CN105675626B - A kind of character defect inspection method of tire-mold - Google Patents
A kind of character defect inspection method of tire-mold Download PDFInfo
- Publication number
- CN105675626B CN105675626B CN201610107512.7A CN201610107512A CN105675626B CN 105675626 B CN105675626 B CN 105675626B CN 201610107512 A CN201610107512 A CN 201610107512A CN 105675626 B CN105675626 B CN 105675626B
- Authority
- CN
- China
- Prior art keywords
- image
- character
- roi image
- cad
- roi
- 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
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
-
- 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 kind of character defect inspection methods of tire-mold, including：S1, it treats detection tire fetal membrane and is scanned and acquires and obtain one group of image, and obtain tire outer arc shape profile；After S2, the center of circle for being fitted tire outer arc shape profile and radius, positioning tire fetal membrane image-region is as ROI image to be measured；S3, ROI image is classified；S4, the classification according to ROI image, select different methods to be handled, and obtain the CAD image block to match with each ROI image；S5, character recognition is carried out, and then defect dipoles is carried out according to character identification result；S6, in response to judge there are character defects the case where, return to step S4 and S5 to again carry out defect dipoles after, the judging result for selecting character defect less is as final result.Present invention detection stability is high, testing cost is low, accuracy in detection is high, rate of false alarm is low and applied widely, can be widely applied in tire fetal membrane detection field.
Description
Technical field
The present invention relates to image processing fields, more particularly to a kind of character defect inspection method of tire-mold.
Background technology
Explanation of nouns：
ROI：Region Of Interest, area-of-interest；
NCC：Normalized Cross Correlation normalized crosscorrelations.
In tire-mold production, quality testing is particularly important, wherein the defects detection of character is the important of quality testing
Work.Currently, human eye is relied primarily on for the defects detection of tire-mold character in industry, however, the noisy environment of plant, greatly
The detection work of amount and the high request to quality testing, these all to be difficult to meet need by the detection mode of human eye merely
It asks.Machine vision is exactly to be completed to observe and be judged, the product quality being usually used in high volume production process for human eye with machine
Detection is examined either applied to implacable occasion of hazardous environment or human eye vision of unsuitable people etc. compared to artificial vision
It looks into, accuracy of detection and speed can be greatly improved, to improve production efficiency, can also avoid caused by human eye vision detection
Deviation and error.Machine vision is widely applied in industrial every field.Machine vision is in industrial products
Applied on a large scale in character defects detection, character defect includes the stroke defect of character, character bite and wrongly typed.Word
Defect detecting system is accorded with, exactly requires to detect undesirable character, seeks to be tested with stroke defect, is bitten or wrong
The character of print.Traditional character defect inspection method based on machine vision mainly does template with standard character image, by carrying
It takes some features of character, such as shape feature to establish template, testing image is matched with standard form, if matching result is low
In threshold value, then it is assumed that be defective.This method, it is easy to accomplish, detection result is preferable.However, coming for tire-mold
It says, since output is small, from the angle of production efficiency, it is impossible to shoot standard module image as template.Application No. is
201510437595.1 the Chinese patent Shen of the entitled tire film surface character defect inspection method based on machine vision
Please, it is proposed that it is a kind of by carrying out polar coordinate transform to testing image and CAD design figure figure before template matches, with to be detected flat
The method that straight type image is detected as template, flat type CAD image as target, specifically in the acquisition of flat type CAD diagram and
It is by, into row threshold division, and then passing through to each ROI image to be measured during the image block that ROI image to be measured matches
After morphology operations are classified ROI image to be measured, two-value is converted into after ROI image to be measured being pre-processed according to classification
Image.Then the corresponding flat type image of CAD design figure for obtaining tire-mold to be detected, according to the flat type image with it is to be measured
ROI image height ratio zooms in and out ROI image to be measured, and then intercepts the image block wide with ROI image block successively, calculates phase
Relationship number after the maximum image block of related coefficient is as the image block to match with ROI image to be measured, carries out character recognition, from
And defect dipoles are carried out according to character identification result.This method testing cost is low and the scope of application is wider, can rapidly into
Row detection.But this method mainly carries out matching positioning using the information of the big character of picture top half, when on image
When half part does not have character or only small characters, matching the result of positioning can malfunction, and can not ensure all ROI images to be measured all
Matched CAD image block can be accurately obtained, larger detection error may be brought.And in Character segmentation, for some
It is densely distributed, the smaller character of size, when segmentation individual characters may will disconnect or with other Characters Stucks, cause to report by mistake,
Bring detection error.
Invention content
In order to solve the above technical problems, the object of the present invention is to provide a kind of character defects detection sides of tire-mold
Method.
The technical solution adopted by the present invention to solve the technical problems is：
A kind of character defect inspection method of tire-mold, including step：
S1, detection tire fetal membrane is treated successively be scanned and acquire and obtain one group of image, and it is every to what is acquired respectively
It opens after image is handled and obtains tire outer arc shape profile；
It, will be outside tire to be measured by polar coordinate transform after S2, the center of circle for being fitted tire outer arc shape profile and radius
The arc-shaped image in side is converted to flat type testing image, and positions tire into after row threshold division to flat type testing image
Film image region is as ROI image to be measured；
S3, respectively to each ROI image into row threshold division, and then by morphology operations by the ROI after Threshold segmentation
Image is classified, while the corresponding CAD flat types image of the CAD design figure for obtaining tire fetal membrane to be detected；
S4, the classification according to ROI image, select different methods to handle CAD flat types image and ROI image,
And interception obtains and treated CAD image block that each ROI image matches on flat type image after treatment；
S5, character recognition is carried out to each ROI image and matched CAD image block, and then according to character recognition
As a result defect dipoles are carried out；
S6, in response to judge there are character defects the case where, return to step S4 and S5 to again carry out defect sentence
It has no progeny, the judging result for selecting character defect less is as final result.
Further, respectively to each ROI image into row threshold division described in the step S3, and then pass through form student movement
It the step of ROI image after Threshold segmentation is classified in calculation, specifically includes：
S31, the initial area and elemental height for calculating separately each ROI image；
S32, to ROI image into row threshold division, divide foreground area；
S33, it obtains and presets Morphological Structuring Elements, foreground area is corroded and carries out connectivity label, and according to pre-
If after screening conditions screen connected domain, ROI image is divided into A classes and B classes according to the connected domain quantity filtered out.
Further, described in the step S33 according to presetting after screening conditions screen connected domain, according to filtering out
Connected domain quantity the step of ROI image is divided into A classes and B classes, be specially：
Connected domain is screened, the connection that area is more than 1/2 elemental height more than 1/2 initial area and height is filtered out
ROI image is divided into A classes, if the connected domain quantity filtered out is more than by domain quantity if the connected domain quantity filtered out is equal to 0
0, then ROI image is divided into B classes.
Further, the step S4, including：
S41, the classification according to ROI image, according to the iteration of number of processes, the case where for ROI image being A classes, successively
Selection processing method one and processing method two handle CAD flat types image and ROI image, are B classes for ROI image
Situation selects processing method two and processing method three to handle CAD flat types image and ROI image successively；
S42, ROI image is zoomed in and out according to the height ratio of treated CAD flat types image and ROI image；
It is intercepted successively on S43, CAD flat type images after treatment with the ROI image after scaling with wide image block, meter
Calculate each image block with scaling after ROI image related coefficient, and then using the maximum image block of related coefficient as with the ROI
The CAD image block that image matches；
The processing method one is specially：To ROI image into carrying out Morphological scale-space after row threshold division, and according to form
Learn the ratio of treated region area and initial area, positioning obtains the character zone for include character, and then by ROI image turn
It is changed to binary image, while by CAD flat types image into being converted to bianry image after row threshold division；
The processing method two is specially：Standard deviation filtering is carried out to ROI image and CAD flat type images, and intercepts mark
The lower half portion of the quasi- filtered ROI image of difference；
The processing method three is specially：The edge image of ROI image is obtained using canny operators and is converted to binary map
Picture, while by CAD flat types image into being converted to bianry image after row threshold division.
Further, the step S1 is specially：
Detection tire fetal membrane is treated successively is scanned and acquires one group of image of acquisition, and every figure to being acquired respectively
After carrying out image denoising and Threshold segmentation processing, tire fetal membrane profile is obtained, and then profile is disconnected according to contour curvature, to
According to the direction of every section of profile, length and curvature, tire outer arc shape profile is obtained.
Further, the step S5, including：
S51, to CAD image block into morphology operations are carried out after row threshold division, carried out according to preset connected domain threshold value
Connected domain is screened, and CAD image block is divided into small characters region and big character zone；
S52, the classification according to ROI image carry out morphology operations, then according to preset connected domain threshold to ROI image
Value carries out connected domain screening, and ROI image is also divided into small characters region and big character zone；
S53, the classification according to ROI image, to the big character zone of ROI image and CAD image block carry out feature extraction and
After characteristic matching, defect dipoles are carried out according to matching result；
S54, for the small characters region of ROI image and CAD image block, after carrying out character recognition, word that identification is obtained
Symbol array is divided into multiple character strings, and then after the character string that ROI image and the identification of CAD image block obtain is matched, according to
Matching result carries out defect dipoles.
Further, the step S52 is specially：
The case where for ROI image being A classes, after carrying out Local threshold segmentation and region growing to ROI image, carry out form
Student movement is calculated, and then carries out connected domain screening according to preset connected domain threshold value, and ROI image is also divided into small characters region and big
Character zone；
For ROI image be B classes the case where, mean filter, Region growing segmentation and two-value are carried out successively to ROI image
Change after result negates and carry out morphology operations, connected domain screening is then carried out according to preset connected domain threshold value, by ROI image
It is divided into small characters region and big character zone.
Further, the step S53 is specially：
For ROI image be A classes the case where, using the big character zone of ROI image as template, in the big of CAD image block
NCC matchings are carried out on character zone, if matching degree is more than preset matching threshold value, to the big word of ROI image and CAD image block
Symbol region carries out morphology and subtracts each other, after difference operation and morphological erosion successively, judges whether the area in the region obtained is less than
Predetermined threshold value, if so, judging the character, there are printing defects, otherwise, it is determined that the character printing is correct；
For ROI image be B classes the case where, using canny operators obtain ROI image big character zone edge after make
It for template, scans for matching on the binary image of the big character zone of CAD image block, if matching degree is less than preset matching
Threshold value then judges the character there are printing defects, and the centre coordinate of misregistration character region.
Further, the step S54, including：
S541, two words are obtained respectively after progress character recognition for the small characters region of ROI image and CAD image block
Array is accorded with, and then each character array is divided into multiple character strings；
S542, each character string to ROI image, carry out matching search in the character array of CAD image block, if matching
It is unsuccessful, S543 is thened follow the steps, otherwise judges that character string printing is correct；
Character zone division is re-started after S543, adjusting parameter, and then to the corresponding small characters region of the character string
After ROI image extracts character again, identification obtains a new character string；
S544, matching is searched for the new character string and is returned if matching is unsuccessful in the character array of CAD image block
The identification of step S543 repeat character strings, matching operation, and judge whether the successful match in defined searching times, if so,
Judge that character string printing is correct, and is entered into correct characters array, conversely, judging the character string, there are printing defects, and
The centre coordinate of misregistration character string region；
S545, each character string to CAD image block, carry out matching search in correct characters array, if matching not at
Work(thens follow the steps S546, otherwise judges that character string printing is correct；
S546, it after extracting character on the ROI image of the character string corresponding region, identifies and obtains a number of checking character
Group, and then matching search is carried out to the character string in array of checking character, if matching is unsuccessful, judge that the character string exists
Defect is bitten, otherwise judges that character string printing is correct.
Further, the corresponding flat type image of CAD design figure described in the step S3 obtains in the following manner：
CAD design figure is obtained and by it into binary map is converted to after row threshold division, by the marking image in CAD design figure
As foreground image, and then it is fitted the minimum circumscribed circle of the foreground image, and after obtaining the center of circle and the radius of the minimum circumscribed circle,
Polar coordinate transform is carried out according to the center of circle of acquisition and radius, obtains the flat type image of CAD design figure.
The beneficial effects of the invention are as follows：A kind of character defect inspection method of tire-mold of the present invention, including：S1, according to
Secondary detection tire fetal membrane for the treatment of is scanned and acquires one group of image of acquisition, and handles respectively the every image acquired
Tire outer arc shape profile is obtained afterwards；After S2, the center of circle for being fitted tire outer arc shape profile and radius, become by polar coordinates
The tire outer arc shape image for changing commanders to be measured is converted to flat type testing image, and carries out threshold value point to flat type testing image
After cutting, positioning tire fetal membrane image-region is as ROI image to be measured；S3, respectively to each ROI image into row threshold division,
And then the ROI image after Threshold segmentation is classified by morphology operations, while the CAD for obtaining tire fetal membrane to be detected is set
Meter schemes corresponding CAD flat types image；S4, the classification according to ROI image, select different methods to CAD flat types image and
ROI image is handled, and interception obtains that each ROI image matches with treated on flat type image after treatment
CAD image block；S5, character recognition is carried out to each ROI image and matched CAD image block, and then is known according to character
Other result carries out defect dipoles；S6, in response to judging that there are character defects the case where, return to step S4 and S5 to again
After carrying out defect dipoles, the judging result for selecting character defect less is as final result.This method can detect to wait for automatically
The character defect of tire fetal membrane is detected, detection stability is high, testing cost is low, accuracy in detection is high, rate of false alarm is low and applicable model
It encloses extensively, fast and effeciently tire fetal membrane character defect can be detected.
Description of the drawings
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 1 is a kind of flow chart of the character defect inspection method of tire-mold of the present invention.
Specific implementation mode
Referring to Fig.1, the present invention provides a kind of character defect inspection methods of tire-mold, including step：
S1, detection tire fetal membrane is treated successively be scanned and acquire and obtain one group of image, and it is every to what is acquired respectively
It opens after image is handled and obtains tire outer arc shape profile；
It, will be outside tire to be measured by polar coordinate transform after S2, the center of circle for being fitted tire outer arc shape profile and radius
The arc-shaped image in side is converted to flat type testing image, and positions tire into after row threshold division to flat type testing image
Film image region is as ROI image to be measured；
S3, respectively to each ROI image into row threshold division, and then by morphology operations by the ROI after Threshold segmentation
Image is classified, while the corresponding CAD flat types image of the CAD design figure for obtaining tire fetal membrane to be detected；
S4, the classification according to ROI image, select different methods to handle CAD flat types image and ROI image,
And interception obtains and treated CAD image block that each ROI image matches on flat type image after treatment；
S5, character recognition is carried out to each ROI image and matched CAD image block, and then according to character recognition
As a result defect dipoles are carried out；
S6, in response to judge there are character defects the case where, return to step S4 and S5 to again carry out defect sentence
It has no progeny, the judging result for selecting character defect less is as final result.
It is further used as preferred embodiment, threshold value point is carried out to each ROI image respectively described in the step S3
It cuts, and then the step of ROI image after Threshold segmentation is classified by morphology operations, specifically includes：
S31, the initial area and elemental height for calculating separately each ROI image；
S32, to ROI image into row threshold division, divide foreground area；
S33, it obtains and presets Morphological Structuring Elements, foreground area is corroded and carries out connectivity label, and according to pre-
If after screening conditions screen connected domain, ROI image is divided into A classes and B classes according to the connected domain quantity filtered out.
Be further used as preferred embodiment, described in the step S33 according to preset screening conditions to connected domain into
After row screening, the step of ROI image is divided by A classes and B classes according to the connected domain quantity filtered out, it is specially：
Connected domain is screened, the connection that area is more than 1/2 elemental height more than 1/2 initial area and height is filtered out
ROI image is divided into A classes, if the connected domain quantity filtered out is more than by domain quantity if the connected domain quantity filtered out is equal to 0
0, then ROI image is divided into B classes.
It is further used as preferred embodiment, the step S4, including：
S41, the classification according to ROI image, according to the iteration of number of processes, the case where for ROI image being A classes, successively
Selection processing method one and processing method two handle CAD flat types image and ROI image, are B classes for ROI image
Situation selects processing method two and processing method three to handle CAD flat types image and ROI image successively；
S42, ROI image is zoomed in and out according to the height ratio of treated CAD flat types image and ROI image；
It is intercepted successively on S43, CAD flat type images after treatment with the ROI image after scaling with wide image block, meter
Calculate each image block with scaling after ROI image related coefficient, and then using the maximum image block of related coefficient as with the ROI
The CAD image block that image matches；
The processing method one is specially：To ROI image into carrying out Morphological scale-space after row threshold division, and according to form
Learn the ratio of treated region area and initial area, positioning obtains the character zone for include character, and then by ROI image turn
It is changed to binary image, while by CAD flat types image into being converted to bianry image after row threshold division；
The processing method two is specially：Standard deviation filtering is carried out to ROI image and CAD flat type images, and intercepts mark
The lower half portion of the quasi- filtered ROI image of difference；
The processing method three is specially：The edge image of ROI image is obtained using canny operators and is converted to binary map
Picture, while by CAD flat types image into being converted to bianry image after row threshold division.
It is further used as preferred embodiment, the step S1 is specially：
Detection tire fetal membrane is treated successively is scanned and acquires one group of image of acquisition, and every figure to being acquired respectively
After carrying out image denoising and Threshold segmentation processing, tire fetal membrane profile is obtained, and then profile is disconnected according to contour curvature, to
According to the direction of every section of profile, length and curvature, tire outer arc shape profile is obtained.
It is further used as preferred embodiment, the step S5, including：
S51, to CAD image block into morphology operations are carried out after row threshold division, carried out according to preset connected domain threshold value
Connected domain is screened, and CAD image block is divided into small characters region and big character zone；
S52, the classification according to ROI image carry out morphology operations, then according to preset connected domain threshold to ROI image
Value carries out connected domain screening, and ROI image is also divided into small characters region and big character zone；
S53, the classification according to ROI image, to the big character zone of ROI image and CAD image block carry out feature extraction and
After characteristic matching, defect dipoles are carried out according to matching result；
S54, for the small characters region of ROI image and CAD image block, after carrying out character recognition, word that identification is obtained
Symbol array is divided into multiple character strings, and then after the character string that ROI image and the identification of CAD image block obtain is matched, according to
Matching result carries out defect dipoles.
It is further used as preferred embodiment, the step S52 is specially：
The case where for ROI image being A classes, after carrying out Local threshold segmentation and region growing to ROI image, carry out form
Student movement is calculated, and then carries out connected domain screening according to preset connected domain threshold value, and ROI image is also divided into small characters region and big
Character zone；
For ROI image be B classes the case where, mean filter, Region growing segmentation and two-value are carried out successively to ROI image
Change after result negates and carry out morphology operations, connected domain screening is then carried out according to preset connected domain threshold value, by ROI image
It is divided into small characters region and big character zone.
It is further used as preferred embodiment, the step S53 is specially：
For ROI image be A classes the case where, using the big character zone of ROI image as template, in the big of CAD image block
NCC matchings are carried out on character zone, if matching degree is more than preset matching threshold value, to the big word of ROI image and CAD image block
Symbol region carries out morphology and subtracts each other, after difference operation and morphological erosion successively, judges whether the area in the region obtained is less than
Predetermined threshold value, if so, judging the character, there are printing defects, otherwise, it is determined that the character printing is correct；
For ROI image be B classes the case where, using canny operators obtain ROI image big character zone edge after make
It for template, scans for matching on the binary image of the big character zone of CAD image block, if matching degree is less than preset matching
Threshold value then judges the character there are printing defects, and the centre coordinate of misregistration character region.
It is further used as preferred embodiment, the step S54, including：
S541, two words are obtained respectively after progress character recognition for the small characters region of ROI image and CAD image block
Array is accorded with, and then each character array is divided into multiple character strings；
S542, each character string to ROI image, carry out matching search in the character array of CAD image block, if matching
It is unsuccessful, S543 is thened follow the steps, otherwise judges that character string printing is correct；
Character zone division is re-started after S543, adjusting parameter, and then to the corresponding small characters region of the character string
After ROI image extracts character again, identification obtains a new character string；
S544, matching is searched for the new character string and is returned if matching is unsuccessful in the character array of CAD image block
The identification of step S543 repeat character strings, matching operation, and judge whether the successful match in defined searching times, if so,
Judge that character string printing is correct, and is entered into correct characters array, conversely, judging the character string, there are printing defects, and
The centre coordinate of misregistration character string region；
S545, each character string to CAD image block, carry out matching search in correct characters array, if matching not at
Work(thens follow the steps S546, otherwise judges that character string printing is correct；
S546, it after extracting character on the ROI image of the character string corresponding region, identifies and obtains a number of checking character
Group, and then matching search is carried out to the character string in array of checking character, if matching is unsuccessful, judge that the character string exists
Defect is bitten, otherwise judges that character string printing is correct.
It is further used as preferred embodiment, tire outer arc shape profile is fitted described in the step S2
And the step of being split after flat type testing image is converted to, it is specially：It is fitted the center of circle of tire outer arc shape profile
After radius, tire outer arc shape image to be measured is converted to by flat type testing image by polar coordinate transform, and to flat
Straight type testing image is split.
It is further used as preferred embodiment, the corresponding flat type image of CAD design figure described in the step S3 is
It obtains in the following manner：
CAD design figure is obtained and by it into binary map is converted to after row threshold division, by the marking image in CAD design figure
As foreground image, and then it is fitted the minimum circumscribed circle of the foreground image, and after obtaining the center of circle and the radius of the minimum circumscribed circle,
Polar coordinate transform is carried out according to the center of circle of acquisition and radius, obtains the flat type image of CAD design figure.
It elaborates to the present invention below in conjunction with specific embodiment.
Referring to Fig.1, the character defect inspection method of a kind of tire-mold, including step：
S1, detection tire fetal membrane is treated successively be scanned and acquire and obtain one group of image, and it is every to what is acquired respectively
It opens after image is handled and obtains tire outer arc shape profile, be specially：Detection tire fetal membrane is treated successively to be scanned
And acquire and obtain one group of image, and after carrying out image denoising and Threshold segmentation processing to every image being acquired respectively, obtain
Tire fetal membrane profile, and then profile is disconnected according to contour curvature, to according to the direction of every section of profile, length and curvature, obtain
Obtain tire outer arc shape profile.
Profile is disconnected according to contour curvature to be as follows：Judge the point on profile whether one according to contour area
On straight line or a camber line, if the curvature of certain point is consistent with the curvature nearby put, then it represents that 2 points in same camber line
Or on same straight line, otherwise, indicates at 2 points not on same camber line or straight line, 2 points are disconnected.It can be obtained by the method
Direction, length and the curvature for obtaining every section of profile, according to the feature of arc-shaped profile, to obtain tire outer arc shape wheel
It is wide.
It, will be outside tire to be measured by polar coordinate transform after S2, the center of circle for being fitted tire outer arc shape profile and radius
The arc-shaped image in side is converted to flat type testing image, and positions tire into after row threshold division to flat type testing image
Film image region is as ROI image to be measured；
S3, respectively to each ROI image into row threshold division, and then by morphology operations by the ROI after Threshold segmentation
Image is classified, while the corresponding CAD flat types image of the CAD design figure for obtaining tire fetal membrane to be detected；
Wherein, respectively to each ROI image into row threshold division, and then will be after Threshold segmentation by morphology operations
The step of ROI image is classified specifically includes step S31~S33：
S31, the initial area S_area and elemental height S_Height for calculating separately each ROI image；
S32, to ROI image into row threshold division, divide foreground area, such as the threshold value of selection is 120, will be above 120
Be divided into foreground area；
S33, it obtains and presets Morphological Structuring Elements, foreground area is corroded and carries out connectivity label, and according to pre-
If after screening conditions screen connected domain, ROI image is divided into A classes and B classes according to the connected domain quantity filtered out, specifically
For：It obtains and presets Morphological Structuring Elements, corroded and carried out connectivity label to foreground area, and sieve to connected domain
Choosing filters out the connected domain quantity that area is more than 1/2 elemental height S_Height more than 1/2 initial area S_area and height,
If the connected domain quantity filtered out is equal to 0, ROI image is divided into A classes, it, will if the connected domain quantity filtered out is more than 0
ROI image is divided into B classes.
The corresponding flat type image of CAD design figure obtains in the following manner：It obtains CAD design figure and is carried out
Binary map is converted to after Threshold segmentation, using the marking image in CAD design figure as foreground image, and then is fitted the foreground image
Minimum circumscribed circle, and after obtaining the center of circle and the radius of the minimum circumscribed circle, polar coordinates are carried out according to the center of circle of acquisition and radius
Transformation obtains the flat type image of CAD design figure.
More specifically, it is fitted the minimum circumscribed circle of the foreground image, and obtains the center of circle and the radius of the minimum circumscribed circle
Step is specially：
It is obtained by non-linear optimal alternative manner fitting：It is fitted the circumscribed circle of the foreground image, according to the following formula by side
The squared-distance of all the points to fitting circumscribed circle on edge carries out cumulative summation, and then using the circumscribed circle of summation minimum as before this
The minimum circumscribed circle of scape image, and obtain the center of circle and the radius of the minimum circumscribed circle：
In above formula, ε2Indicate cumulative summation of all the points on edge to the squared-distance for being fitted circumscribed circle, (α, β) is indicated
The coordinate in the center of circle, ρ indicate the radius of circle, (ri,ci) indicate edge on point coordinate.
Preferably, the center of circle according to acquisition and radius carry out the step of polar coordinate transform, are specially：
In conjunction with following formula, polar coordinate transform is carried out to CAD design figure according to the center of circle of acquisition and radius：
In above formula, (α, β) indicates the coordinate of transform center,Indicate that the point on CAD design figure carries out polar coordinates change
Coordinate after changing, diFor the distance relative to transform center,For vectorial angle, (ri,ci) be polar coordinate transform before coordinate.
S4, the classification according to ROI image, select different methods to handle CAD flat types image and ROI image,
And on flat type image after treatment interception obtain with treated CAD image block that each ROI image matches, it is specific to wrap
Include step S41~S43：
S41, the classification according to ROI image, according to the iteration of number of processes, the case where for ROI image being A classes, successively
Selection processing method one and processing method two handle CAD flat types image and ROI image, are B classes for ROI image
Situation selects processing method two and processing method three to handle CAD flat types image and ROI image successively；According to processing
The iteration of number sequentially selects different methods to handle CAD flat types image and ROI image, such as ROI image is A
Class, first time selection method one are handled, if testing result malfunctions, when carrying out second and handling, then and selection method two；
S42, ROI image is zoomed in and out according to the height ratio of treated CAD flat types image and ROI image；
It is intercepted successively on S43, CAD flat type images after treatment with the ROI image after scaling with wide image block, meter
Calculate each image block with scaling after ROI image related coefficient, and then using the maximum image block of related coefficient as with the ROI
The CAD image block that image matches；Related coefficient refers to the related coefficient of image block and the matrix of the ROI image after scaling.
The processing method one is specially：To ROI image into carrying out Morphological scale-space after row threshold division, and according to form
Learn the ratio of treated region area and initial area S_area, positioning acquisition includes the character zone of character, and then by ROI
Image is converted to binary image, while by CAD flat types image into being converted to bianry image after row threshold division；
The processing method two is specially：Standard deviation filtering is carried out to ROI image and CAD flat type images, and intercepts mark
The lower half portion of the quasi- filtered ROI image of difference；
The processing method three is specially：The edge image of ROI image is obtained using canny operators and is converted to binary map
Picture, while by CAD flat types image into being converted to bianry image after row threshold division.
S5, character recognition is carried out to each ROI image and matched CAD image block, and then according to character recognition
As a result defect dipoles are carried out, S51~S54 is specifically included：
S51, to CAD image block into morphology operations are carried out after row threshold division, carried out according to preset connected domain threshold value
Connected domain is screened, and CAD image block is divided into small characters region and big character zone；
S52, the classification according to ROI image carry out morphology operations, then according to preset connected domain threshold to ROI image
Value carries out connected domain screening, ROI image is also divided into small characters region and big character zone, specially：It is for ROI image
The case where A classes, carries out Local threshold segmentation with after region growing to ROI image, morphology operations is carried out, then according to preset
Connected domain threshold value carries out connected domain screening, and ROI image is also divided into small characters region and big character zone；
For ROI image be B classes the case where, mean filter, Region growing segmentation and two-value are carried out successively to ROI image
Change after result negates and carry out morphology operations, connected domain screening is then carried out according to preset connected domain threshold value, by ROI image
It is divided into small characters region and big character zone.
S53, the classification according to ROI image, to the big character zone of ROI image and CAD image block carry out feature extraction and
After characteristic matching, defect dipoles are carried out according to matching result, specially：
For ROI image be A classes the case where, using the big character zone of ROI image as template, in the big of CAD image block
NCC matchings are carried out on character zone, if matching degree is more than preset matching threshold value, to the big word of ROI image and CAD image block
Symbol region carries out morphology and subtracts each other, after difference operation and morphological erosion successively, judges whether the area in the region obtained is less than
Predetermined threshold value, if so, judging the character, there are printing defects, otherwise, it is determined that the character printing is correct；
For ROI image be B classes the case where, using canny operators obtain ROI image big character zone sub-pix essence
It is used as template after spending edge, scans for matching on the binary image of the big character zone of CAD image block, if matching degree is small
In preset matching threshold value, then the character is judged there are printing defects, and the centre coordinate of misregistration character region.
S54, for the small characters region of ROI image and CAD image block, after carrying out character recognition, word that identification is obtained
Symbol array is divided into multiple character strings, and then after the character string that ROI image and the identification of CAD image block obtain is matched, according to
Matching result carries out defect dipoles, specifically includes step S541~S546：
S541, two words are obtained respectively after progress character recognition for the small characters region of ROI image and CAD image block
Array is accorded with, and then each character array is divided into multiple character strings；ROI image and the corresponding character array difference of CAD image block
For Array_ROI and Array_CAD, character string is respectively String_ROI [j] and String_CAD [i], wherein i=1,2,
3...N, N is the corresponding character string number of CAD image block, and j=1,2,3...M, M are the corresponding character string number of ROI image；
S542, each character string String_ROI [j] to ROI image, in the character array Array_ of CAD image block
Matching search is carried out in CAD, if matching is unsuccessful, thens follow the steps S543, otherwise judges that character string printing is correct；
Character zone division is re-started after S543, adjusting parameter, and then to the corresponding small characters region of the character string
After ROI image extracts character again, identification obtains a new character string；
S544, in the character array Array_CAD of CAD image block matching search for the new character string, if matching not at
Work(, then the identification of return to step S543 repeat character strings, matching operation, and judge whether in defined searching times matching at
Work(if so, judging that character string printing is correct, and is entered into correct characters array String_Re, conversely, judging the word
Symbol string is there are printing defects, and the centre coordinate of misregistration character string region；
S545, each character string String_CAD [i] to CAD image block, in correct characters array String_Re into
Row matching search, if matching is unsuccessful, thens follow the steps S546, otherwise judges that character string printing is correct；
S546, it after extracting character on the ROI image of the character string corresponding region, identifies and obtains an array of checking character
String_Recheck, and then matching search is carried out to the character string in the array String_Recheck that checks character, if
With unsuccessful, then judge that the character string exists and bite defect, otherwise judge character string printing correctly.
S6, in response to judge there are character defects the case where, return to step S4 and S5 to again carry out defect sentence
It has no progeny, the judging result for selecting character defect less is as final result.
This method incorporates feedback mechanism in detection process, after first time character defects detection, if detection does not conform to
Lattice after defects detection twice, using the less result of mistake as final result, carry then again into line character defects detection
The high stability of detection, reduces wrong rate of false alarm, avoids the matching error that single detection process is brought, enhance inspection
The accuracy of survey.And it is directed to different character classifications, judged using different detection methods, for being easy to happen mistake
The character field of wrong report incorporates feedback mechanism, after the division of first time character zone, to the CAD image block of interception and ROI image into
Row detection judgement, if it is determined that it is unqualified, error result is fed back to previous step, changes method, carries out second of character zone
It divides, then re-starts detection and judge, improve the accuracy of detection.
Preferably, further comprising the steps of：
S7, the ROI image of acquired image is spliced successively according to acquisition order, obtains tire fetal membrane to be detected
The stitching image of flat type；
S8, inverse pole coordinate transform is carried out to the stitching image of flat type, obtains arc-shaped stitching image；
S9, to judging defective character, highlighted on the corresponding position of arc-shaped stitching image, for example, being directed to
It in the presence of the character for biting defect, being marked with Blue circles on the corresponding position of arc-shaped stitching image, being lacked for there is printing
Sunken character is marked on the corresponding position of arc-shaped stitching image with red circle.
This method can detect the character defect of tire fetal membrane to be detected automatically, and detection stability is high, testing cost is low
And it is applied widely, fast and effeciently tire fetal membrane character defect can be detected.
It is to be illustrated to the preferable implementation of the present invention, but the invention is not limited to the implementation above
Example, those skilled in the art can also make various equivalent variations or be replaced under the premise of without prejudice to spirit of that invention
It changes, these equivalent modifications or replacement are all contained in the application claim limited range.
Claims (7)
1. a kind of character defect inspection method of tire-mold, which is characterized in that including step：
S1, detection tire fetal membrane is treated successively be scanned and acquire and obtain one group of image, and respectively to acquired every figure
As obtaining tire outer arc shape profile after being handled；
It, will be round on the outside of tire to be measured by polar coordinate transform after S2, the center of circle for being fitted tire outer arc shape profile and radius
Arc image is converted to flat type testing image, and positions tire fetal membrane figure into after row threshold division to flat type testing image
As region is as ROI image to be measured；
S3, respectively to each ROI image into row threshold division, and then by morphology operations by the ROI image after Threshold segmentation
Classify, while the corresponding CAD flat types image of the CAD design figure for obtaining tire fetal membrane to be detected；
S4, the classification according to ROI image, select different methods to handle CAD flat types image and ROI image, and
Interception obtains and treated CAD image block that each ROI image matches on treated flat type image；
S5, character recognition is carried out to each ROI image and matched CAD image block, and then according to character identification result
Carry out defect dipoles；
S6, in response to judge there are character defects the case where, return to step S4 and S5 to again carry out defect dipoles after,
The judging result for selecting character defect less is as final result；
Respectively to each ROI image into row threshold division described in the step S3, and then threshold value is divided by morphology operations
The step of ROI image after cutting is classified, specifically include S31~S33：
S31, the initial area and elemental height for calculating separately each ROI image；
S32, to ROI image into row threshold division, divide foreground area；
S33, it obtains and presets Morphological Structuring Elements, corroded and carried out connectivity label to foreground area, and according to default sieve
After selecting condition to screen connected domain, ROI image is divided by A classes and B classes according to the connected domain quantity filtered out；
After being screened to connected domain according to default screening conditions described in the step S33, according to the connected domain number filtered out
The step of ROI image is divided into A classes and B classes by amount, it is specially：
Connected domain is screened, the connected domain number that area is more than 1/2 elemental height more than 1/2 initial area and height is filtered out
ROI image is divided into A classes by amount if the connected domain quantity filtered out is equal to 0, if the connected domain quantity filtered out is more than 0,
ROI image is divided into B classes；
The step S4, including S41~S43：
S41, the classification according to ROI image the case where for ROI image being A classes, are selected successively according to the iteration of number of processes
Processing method one and processing method two handle CAD flat types image and ROI image, for the feelings that ROI image is B classes
Condition selects processing method two and processing method three to handle CAD flat types image and ROI image successively；
S42, ROI image is zoomed in and out according to the height ratio of treated CAD flat types image and ROI image；
With the ROI image after scaling with wide image block, calculating is every for interception successively on S43, CAD flat type images after treatment
A image block with scaling after ROI image related coefficient, and then using the maximum image block of related coefficient as with the ROI image
The CAD image block to match；
The processing method one is specially：To ROI image into carrying out Morphological scale-space after row threshold division, and according to morphology at
The ratio of region area and initial area after reason, positioning obtains the character zone for including character, and then ROI image is converted to
Binary image, while by CAD flat types image into being converted to bianry image after row threshold division；
The processing method two is specially：Standard deviation filtering is carried out to ROI image and CAD flat type images, and intercepts standard deviation
The lower half portion of filtered ROI image；
The processing method three is specially：The edge image of ROI image is obtained using canny operators and is converted to bianry image,
Simultaneously by CAD flat types image into being converted to bianry image after row threshold division.
2. a kind of character defect inspection method of tire-mold according to claim 1, which is characterized in that the step
S1 is specially：
Treat detection tire fetal membrane successively and be scanned and acquire and obtain one group of image, and respectively to every image being acquired into
After row image denoising and Threshold segmentation processing, tire fetal membrane profile is obtained, and then profile is disconnected according to contour curvature, to basis
Direction, length and the curvature of every section of profile obtain tire outer arc shape profile.
3. a kind of character defect inspection method of tire-mold according to claim 1, which is characterized in that the step
S5, including：
S51, to CAD image block into morphology operations are carried out after row threshold division, be connected to according to preset connected domain threshold value
Domain is screened, and CAD image block is divided into small characters region and big character zone；
S52, the classification according to ROI image, to ROI image carry out morphology operations, then according to preset connected domain threshold value into
Row connected domain is screened, and ROI image is also divided into small characters region and big character zone；
S53, the classification according to ROI image carry out feature extraction and feature to the big character zone of ROI image and CAD image block
After matching, defect dipoles are carried out according to matching result；
S54, for the small characters region of ROI image and CAD image block, after carrying out character recognition, number of characters that identification is obtained
Group is divided into multiple character strings, and then after the character string that ROI image and the identification of CAD image block obtain is matched, according to matching
As a result defect dipoles are carried out.
4. a kind of character defect inspection method of tire-mold according to claim 3, which is characterized in that the step
S52 is specially：
The case where for ROI image being A classes, after carrying out Local threshold segmentation and region growing to ROI image, carry out form student movement
It calculates, connected domain screening is then carried out according to preset connected domain threshold value, ROI image is also divided into small characters region and big character
Region；
For ROI image be B classes the case where, carry out mean filter, Region growing segmentation and binaryzation knot successively to ROI image
Fruit carries out morphology operations after negating, and then carries out connected domain screening according to preset connected domain threshold value, ROI image is also divided
For small characters region and big character zone.
5. a kind of character defect inspection method of tire-mold according to claim 4, which is characterized in that the step
S53 is specially：
For ROI image be A classes the case where, using the big character zone of ROI image as template, in the big character of CAD image block
NCC matchings are carried out on region, if matching degree is more than preset matching threshold value, to the big character area of ROI image and CAD image block
Domain carries out morphology and subtracts each other, after difference operation and morphological erosion successively, and it is default to judge whether the area in the region obtained is less than
Threshold value, if so, judging the character, there are printing defects, otherwise, it is determined that the character printing is correct；
For ROI image be B classes the case where, using canny operators obtain ROI image big character zone edge after be used as mould
Plate scans for matching on the binary image of the big character zone of CAD image block, if matching degree is less than preset matching threshold
Value then judges the character there are printing defects, and the centre coordinate of misregistration character region.
6. a kind of character defect inspection method of tire-mold according to claim 4, which is characterized in that the step
S54, including：
S541, two number of characters are obtained respectively after progress character recognition for the small characters region of ROI image and CAD image block
Group, and then each character array is divided into multiple character strings；
S542, each character string to ROI image, carry out matching search in the character array of CAD image block, if matching not at
Work(thens follow the steps S543, otherwise judges that character string printing is correct；
Character zone division is re-started after S543, adjusting parameter, and then the ROI in the corresponding small characters region of the character string is schemed
After extracting character again, identification obtains a new character string；
S544, the new character string, if matching is unsuccessful, return to step are searched in matching in the character array of CAD image block
The identification of S543 repeat character strings, matching operation, and judge whether the successful match in defined searching times, if so, judging
Character string printing is correct, and is entered into correct characters array, conversely, judging the character string, there are printing defects, and record
The centre coordinate of error character string region；
S545, each character string to CAD image block, carry out matching search in correct characters array, if matching is unsuccessful,
Step S546 is executed, otherwise judges that character string printing is correct；
S546, it after extracting character on the ROI image of the character string corresponding region, identifies and obtains an array of checking character, into
And matching search is carried out to the character string in array of checking character, if matching is unsuccessful, judges that the character string exists and bite
Defect, on the contrary judge that character string printing is correct.
7. a kind of character defect inspection method of tire-mold according to claim 1, which is characterized in that the step S3
Described in the corresponding flat type image of CAD design figure obtain in the following manner：
Obtain CAD design figure and by it into being converted to binary map after row threshold division, using the marking image in CAD design figure as
Foreground image, and then be fitted the minimum circumscribed circle of the foreground image, and after obtaining the center of circle and the radius of the minimum circumscribed circle, according to
The center of circle of acquisition carries out polar coordinate transform with radius, obtains the flat type image of CAD design figure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610107512.7A CN105675626B (en) | 2016-02-26 | 2016-02-26 | A kind of character defect inspection method of tire-mold |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610107512.7A CN105675626B (en) | 2016-02-26 | 2016-02-26 | A kind of character defect inspection method of tire-mold |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105675626A CN105675626A (en) | 2016-06-15 |
| CN105675626B true CN105675626B (en) | 2018-08-07 |
Family
ID=56305136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610107512.7A Active CN105675626B (en) | 2016-02-26 | 2016-02-26 | A kind of character defect inspection method of tire-mold |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105675626B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355572B (en) * | 2016-08-19 | 2019-05-21 | 广东工业大学 | The automatic positioning method of tire-mold image |
| CN106897990B (en) * | 2016-08-31 | 2019-10-25 | 广东工业大学 | The character defect inspection method of tire-mold |
| JP6804292B2 (en) * | 2016-12-28 | 2020-12-23 | オムロンヘルスケア株式会社 | Terminal equipment |
| CN107328793B (en) * | 2017-06-30 | 2019-12-03 | 航天新长征大道科技有限公司 | A kind of jewelry surface word print flaw detection method and device based on machine vision |
| CN107948464B (en) * | 2017-09-15 | 2019-07-23 | 兰州交通大学 | A kind of geometric correction method and system of the laterally offset of printed matter detection image |
| TWI671686B (en) * | 2018-01-24 | 2019-09-11 | 緯創資通股份有限公司 | Image data retrieving method and image data retrieving device |
| CN108711148B (en) * | 2018-05-11 | 2022-05-27 | 沈阳理工大学 | Tire defect intelligent detection method based on deep learning |
| CN109142383B (en) * | 2018-08-10 | 2021-07-09 | 惠州太初科技有限公司 | Character defect detection method based on morphology |
| CN109685070B (en) * | 2019-01-11 | 2023-01-24 | 上海大学(浙江·嘉兴)新兴产业研究院 | Image preprocessing method |
| CN109712162B (en) * | 2019-01-18 | 2023-03-21 | 珠海博明视觉科技有限公司 | Cable character defect detection method and device based on projection histogram difference |
| CN111060527B (en) * | 2019-12-30 | 2021-10-29 | 歌尔股份有限公司 | Character defect detection method and device |
| CN112966746A (en) * | 2020-11-20 | 2021-06-15 | 扬州大学 | Stable variable gray template generation method suitable for tire defect detection |
| CN114120310B (en) * | 2022-01-27 | 2022-06-21 | 廊坊易砚领创科技有限公司 | Detection method of tire mold side plate |
| CN115497099B (en) * | 2022-09-23 | 2023-04-18 | 神州数码系统集成服务有限公司 | Single character image matching and identifying method based on circular scanning |
| CN116758045B (en) * | 2023-07-05 | 2024-01-23 | 日照鲁光电子科技有限公司 | Surface defect detection method and system for semiconductor light-emitting diode |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9110032B2 (en) * | 2013-03-14 | 2015-08-18 | Integro Technologies Corp. | System and methods for inspecting tire wheel assemblies |
| CN105067638A (en) * | 2015-07-22 | 2015-11-18 | 广东工业大学 | Tire fetal-membrane surface character defect detection method based on machine vision |
| CN204842266U (en) * | 2015-07-30 | 2015-12-09 | 昆山德玛驰自动化设备科技有限公司 | CCD character detects machine |
| CN105283750A (en) * | 2013-06-13 | 2016-01-27 | 米其林企业总公司 | Method for processing a digital image of the surface of a tire in order to detect an anomaly |
| CN105352974A (en) * | 2015-11-13 | 2016-02-24 | 广东工业大学 | A device for recognizing and detecting surface words of a tyre sidewall of a tyre mold |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6317892B2 (en) * | 2013-06-06 | 2018-04-25 | 株式会社ブリヂストン | Appearance inspection apparatus and appearance inspection method |
-
2016
- 2016-02-26 CN CN201610107512.7A patent/CN105675626B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9110032B2 (en) * | 2013-03-14 | 2015-08-18 | Integro Technologies Corp. | System and methods for inspecting tire wheel assemblies |
| CN105283750A (en) * | 2013-06-13 | 2016-01-27 | 米其林企业总公司 | Method for processing a digital image of the surface of a tire in order to detect an anomaly |
| CN105067638A (en) * | 2015-07-22 | 2015-11-18 | 广东工业大学 | Tire fetal-membrane surface character defect detection method based on machine vision |
| CN204842266U (en) * | 2015-07-30 | 2015-12-09 | 昆山德玛驰自动化设备科技有限公司 | CCD character detects machine |
| CN105352974A (en) * | 2015-11-13 | 2016-02-24 | 广东工业大学 | A device for recognizing and detecting surface words of a tyre sidewall of a tyre mold |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105675626A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105675626B (en) | A kind of character defect inspection method of tire-mold | |
| CN106845372B (en) | The ship target detection recognition method and system of a kind of space remote sensing optical imagery | |
| CN105067638B (en) | Tire fetal membrane face character defect inspection method based on machine vision | |
| CN104992449B (en) | Information identification and surface defect online test method based on machine vision | |
| WO2020248439A1 (en) | Crown cap surface defect online inspection method employing image processing | |
| CN110930390B (en) | Chip pin missing detection method based on semi-supervised deep learning | |
| Zhong et al. | Blob analyzation-based template matching algorithm for LED chip localization | |
| CN108491788A (en) | A kind of intelligent extract method and device for financial statement cell | |
| CN105913093A (en) | Template matching method for character recognizing and processing | |
| CN108090494B (en) | Textile defect identification method based on Gabor filter and support vector machine | |
| CN111507976B (en) | Defect detection method and system based on multi-angle imaging | |
| CN103871053A (en) | Vision conspicuousness-based cloth flaw detection method | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN103942777A (en) | Mobile phone glass cover plate defect detecting method based on principal component analysis | |
| Dong et al. | A random forest-based automatic inspection system for aerospace welds in X-ray images | |
| CN113724231A (en) | Industrial defect detection method based on semantic segmentation and target detection fusion model | |
| CN106056597A (en) | Object visual detection method and device | |
| Ji et al. | Apple grading method based on features of color and defect | |
| CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
| CN103699876A (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
| Abdellah et al. | Defect detection and identification in textile fabric by SVM method | |
| CN114549493A (en) | Magnetic core defect detection system and method based on deep learning | |
| CN103258218A (en) | Matte detection frame generation method and device and defect detection method and device | |
| TWI543117B (en) | Method for recognizing and locating object | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |