning coordinate information into a system database;
and S1.3, converting the linear line coordinate position of the corresponding target substrate in the database into a pulse signal, and controlling the loading platform to move to the target position for image acquisition.
3. The method as claimed in claim 1, wherein the step S3 comprises the steps of:
s3.1, extracting and segmenting the bubble or crease defect region based on adaptive threshold segmentation of three times of the size of a higher peak value in a smooth histogram of the input image;
s3.2, smoothing a histogram based on an interpolation method, setting a step length, and calculating a smoothed value temp of a certain point x on the histogram f according to the following formula:
s3.3, setting a gray scale image of the coated flexible substrate as I1, setting a binary image of a defect suspected area as I2, and setting a threshold value T as a value three times the gray scale value of a higher peak in a gray smooth histogram, wherein a conversion formula of the binary image and the gray scale image is as follows:
I2＝(I1)≥T。
4. the method as claimed in claim 1, wherein the step S4 includes:
s4.1, aiming at the binary image, adopting a median filter with the size of 3 x 3 templates to ensure that interference points similar to salt and pepper noise in the binary image are eliminated as far as possible while ensuring that the pattern details are input into a substrate;
s4.2, performing closing operation, namely expanding firstly and then corroding, closing narrow gaps and slender gullies, eliminating small cavities and filling up fractures in the contour lines;
s4.3 the information in the binary image to be transmitted into the subsequent detection method consists of two parts: the white area represents the defect suspected area, and the rest areas represent irrelevant information.
5. The method as claimed in claim 4, wherein the step S4.2 is performed by using a cross-shaped structure element to fill up the fine holes in the target area of the filtered binary image.
6. The method as claimed in claim 4, wherein the step S5 includes:
s5.1, extracting contours from the binary image, calculating the area contained in each contour, and if the area is smaller than a set threshold, determining the contour as interference instead of defect processing without performing subsequent feature calculation processing;
s5.2, calculating the numerical values of the three types of characteristics of the pictures with the determined defects, wherein the numerical values comprise the number of defect areas, the rectangular degree and the circular degree;
s5.3, the rectangular degree represents the area proportion of the two-dimensional object to the minimum circumscribed rectangle, and the area proportion is defined as R ═ S0/SMERIn which S is0Is the area of the object, SMERIs the area of its smallest circumscribed rectangle;
s5.4, the circularity is the approximation degree of a standard circle starting from the irregularity degree of a two-dimensional space, and the calculation formula is as follows, wherein A represents the area of an imaging region of the object in a binary image of the object, C represents the perimeter of the imaging region of the object in the image, and R represents the circularity:
7. the method as claimed in claim 4, wherein the step S6 includes:
s6.1, aiming at a single feature, by observing the numerical rule of different defect types under the feature, setting a threshold classification rule;
s6.2, calculating and inputting classification judgment results of the laminated flexible substrate pattern under different characteristics, taking the category with large quantity as a final returned classification result, and recording the classification result into a system database;
s6.3, calculating and analyzing the defect type of the linear line part of the film-coated flexible substrate, and labeling the defect part on an input original image for an engineer or a field operator to observe.
8. The detection method of the flexible IC substrate linear line bubble and crease defect detection system according to claim 1, wherein the image acquisition subsystem comprises a motion control module and an image acquisition module;
the motion control module controls the loading platform to move to a target position by using a pulse signal so as to enable the camera to take a picture;
the image acquisition module controls the microscope to photograph the flexible IC substrate placed on the loading platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810749681.XA CN108802051B (en) | 2018-07-10 | 2018-07-10 | System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810749681.XA CN108802051B (en) | 2018-07-10 | 2018-07-10 | System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108802051A CN108802051A (en) | 2018-11-13 |
| CN108802051B true CN108802051B (en) | 2020-05-19 |
Family
ID=64074667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810749681.XA Active CN108802051B (en) | 2018-07-10 | 2018-07-10 | System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108802051B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110286126B (en) * | 2019-06-17 | 2021-09-14 | 浙江大学 | Wafer surface defect regional detection method based on visual image |
| CN110441319B (en) * | 2019-09-09 | 2022-05-03 | 凌云光技术股份有限公司 | Method and device for detecting appearance defects |
| CN111595850B (en) * | 2020-04-27 | 2022-07-15 | 平安科技（深圳）有限公司 | Slice defect detection method, electronic device and readable storage medium |
| CN112884744A (en) * | 2021-02-22 | 2021-06-01 | 深圳中科飞测科技股份有限公司 | Detection method and device, detection equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103792234B (en) * | 2012-10-29 | 2015-11-25 | 昆山钞票纸业有限公司 | Reciprocating motion type bank-note paper fluorescent fiber on-line measuring device |
| CN107966454A (en) * | 2017-12-25 | 2018-04-27 | 陕西科技大学 | A kind of end plug defect detecting device and detection method based on FPGA |
-
2018
- 2018-07-10 CN CN201810749681.XA patent/CN108802051B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108802051A (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108802051B (en) | System and method for detecting bubble and crease defects of linear circuit of flexible IC substrate | |
| CN110826416B (en) | Bathroom ceramic surface defect detection method and device based on deep learning | |
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN108364311B (en) | Automatic positioning method for metal part and terminal equipment | |
| CN113592845A (en) | Defect detection method and device for battery coating and storage medium | |
| CN109035219B (en) | FICS golden finger defect detection system and detection method based on BP neural network | |
| CN109632808B (en) | Edge defect detection method and device, electronic equipment and storage medium | |
| JP6099479B2 (en) | Crack detection method | |
| CN110084802B (en) | High-precision PCB chip pin center positioning method | |
| JP5852919B2 (en) | Crack detection method | |
| CN110443791B (en) | Workpiece detection method and device based on deep learning network | |
| CN112037203A (en) | Side surface defect detection method and system based on complex workpiece outer contour registration | |
| CN111982921A (en) | Hole defect detection method and device, conveying platform and storage medium | |
| CN113160161B (en) | Method and device for detecting defects at edge of target | |
| CN114387233A (en) | Sand mold defect detection method and system based on machine vision | |
| CN105718931B (en) | System and method for determining clutter in acquired images | |
| CN115791822A (en) | Visual detection algorithm and detection system for wafer surface defects | |
| CN110660072B (en) | Method and device for identifying straight line edge, storage medium and electronic equipment | |
| WO2021000948A1 (en) | Counterweight weight detection method and system, and acquisition method and system, and crane | |
| CN115100191A (en) | Metal casting defect identification method based on industrial detection | |
| CN110582159A (en) | FPC bonding pad surface defect processing system and method | |
| CN115409785A (en) | Method for detecting defects of small pluggable transceiver module base | |
| JP2006292593A (en) | Flaw detector, flaw detecting method, computer program and recording medium | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN113781413B (en) | Electrolytic capacitor positioning method based on Hough gradient method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |