CN110348461A - A kind of Surface Flaw feature extracting method - Google Patents
A kind of Surface Flaw feature extracting method Download PDFInfo
- Publication number
- CN110348461A CN110348461A CN201910607775.8A CN201910607775A CN110348461A CN 110348461 A CN110348461 A CN 110348461A CN 201910607775 A CN201910607775 A CN 201910607775A CN 110348461 A CN110348461 A CN 110348461A
- Authority
- CN
- China
- Prior art keywords
- image
- workpiece
- gray
- surface flaw
- extracting method
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000010008 shearing Methods 0.000 claims abstract description 10
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000011218 segmentation Effects 0.000 claims description 13
- 230000007547 defect Effects 0.000 claims description 11
- 230000004069 differentiation Effects 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims 1
- 238000005286 illumination Methods 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of Surface Flaw feature extracting methods, comprising the following steps: S1, source images acquisition;S2, source images pretreatment;S3, threshold cutting;S4, workpiece area positioning;S5, shearing;S6, filtering processing;S7, contours extract;S8, feature extraction;S9, eigenvector recognition.Advantage is: the present invention is good to the good adaptability of illumination variation, has good Negative selection and scale selection characteristic, also improves robustness while improving the accuracy differentiated relative to existing Surface Flaw feature extracting method.
Description
Technical field
The present invention relates to workpiece quality detection technique field more particularly to a kind of Surface Flaw feature extracting methods.
Background technique
With the development of manufacturing technology, the requirement for being machined reliability is also higher and higher, automatic to Surface Flaw
More stringent requirements are proposed for detection.The new automatic etection theory extracted for Surface Flaw of research and development and method, meet enterprise
Industry there is an urgent need to also be of great significance to mechanical subject fundamental research.
At present for Surface Flaw Detection technology, the baseband signal feature for being mainly based upon workpiece surface image is organic
Defect gray feature separates defect, i.e., carries out defect using the shade of gray difference of image deflects part and background area
Separation, and the influence of factors such as workpiece image characteristic extraction procedure is blocked, dynamic background, visual angle and illumination variation and have
There is very big challenge.
For this purpose, it is proposed that a kind of Surface Flaw feature extracting method solves the above problems.
Summary of the invention
The purpose of the present invention is to solve the problems of the prior art, and a kind of Surface Flaw feature proposed mentions
Take method.
To achieve the goals above, present invention employs following technical solutions:
A kind of Surface Flaw feature extracting method, comprising the following steps:
S1, source images acquisition: workpiece surface image is collected using professional imaging device;
S2, source images pretreatment: improving image quality promotes picture contrast;
S3, threshold cutting: according to Threshold Segmentation Algorithm, to treated, image carries out threshold cutting;
S4, workpiece area positioning: regional area filling is carried out to the bianry image after Threshold segmentation and is filled out with besieged region
It fills;
S5, shearing: the workpiece area outer profile of bianry image after filling is extracted, outlines workpiece area using minimum circumscribed rectangle
Domain;Workpiece image is obtained using the working region of workpiece area shearing algorithm shearing source images;
S6, filtering processing: workpiece image is filtered using Gabor filter, filters out workpiece said surface
On bar shaped texture, obtain multiple filtering workpiece images;
S7, contours extract: filtering workpiece image progress edge sharpening is handled and obtains edge sharpening image, at edge sharpening
Self-adaption binaryzation processing is carried out after reason again and obtains contour images;
S8, feature extraction: carrying out contour detecting processing to the contour images using the patch of pre-set dimension size, from
And obtain feature vector V corresponding to each patchij, and by all workpiece features vector VijSimultaneously composition characteristic is normalized
Vector set Vi, wherein the subscript j is described eigenvector in described eigenvector collection and ViWithin serial number;
S9, eigenvector recognition: by all feature vector set ViIn feature vector VijBring trained point in advance into
Differentiation operation is carried out in class device, wherein differentiate that result is divided into normal and two kinds of result types of defect, be identified as the feature of defect
Vector is Surface Flaw feature vector.
In above-mentioned Surface Flaw feature extracting method, in the step S3, before carrying out Threshold segmentation, removal
Grey level histogram is counted after noise in source images, display foreground and two maximum values of background gray scale are obtained, using gray scale stretching
Algorithm obtains gray scale stretching image.
In above-mentioned Surface Flaw feature extracting method, the gray scale stretching algorithm is calculated by the following formula:
Wherein, the number of greyscale levels of source images is 0~M, and background colour is white, and foreground is black, and a is grey in 0~M/2
The corresponding gray value of histogram prospect maximum value is spent, b is the corresponding gray value of grey level histogram background maximum value in M/2~M,
X, y are pixel coordinates, and f (x, y) is gray value of the source images in coordinate (x, y), and g (x, y) is the coordinate (x, y) after gray scale stretching
The gray value at place, series are 0~M, and c, d are setting value.
In above-mentioned Surface Flaw feature extracting method, in the step S6, Gabor filter is to workpiece figure
As the Gabor kernel function g being filtered2Formula is defined as:
It is describedIt is describedThe λ is the Gabor kernel function
Wavelength, the δ are the scale size of the Gabor kernel function, and the θ is to inhibit angle, describedFor phase difference, described (x,
It y) is the coordinate of the gray level image and filtered image corresponding pixel points.
In above-mentioned Surface Flaw feature extracting method, in the step S8, feature vector VijIncluding passing through
Contour detecting handle profile obtained is long, profile is wide, gray average 5 of the position coordinates (x, y) of profile and the profile
Characteristic value.
In above-mentioned Surface Flaw feature extracting method, in the step S8, feature vector VijIncluding passing through
Contour detecting handle profile obtained is long, profile is wide, gray average 5 of the position coordinates (x, y) of profile and the profile
Characteristic value.
In above-mentioned Surface Flaw feature extracting method, in step s3, Threshold Segmentation Algorithm includes following step
Suddenly
The grey level histogram number of gray scale stretching image is Hist [256], and the number of pixels that gray value is i is ni=Hist
[i], total pixel number of the gray value between [0~T] are N,Gray value is the probability of the pixel of i are as follows:
The sum of gray value pixel between [T+1~255] is L, thenGray value is the pixel of i
Probability are as follows:
It asksThe corresponding i of maximum value max { sum [i], i ∈ [0~255] }, wherein
Obtained i is image segmentation threshold T, carries out Threshold segmentation to gray scale stretching image according to T.
Compared with prior art, the invention has the benefit that
1, by counting grey level histogram after taking out the noise in source images, and gray scale is obtained by gray scale stretching algorithm and is drawn
Image is stretched, followed by threshold cutting, can quickly and accurately extract the image of the correspondence range of the workpiece, so as to
Greatly reduce the operand of subsequent processes, at the same can also be corresponded to avoid workpiece the picture material except range to differentiation at
The interference of reason also improves robustness while improving the accuracy of differentiation.
2 operations for positioning and shearing by workpiece area obtain the outer profile in workpiece image region, use minimum external square
Shape outlines workpiece area outer profile, and is cut into workpiece image, provides the inclination angle of workpiece image.
3, workpiece image is filtered using Gabor filter, filters out the profile and surface of workpiece itself
The interference and influence that bar shaped texture extracts subsequent characteristics, further, since carrying out edge to using the image after filtering processing
Contours extract is being carried out after sharpening, therefore is substantially increasing the reliability and robustness of contour feature extraction;Due to Gabor core
Function is capable of providing good direction selection and scale selection characteristic for the edge sensitive of image, and for illumination variation
It is insensitive, it is capable of providing to the good adaptability of illumination variation, also, due in Gabor filtering mode and human visual system
The visual stimulus response of simple cell is closely similar, therefore with good in terms of the local space and frequency-domain information for extracting target
Good characteristic.In addition, have operation simple by using the mode that Garbor is filtered, it can be readily appreciated that parameter is easy to adjust, and
And the complexity of calculating is reduced, reduce calculation amount, improves response speed.
Specific embodiment
Following embodiment only exists in illustrative purpose, limits the scope of the invention without being intended to.
Embodiment
A kind of Surface Flaw feature extracting method, comprising the following steps:
(1) source images acquire: collecting workpiece surface image using professional imaging device;
(2) source images pre-process: improving image quality promotes picture contrast;
(3) grey level histogram is counted after removing the noise in source images, obtains display foreground and two maximums of background gray scale
Value, obtains gray scale stretching image using gray scale stretching algorithm;
Gray scale stretching algorithm is calculated by the following formula:
Wherein, the number of greyscale levels of source images is 0~M, and background colour is white, and foreground is black, and a is grey in 0~M/2
The corresponding gray value of histogram prospect maximum value is spent, b is the corresponding gray value of grey level histogram background maximum value in M/2~M,
X, y are pixel coordinates, and f (x, y) is gray value of the source images in coordinate (x, y), and g (x, y) is the coordinate (x, y) after gray scale stretching
The gray value at place, series are 0~M, and c, d are setting value
(4) threshold cutting: according to Threshold Segmentation Algorithm, to treated, image carries out threshold cutting;
The grey level histogram number of gray scale stretching image is Hist [256], and the number of pixels that gray value is i is ni=Hist
[i], total pixel number of the gray value between [0~T] are N,Gray value is the probability of the pixel of i are as follows:
The sum of gray value pixel between [T+1~255] is L, thenGray value is the pixel of i
Probability are as follows:
It asksThe corresponding i of maximum value max { sum [i], i ∈ [0~255] }, wherein
Obtained i is image segmentation threshold T, carries out Threshold segmentation to gray scale stretching image according to T
(5) workpiece area positions: carrying out regional area filling to the bianry image after Threshold segmentation and fills out with besieged region
It fills;
(6) it shears: extracting the workpiece area outer profile of bianry image after filling, outline workpiece area using minimum circumscribed rectangle
Domain;Workpiece image is obtained using the working region of workpiece area shearing algorithm shearing source images;
(7) it is filtered: workpiece image being filtered using Gabor filter, filters out workpiece said surface
On bar shaped texture, obtain multiple filtering workpiece images;
The Gabor kernel function g that Gabor filter is filtered workpiece image2Formula is defined as:
λ is the wavelength of Gabor kernel function, and δ is Gabor core
The scale size of function, θ are to inhibit angle,For phase difference, (x, y) is gray level image and filtered image corresponding pixel points
Coordinate
(8) contours extract: filtering workpiece image progress edge sharpening is handled and obtains edge sharpening image, at edge sharpening
Self-adaption binaryzation processing is carried out after reason again and obtains contour images;
(9) feature extraction: contour detecting processing is carried out to contour images using the patch of pre-set dimension size, to obtain
Obtain feature vector V corresponding to each patchij, and by all workpiece features vector VijSimultaneously composition characteristic vector is normalized
Set Vi, wherein subscript j is feature vector in set of eigenvectors and ViWithin serial number;
Feature vector VijIncluding by contour detecting handle profile obtained is long, profile is wide, the position coordinates of profile (x,
And 5 characteristic values of gray average of profile y);
(10) eigenvector recognition: by all feature vector set ViIn feature vector VijBring trained point in advance into
Differentiation operation is carried out in class device, wherein differentiate that result is divided into normal and two kinds of result types of defect, be identified as the feature of defect
Vector is Surface Flaw feature vector;
Feature vector VijIncluding by contour detecting handle profile obtained is long, profile is wide, the position coordinates of profile (x,
And 5 characteristic values of gray average of profile y).
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (7)
1. a kind of Surface Flaw feature extracting method, which comprises the following steps:
S1, source images acquisition: workpiece surface image is collected using professional imaging device;
S2, source images pretreatment: improving image quality promotes picture contrast;
S3, threshold cutting: according to Threshold Segmentation Algorithm, to treated, image carries out threshold cutting;
S4, workpiece area positioning: regional area filling and besieged area filling are carried out to the bianry image after Threshold segmentation;
S5, shearing: the workpiece area outer profile of bianry image after filling is extracted, outlines workpiece area using minimum circumscribed rectangle;
Workpiece image is obtained using the working region of workpiece area shearing algorithm shearing source images;
S6, filtering processing: workpiece image is filtered using Gabor filter, is filtered out on workpiece said surface
Bar shaped texture obtains multiple filtering workpiece images;
S7, contours extract: edge sharpening processing is carried out to filtering workpiece image and obtains edge sharpening image, edge sharpening handles it
It carries out self-adaption binaryzation processing again afterwards and obtains contour images;
S8, feature extraction: contour detecting processing is carried out to the contour images using the patch of pre-set dimension size, to obtain
Obtain feature vector V corresponding to each patchij, and by all workpiece features vector VijSimultaneously composition characteristic vector is normalized
Set Vi, wherein the subscript j is described eigenvector in described eigenvector collection and ViWithin serial number;
S9, eigenvector recognition: by all feature vector set ViIn feature vector VijBring preparatory trained classifier into
In carry out differentiation operation, wherein differentiate that result is divided into normal and two kinds of result types of defect, be identified as the feature vector of defect
As Surface Flaw feature vector.
2. a kind of Surface Flaw feature extracting method according to claim 1, it is characterised in that: in the step S3
In, before carrying out Threshold segmentation, grey level histogram is counted after removing the noise in source images, obtains display foreground and background gray scale two
A maximum value obtains gray scale stretching image using gray scale stretching algorithm.
3. a kind of Surface Flaw feature extracting method according to claim 2, it is characterised in that: the gray scale stretching
Algorithm is calculated by the following formula:
Wherein, the number of greyscale levels of source images is 0~M, and background colour is white, and foreground is black, and a is that gray scale is straight in 0~M/2
The corresponding gray value of square figure prospect maximum value, b are the corresponding gray value of grey level histogram background maximum value, x, y in M/2~M
It is pixel coordinate, f (x, y) is gray value of the source images in coordinate (x, y), and g (x, y) is at the coordinate (x, y) after gray scale stretching
Gray value, series be 0~M, c, d be setting value.
4. a kind of Surface Flaw feature extracting method according to claim 2, it is characterised in that: in the step S6
In, the Gabor kernel function g that Gabor filter is filtered workpiece image2Formula is defined as:
It is describedIt is describedThe λ is the wavelength of the Gabor kernel function,
The δ is the scale size of the Gabor kernel function, and the θ is to inhibit angle, describedFor phase difference, (x, y) is institute
State the coordinate of gray level image Yu filtered image corresponding pixel points.
5. a kind of Surface Flaw feature extracting method according to claim 1, it is characterised in that: in the step S8
In, feature vector VijIncluding by contour detecting handle profile obtained is long, profile is wide, the position coordinates (x, y) of profile and
5 characteristic values of gray average of the profile.
6. a kind of Surface Flaw feature extracting method according to claim 1, it is characterised in that: in the step S9
In, the trained classifier is to advance with training sample to be trained to what is constructed based on neural network to training pattern
The model obtained afterwards, the training sample include historic defects characteristic information and corresponding defect classification information.
7. a kind of Surface Flaw feature extracting method according to claim 2, it is characterised in that: in step s3,
Threshold Segmentation Algorithm includes the following steps
The grey level histogram number of gray scale stretching image is Hist [256], and the number of pixels that gray value is i is ni=Hist [i], ash
Total pixel number of the angle value between [0~T] is N,Gray value is the probability of the pixel of i are as follows:
The sum of gray value pixel between [T+1~255] is L, thenGray value is the probability of the pixel of i
Are as follows:
It asksThe corresponding i of maximum value max { sum [i], i ∈ [0~255] }, wherein
Obtained i is image segmentation threshold T, carries out Threshold segmentation to gray scale stretching image according to T.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910607775.8A CN110348461A (en) | 2019-07-05 | 2019-07-05 | A kind of Surface Flaw feature extracting method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910607775.8A CN110348461A (en) | 2019-07-05 | 2019-07-05 | A kind of Surface Flaw feature extracting method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110348461A true CN110348461A (en) | 2019-10-18 |
Family
ID=68177941
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910607775.8A Withdrawn CN110348461A (en) | 2019-07-05 | 2019-07-05 | A kind of Surface Flaw feature extracting method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110348461A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111390578A (en) * | 2020-06-08 | 2020-07-10 | 佛山市南海富大精密机械有限公司 | Five-axis linkage numerical control machine tool |
CN112505049A (en) * | 2020-10-14 | 2021-03-16 | 上海互觉科技有限公司 | Mask inhibition-based method and system for detecting surface defects of precision components |
CN112907498A (en) * | 2019-11-18 | 2021-06-04 | 中国商用飞机有限责任公司 | Pore identification method, device, equipment and storage medium |
CN113426709A (en) * | 2021-07-21 | 2021-09-24 | 长沙荣业软件有限公司 | Intelligent detection robot for grain material purchase and grain material classification method |
CN114155241A (en) * | 2022-01-28 | 2022-03-08 | 浙江华睿科技股份有限公司 | Foreign matter detection method and device and electronic equipment |
CN114170200A (en) * | 2021-12-13 | 2022-03-11 | 沭阳鑫洪锐金属制品有限公司 | Metal pitting defect degree evaluation method and system based on artificial intelligence |
-
2019
- 2019-07-05 CN CN201910607775.8A patent/CN110348461A/en not_active Withdrawn
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112907498A (en) * | 2019-11-18 | 2021-06-04 | 中国商用飞机有限责任公司 | Pore identification method, device, equipment and storage medium |
CN112907498B (en) * | 2019-11-18 | 2024-04-30 | 中国商用飞机有限责任公司 | Pore identification method, device, equipment and storage medium |
CN111390578A (en) * | 2020-06-08 | 2020-07-10 | 佛山市南海富大精密机械有限公司 | Five-axis linkage numerical control machine tool |
CN111390578B (en) * | 2020-06-08 | 2020-09-08 | 佛山市南海富大精密机械有限公司 | Five-axis linkage numerical control machine tool |
CN112505049A (en) * | 2020-10-14 | 2021-03-16 | 上海互觉科技有限公司 | Mask inhibition-based method and system for detecting surface defects of precision components |
CN112505049B (en) * | 2020-10-14 | 2021-08-03 | 上海互觉科技有限公司 | Mask inhibition-based method and system for detecting surface defects of precision components |
CN113426709A (en) * | 2021-07-21 | 2021-09-24 | 长沙荣业软件有限公司 | Intelligent detection robot for grain material purchase and grain material classification method |
CN114170200A (en) * | 2021-12-13 | 2022-03-11 | 沭阳鑫洪锐金属制品有限公司 | Metal pitting defect degree evaluation method and system based on artificial intelligence |
CN114170200B (en) * | 2021-12-13 | 2023-01-20 | 沭阳鑫洪锐金属制品有限公司 | Metal pitting defect degree evaluation method and system based on artificial intelligence |
CN114155241A (en) * | 2022-01-28 | 2022-03-08 | 浙江华睿科技股份有限公司 | Foreign matter detection method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110348461A (en) | A kind of Surface Flaw feature extracting method | |
CN111310558B (en) | Intelligent pavement disease extraction method based on deep learning and image processing method | |
CN109410230B (en) | Improved Canny image edge detection method capable of resisting noise | |
CN106548463B (en) | Sea fog image automatic defogging method and system based on dark and Retinex | |
WO2022205525A1 (en) | Binocular vision-based autonomous underwater vehicle recycling guidance false light source removal method | |
CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
CN110120056B (en) | Blood leukocyte segmentation method based on adaptive histogram threshold and contour detection | |
CN105740945A (en) | People counting method based on video analysis | |
CN104732536A (en) | Sub-pixel edge detection method based on improved morphology | |
CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
CN109993099A (en) | A kind of lane line drawing recognition methods based on machine vision | |
CN103175844A (en) | Detection method for scratches and defects on surfaces of metal components | |
CN108921004A (en) | Safety cap wears recognition methods, electronic equipment, storage medium and system | |
CN112907519A (en) | Metal curved surface defect analysis system and method based on deep learning | |
CN114118144A (en) | Anti-interference accurate aerial remote sensing image shadow detection method | |
CN103729856B (en) | A kind of Fabric Defects Inspection detection method utilizing S-transformation signal extraction | |
CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
CN109781737B (en) | Detection method and detection system for surface defects of hose | |
CN112614062A (en) | Bacterial colony counting method and device and computer storage medium | |
CN112734761A (en) | Industrial product image boundary contour extraction method | |
CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
CN108090492B (en) | Contour detection method based on scale clue suppression | |
CN112861654A (en) | Famous tea picking point position information acquisition method based on machine vision | |
CN111768455A (en) | Image-based wood region and dominant color extraction 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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191018 |