CN111062939B - Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics - Google Patents
Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics Download PDFInfo
- Publication number
- CN111062939B CN111062939B CN201911407477.0A CN201911407477A CN111062939B CN 111062939 B CN111062939 B CN 111062939B CN 201911407477 A CN201911407477 A CN 201911407477A CN 111062939 B CN111062939 B CN 111062939B
- Authority
- CN
- China
- Prior art keywords
- avg
- defect
- gray
- strip steel
- global
- 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
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8829—Shadow projection or structured background, e.g. for deflectometry
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to the technical field of computer vision, and discloses a rapid quality screening and defect characteristic automatic extraction method for a strip steel surface, which comprises the following steps: 1) Carrying out gray projection on the acquired strip steel surface image to obtain a gray matrix image; 2) Finding out the maximum value R of gray projection values of each row in the gray matrix diagram Max Minimum value R Min Maximum value C of gray projection value of each column Max Minimum value C Min Calculating the gray projection mean value R of each row Avg Mean value C of gray projection of each column Avg Then judging whether the strip steel surface image has defects or not according to the average value of gray projection values of each row and each column and the difference value between the maximum value and the minimum value; 3) Cutting the gray matrix diagram according to the judging result of the step 2), and marking a defect feature ROI area in the cut gray matrix diagram. The method can rapidly screen the defects in the strip steel surface image, has high calculation speed, and meets the real-time online defect detection requirement of the high-speed strip steel production line.
Description
Technical Field
The application belongs to the technical field of computer vision, and particularly relates to a rapid quality screening and defect characteristic automatic extraction method for a strip steel surface.
Background
The strip steel is one of main products in the steel industry, is an indispensable raw material in the industries of aerospace, shipbuilding, automobile, mechanical manufacturing and the like, and the quality of the strip steel directly influences the quality and performance of the final product. In the process of manufacturing the strip steel, the surface of the strip steel has different types of defects such as cracks, scars, holes and the like due to various factors such as raw materials, rolling equipment, processing technology and the like. The defects on the surface of the strip steel not only easily cause serious production accidents such as strip steel breakage, accumulation, stopping and the like, but also seriously abrade rollers, and cause immeasurable economic and social effects on production enterprises.
In recent years, with the development of industrial technology, enterprises gradually start to use non-contact nondestructive testing technology represented by machine vision, and the non-contact nondestructive testing technology has the advantages of high resolution, strong classification, small influence of environmental electromagnetic fields, large working distance, high measurement precision, low cost and the like. In the production process, the moving speed of the strip steel can exceed 10m/s, a large amount of image data (such as 25 frames/s) can be generated per second to wait for the system to process, and the strip steel containing surface defects only occupies a small part, and most of the strip steel is free of defects, so that the algorithm has high real-time defect detection capability.
The most widely applied algorithm for rapidly discriminating the defects of the strip steel surface is mainly a 'difference shadow method', however, when a camera is adopted to collect the strip steel surface image in actual production, the collected strip steel surface image is influenced by illumination and hardware equipment, and the strip steel boundary image is virtual, so that the strip steel boundary cannot be detected normally. When the acquired strip steel surface image shows the blurring of the strip steel boundary image, a canny operator edge detection is adopted to process the strip steel image, then a obvious long and thin broken fold line is found in the intersection area of the strip steel edge and the background, and the detection is continued by using a differential shadow method, wherein the area where the fold line is located is erroneously identified as the strip steel surface defect, so that the detection of the strip steel surface image by adopting the differential shadow method can identify the blurring area of the strip steel boundary image as the edge defect, and the boundary part does not have the defect in the actual place. The large number of edge 'pseudo defects' provides great challenges for rapid screening of the surface quality of the strip steel and extraction of defect characteristics. How to discriminate the false defects also needs to be included in the range of the investigation of the discrimination of the defects of the strip steel. Aiming at the problems of low area rate of strip steel defects, serious edge pseudo defects and illumination interference, difficult effective extraction of various real defects and the like in the prior art, the application researches a rapid strip steel surface quality screening and defect characteristic automatic extraction method based on a differential shadow method according to the characteristics of strip steel surface defect images.
Disclosure of Invention
The application aims to provide a rapid quality screening and defect characteristic automatic extraction method for a strip steel surface.
In order to achieve the aim of the application, the technical scheme adopted by the application is as follows:
a method for fast quality screening and defect characteristic automatic extraction of strip steel surface comprises the following steps:
(1) Carrying out gray projection on the acquired strip steel surface image in a mode of downward column by column and rightward row by row to obtain a gray matrix diagram;
(2) Analyzing the gray matrix diagram obtained in the step (1) to find out the maximum value R of the gray projection values of each row in the gray matrix diagram Max Minimum value R Min Maximum value C of gray projection value of each column Max Minimum value C Min Calculating the gray projection mean value R of each row Avg Mean value C of gray projection of each column Avg And Global gray average Global for the entire gray matrix map Avg Then judging a defect area, a defect-free area, a boundary pseudo defect area, a conversion area of a band steel boundary and a background area in the band steel surface image according to the average value of gray projection values of each row and each column and the difference value of the maximum value and the minimum value;
(3) Cutting and deleting a boundary pseudo defect area, a conversion area and a background area in the gray matrix diagram according to the judging result in the step (2), and marking a defect feature ROI area in the cut gray matrix diagram.
According to the above method for fast quality discrimination and automatic extraction of defect features on a strip steel surface, preferably, in the step (2), the specific operations of determining a defect area, a defect-free area, a boundary pseudo defect area, a conversion area between a strip steel boundary and a background, and a background area in an image of the strip steel surface according to the difference between the maximum value and the minimum value of each row and each column of gray projection values are as follows:
A. judging each column in the gray matrix diagram:
（A1）C Max and C Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And C in Avg ＞Global Avg 10, the column is defect-free;
（A2）C Max and C Min Difference of C Avg Are all in [ (1-mu) Global Avg ，(1+µ)Global Avg ]If there is a defect in the column;
（A3）C Max and C Min The difference value between [ (1-mu) Global Avg ，(1+µ)Global Avg ]In, but C Avg ＜(1-2µ) Global Avg The column is a conversion area of the boundary of the strip steel and the background; starting from adjacent columns of the conversion area, transversely extending in the direction of increasing the gray average value to obtain a boundary pseudo-defect area, wherein the gray average value of the adjacent columns is larger than that of the conversion area, and the transversely extending width is 1-3 times of the width of the conversion area;
（A4）C Max and C Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And C in Avg ≤Global Avg And/10, the column is a strip steel background area;
B. judging each row in the gray matrix diagram:
（B1）R Max and R is R Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And R is Avg ＞Global Avg 10, then the row is defect free;
（B2）R Max and R is R Min Is the difference of R Avg Are all in [ (1-mu) Global Avg ，(1+µ)Global Avg ]If there is a defect in the row;
（B3）R Max and R is R Min The difference value between [ (1-mu) Global Avg ，(1+µ)Global Avg ]And R is Avg ＜(1-2µ) Global Avg The transition area of the boundary and the background of the behavior strip steel; starting with adjacent rows of the conversion area, and longitudinally extending in the direction of increasing the gray average value to obtain a boundary pseudo-defect area, wherein the gray average value of the adjacent rows is larger than the gray average value of the conversion area, and the longitudinal extending width is 1-3 times of the width of the conversion area;
（B4）R Max and R is R Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And R is Avg ≤Global Avg And/10, the behavior strip steel background area;
wherein [ mu ] is a defect threshold coefficient.
Finding out the column where the defect area is located according to the column judging result, and finding out the row where the defect area is located according to the row judging result, wherein the position where the row and the column intersect is the position where the defect area is located.
According to the rapid quality screening and defect characteristic automatic extraction method for the strip steel surface, the defect threshold coefficient [ mu ] is mainly obtained by performing a preliminary adjustment test according to the on-site illumination condition and the gray value of the defect-free rolled steel, and the size of the value range directly determines the frame size of the defect characteristic ROI. If the value of the [ mu ] is too small, the frame of the ROI area is smaller, so that the algorithm can only frame the obvious defect characteristics and ignore the unobvious defect characteristics; if the value of the mu is too large, the frame of the ROI area is larger, the algorithm can frame the obvious defect characteristics and the unobvious defect characteristics, and the defect-free area around the defect can be possibly framed in.
According to the rapid quality screening and defect characteristic automatic extraction method for the strip steel surface, preferably, the value range of the defect threshold value coefficient mu is 20% -30%. More preferably, the value range of the defect threshold coefficient [ mu ] is 30%.
According to the above method for rapid quality screening and automatic defect feature extraction of the strip steel surface, preferably, the specific operation of step (3) is as follows: and (3) cutting and deleting a boundary pseudo defect region, a conversion region and a background region in the gray matrix diagram according to the judgment result in the step (2), marking rows and columns judged to contain defects in the cut gray matrix diagram, and simultaneously drawing a rectangular frame to form a defect region, wherein the rectangular frame region is a defect characteristic ROI region.
According to the above method for fast quality screening and automatic defect feature extraction of the surface of the strip steel, preferably, in the step (1), before gray projection is performed on the surface image of the strip steel, the background area rough cutting is performed on the surface image of the strip steel, which comprises the following specific operations: and identifying the acquired strip steel surface image according to the characteristic of clear distinction between the strip steel and the background, screening out the edge background in the strip steel surface image, and deleting the edge background. The operation can effectively filter the interference of most of the edge background areas on the image analysis, further reduce the calculated amount and improve the detection efficiency.
Compared with the prior art, the application has the positive beneficial effects that:
(1) The application carries out gray projection on the collected strip steel surface image in a mode of downward columns and rightward rows to obtain a gray matrix image, and can effectively filter defect-free surfaces, edge pseudo defects and illumination interference according to the average value of gray projection values of each row and each column and the difference value of the maximum value and the minimum value in the gray matrix image, rapidly detect defects (especially the defects of longitudinal lines, transverse lines, large-area oxide scale and the like existing on the strip steel surface) in the image, and output defect feature ROI (region of interest) in the strip steel surface image; the method greatly reduces the calculated amount, has the advantages of high calculation speed, high efficiency and high accuracy of detection results, can rapidly screen the defects in the acquired strip steel surface images, meets the real-time online defect detection requirement of a high-speed strip steel production line, can accurately and automatically detect and extract the defect feature ROI (region of interest) in the images, provides high-quality marking data for strip steel defects, omits the problem of marking data by a large amount of manual data, and has strong practicability.
(2) The method has low requirement on hardware performance of equipment, and completely meets the requirement of deployment on an industrial site.
Drawings
FIG. 1 is a graph of the detection result of a strip steel image with a longitudinal inclusion defect on the surface;
FIG. 2 is a partial view of the results of column analysis of the gray matrix image of the original image A in FIG. 1 by column;
FIG. 3 is a partial view of the result of the line analysis of the gray matrix image of the original image A in FIG. 1;
FIG. 4 is an enlarged view of area a of FIG. 3;
FIG. 5 is a graph of the detection result of a strip steel image with a longitudinal scratch defect on the surface;
FIG. 6 is a partial view of the results of column analysis of the gray matrix image of the original image A in FIG. 5 by column;
FIG. 7 is a partial view of the gray matrix image of the original image A in FIG. 5, showing the results of the line analysis;
FIG. 8 is a graph of the detection result of a strip steel image with oxide scale on the surface.
Detailed Description
The present application will be described in further detail by way of the following specific examples, which are not intended to limit the scope of the present application.
Example 1:
a method for fast quality screening and defect characteristic automatic extraction of strip steel surface comprises the following steps:
(1) Carrying out gray projection on the acquired strip steel surface image in a mode of downward column by column and rightward row by row to obtain a gray matrix diagram;
(2) Analyzing the gray matrix diagram obtained in the step (1) to find out the maximum value R of the gray projection values of each row in the gray matrix diagram Max Minimum value R Min Maximum value C of gray projection value of each column Max Minimum value C Min Calculating the gray projection mean value R of each row Avg Mean value C of gray projection of each column Avg And Global gray average Global for the entire gray matrix map Avg And judging a defect area, a defect-free area, a boundary pseudo defect area, a conversion area of the boundary of the strip steel and the background and a background area in the strip steel surface image according to the average value of gray projection values of each row and each column and the difference value of the maximum value and the minimum value.
The specific operation of judging a defect area, a defect-free area, a boundary pseudo defect area, a conversion area of a strip steel boundary and a background area in the strip steel surface image according to the difference value between the maximum value and the minimum value of each row and each column of gray projection values is as follows:
A. judging each column in the gray matrix diagram:
（A1）C Max and C Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And C in Avg ＞Global Avg 10, the column is defect-free;
（A2）C Max and C Min Difference of C Avg Are all in [ (1-mu) Global Avg ，(1+µ)Global Avg ]If there is a defect in the column;
（A3）C Max and C Min The difference value between [ (1-mu) Global Avg ，(1+µ)Global Avg ]In, but C Avg ＜(1-2µ) Global Avg The column is a conversion area of the boundary of the strip steel and the background; starting from adjacent columns of the conversion area, transversely extending in the direction of increasing the gray average value to obtain a boundary pseudo-defect area, wherein the gray average value of the adjacent columns is larger than that of the conversion area, and the transversely extending width is 2 times of the width of the conversion area;
（A4）C Max and C Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And C in Avg ≤Global Avg And/10, the column is a strip background area.
Wherein [ mu ] is a defect threshold coefficient, and the value of the defect threshold coefficient is 30%.
B. Judging each row in the gray matrix diagram:
（B1）R Max and R is R Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And R is Avg ＞Global Avg 10, then the row is defect free;
（B2）R Max and R is R Min Is the difference of R Avg Are all in [ (1-mu) Global Avg ，(1+µ)Global Avg ]If there is a defect in the row;
（B3）R Max and R is R Min The difference value between [ (1-mu) Global Avg ，(1+µ)Global Avg ]And R is Avg ＜(1-2µ) Global Avg The transition area of the boundary and the background of the behavior strip steel; starting with adjacent rows of the conversion region, and longitudinally extending in the direction of increasing the gray average value to obtain a boundary pseudo-defect region, wherein the gray average value of the adjacent rows is larger than that of the conversion regionThe gray average value, the width of the longitudinal extension is 2 times of the width of the conversion area;
（B4）R Max and R is R Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And R is Avg ≤Global Avg And/10, the behavior strip steel background area;
wherein [ mu ] is a defect threshold coefficient, and the value of the defect threshold coefficient is 30%.
(3) And (3) cutting and deleting a boundary pseudo defect region, a conversion region and a background region in the gray matrix diagram according to the judgment result in the step (2), marking rows and columns judged to contain defects in the cut gray matrix diagram, and simultaneously drawing a rectangular frame to form a defect region, wherein the rectangular frame region is a defect characteristic ROI region.
Example 2: the application relates to an effect verification experiment of a rapid quality screening and defect characteristic automatic extraction method for the surface of strip steel
1. Detecting strip steel image with longitudinal inclusion defect on surface
The method of the embodiment 1 of the application is adopted to detect the strip steel image with the longitudinal grain defect on the surface, wherein the collected strip steel surface original image is shown as A in fig. 1, and the A in fig. 1 shows that the strip steel image to be detected has the longitudinal grain defect, the strip steel shooting background area and the conversion area between the strip steel boundary and the background. The detection result is shown in fig. 1B (B is a partial diagram of the detection result), in which the defect region is framed by a square frame, that is, the region framed by the square frame is the detected defect feature ROI region, and the background region, the transition region and the boundary pseudo defect region in the original image a have been deleted by the diagram B, thereby explaining that the defect region and the background region, the transition region and the boundary pseudo defect region in the original image on the surface of the strip steel can be identified by adopting the method described in embodiment 1 of the present application.
Fig. 2 is a partial view of column analysis results of the gray matrix diagram of the original image a in fig. 1 (only a partial view is shown here because the column analysis results are large). As can be seen from FIG. 2, global of the gray matrix diagram Avg =111.3083，(1±µ)Global Avg The value range of (C) is [77.9, 144.7 ]]. Drawing of the figure2, column C where yellow region is located Max - C Min =41，C Avg =2, therefore, the column is the strip background region; c of the column in which the green region is located Max - C Min =101，C Avg =28.8, therefore, the column is the transition region of the strip boundary and background; starting from adjacent columns of the conversion area (the gray average value of the adjacent columns is larger than that of the conversion area), transversely extending in the direction of increasing the gray average value, wherein the width of the transverse extension is 2 times of that of the conversion area, and obtaining a boundary pseudo-defect area, namely a blue area in the figure; three columns of C corresponding to red areas Max And C Min The differences are 119, 126 and 111 in sequence, and the three columns correspond to C Avg The values are 103, 116, 105, respectively, and therefore, there are defects in the three columns corresponding to the red areas. Therefore, as can be seen from fig. 2, the detection method of the present application can clearly detect the background area, the transition area between the strip boundary and the background, the boundary pseudo-defect area and the defect area in the strip surface image.
Fig. 3 is a partial view of the result of the line analysis of the gray matrix diagram of the original image a in fig. 1 by the line analysis (only the partial view is shown here because the result of the line analysis is larger). The behavior defect area corresponding to the red area in fig. 3. As can be seen from fig. 2 and 3, the position of the defective area, i.e., the area outlined by the square frame in fig. 1B, can be accurately found by combining the column detection result with the row detection result. In order to clearly present the row analysis result, taking the region a in fig. 3 as an example, a method is performed on the region a, and an enlarged view thereof is shown in fig. 4.
Detecting strip steel image with longitudinal scratch defect on surface
The method of the embodiment 1 of the application is adopted to detect the strip steel image with the longitudinal grain defect on the surface, wherein the collected strip steel surface original image is shown as A in fig. 5, and as can be known from A in fig. 5, the strip steel image to be detected has the longitudinal grain defect and the strip steel shooting background area. The detection result is shown in fig. 5B (B is a partial diagram of the detection result), in which the defect region is outlined by a square frame, that is, the region outlined by the square frame is the detected defect feature ROI region, and the background region in the original image a has been deleted compared with the original image a, thereby explaining that the defect region in the original image on the strip surface can be identified by adopting the method described in embodiment 1 of the present application.
Fig. 6 is a partial view of column analysis results of the gray matrix diagram of the original image a in fig. 5 (only the partial view is shown here because the column analysis results are larger). The columns corresponding to the red areas in fig. 6 are defective areas. Fig. 7 is a partial view of the line analysis result of the gray matrix diagram of the original image a in fig. 5, which is analyzed by the line (only a contracted diagram is drawn here because the line analysis result diagram is too large). The behavior defect area corresponding to the red area in fig. 7. As can be seen from fig. 6 and 7, the position of the defective area, i.e., the area framed by the square frame in fig. 5B can be accurately found by combining the column detection result with the row detection result.
Detecting the strip steel image with oxide skin covered on the surface
The method of the embodiment 1 of the application is adopted to detect a strip steel image with the surface covered with oxide skin, wherein the collected strip steel surface original image is shown as A in fig. 8, and as can be seen from A in fig. 8, the strip steel image to be detected is covered with oxide skin defects. The detection result is shown in fig. 8B, in which the defect area is framed by a square frame, that is, the area framed by the square frame is the detected defect feature ROI area, thereby illustrating that the defect area in the original image of the strip surface can be identified by using the method described in embodiment 1 of the present application.
The above description is merely illustrative of the preferred embodiments of the present application and is not intended to limit the application to the particular embodiments disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the application.
Claims (4)
1. A method for fast quality screening and defect characteristic automatic extraction of a strip steel surface is characterized by comprising the following steps:
(1) Carrying out gray projection on the acquired strip steel surface image in a mode of downward column by column and rightward row by row to obtain a gray matrix diagram;
(2) For the gray scale obtained in step (1)Analyzing the matrix diagram to find out the maximum value R of each row of gray projection values in the gray matrix diagram Max Minimum value R Min Maximum value C of gray projection value of each column Max Minimum value C Min Calculating the gray projection mean value R of each row Avg Mean value C of gray projection of each column Avg And Global gray average Global for the entire gray matrix map Avg Then judging a defect area, a defect-free area, a boundary pseudo defect area, a conversion area of a band steel boundary and a background area in the band steel surface image according to the average value of gray projection values of each row and each column and the difference value of the maximum value and the minimum value;
(3) Cutting and deleting boundary pseudo defect areas, conversion areas and background areas in the gray matrix diagram according to the judging result in the step (2), and marking defect feature ROI areas in the cut gray matrix diagram.
2. The method for fast quality screening and defect feature extraction on a strip steel surface according to claim 1, wherein in the step (2), the specific operations of determining a defect area, a defect-free area, a boundary pseudo defect area, a conversion area between a strip steel boundary and a background, and a background area in the strip steel surface image according to the difference between the maximum value and the minimum value of each row and each column of gray projection values are as follows:
A. judging each column in the gray matrix diagram:
（A1）C Max and C Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And C in Avg ＞Global Avg 10, the column is defect-free;
（A2）C Max and C Min Difference of C Avg Are all in [ (1-mu) Global Avg ，(1+µ)Global Avg ]If there is a defect in the column;
（A3）C Max and C Min The difference value between [ (1-mu) Global Avg ，(1+µ)Global Avg ]In, but C Avg ＜(1-2µ) Global Avg The column is a conversion area of the boundary of the strip steel and the background; with adjacent columns of conversion regionsStarting, transversely extending in the direction of increasing the gray average value to obtain a boundary pseudo-defect region, wherein the gray average value of the adjacent columns is larger than that of the conversion region, and the transversely extending width is 1-3 times of the width of the conversion region;
（A4）C Max and C Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And C in Avg ≤Global Avg And/10, the column is a strip steel background area;
B. judging each row in the gray matrix diagram:
（B1）R Max and R is R Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And R is Avg ＞Global Avg 10, then the row is defect free;
（B2）R Max and R is R Min Is the difference of R Avg Are all in [ (1-mu) Global Avg ，(1+µ)Global Avg ]If there is a defect in the row;
（B3）R Max and R is R Min The difference value between [ (1-mu) Global Avg ，(1+µ)Global Avg ]And R is Avg ＜(1-2µ) Global Avg The transition area of the boundary and the background of the behavior strip steel; starting with adjacent rows of the conversion area, and longitudinally extending in the direction of increasing the gray average value to obtain a boundary pseudo-defect area, wherein the gray average value of the adjacent rows is larger than the gray average value of the conversion area, and the longitudinal extending width is 1-3 times of the width of the conversion area;
（B4）R Max and R is R Min The difference value of (2) is not in [ (1- [ mu ] O) Global Avg ，(1+µ)Global Avg ]And R is Avg ≤Global Avg And/10, the behavior strip steel background area;
wherein [ mu ] is a defect threshold coefficient.
3. The method for rapidly screening the quality and automatically extracting the defect characteristics of the surface of the strip steel according to claim 2, wherein the value range of the mu is 20% -30%.
4. The method for rapid quality screening and automatic defect feature extraction on a strip steel surface according to claim 3, wherein the specific operation of step (3) is as follows: and (3) cutting and deleting a boundary pseudo defect region, a conversion region and a background region in the gray matrix diagram according to the judgment result in the step (2), marking rows and columns judged to contain defects in the cut gray matrix diagram, and simultaneously drawing a rectangular frame to form a defect region, wherein the rectangular frame region is a defect characteristic ROI region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911407477.0A CN111062939B (en) | 2019-12-31 | 2019-12-31 | Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911407477.0A CN111062939B (en) | 2019-12-31 | 2019-12-31 | Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062939A CN111062939A (en) | 2020-04-24 |
| CN111062939B true CN111062939B (en) | 2023-08-15 |
Family
ID=70305254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911407477.0A Active CN111062939B (en) | 2019-12-31 | 2019-12-31 | Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062939B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113670941A (en) * | 2021-08-30 | 2021-11-19 | 宝钢湛江钢铁有限公司 | Method for online quantitative evaluation of oxidation color defects on surface of multifunctional continuous annealing strip steel |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288613A (en) * | 2011-05-11 | 2011-12-21 | 北京科技大学 | Surface defect detecting method for fusing grey and depth information |
| CN104568956A (en) * | 2013-10-12 | 2015-04-29 | 上海掌迪自动化科技有限公司 | Machine vision based detection method for strip steel surface defects |
| CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
| CN107369136A (en) * | 2017-06-22 | 2017-11-21 | 福建省万龙新材料科技有限公司 | Composite polycrystal-diamond face crack visible detection method |
| CN108629775A (en) * | 2018-05-14 | 2018-10-09 | 华中科技大学 | A kind of hot high-speed rod surface image processing method |
| CN109358065A (en) * | 2018-10-22 | 2019-02-19 | 湖南拓达结构监测技术有限公司 | A kind of subway tunnel appearance detecting method |
| CN110211101A (en) * | 2019-05-22 | 2019-09-06 | 武汉理工大学 | A kind of rail surface defect rapid detection system and method |
| CN110400285A (en) * | 2019-05-30 | 2019-11-01 | 哈尔滨工业大学（深圳） | Wire bonding pad defect location and classification method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI603074B (en) * | 2015-07-03 | 2017-10-21 | 元智大學 | Optical film defect detection method and system thereof |
-
2019
- 2019-12-31 CN CN201911407477.0A patent/CN111062939B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288613A (en) * | 2011-05-11 | 2011-12-21 | 北京科技大学 | Surface defect detecting method for fusing grey and depth information |
| CN104568956A (en) * | 2013-10-12 | 2015-04-29 | 上海掌迪自动化科技有限公司 | Machine vision based detection method for strip steel surface defects |
| CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
| CN107369136A (en) * | 2017-06-22 | 2017-11-21 | 福建省万龙新材料科技有限公司 | Composite polycrystal-diamond face crack visible detection method |
| CN108629775A (en) * | 2018-05-14 | 2018-10-09 | 华中科技大学 | A kind of hot high-speed rod surface image processing method |
| CN109358065A (en) * | 2018-10-22 | 2019-02-19 | 湖南拓达结构监测技术有限公司 | A kind of subway tunnel appearance detecting method |
| CN110211101A (en) * | 2019-05-22 | 2019-09-06 | 武汉理工大学 | A kind of rail surface defect rapid detection system and method |
| CN110400285A (en) * | 2019-05-30 | 2019-11-01 | 哈尔滨工业大学（深圳） | Wire bonding pad defect location and classification method |
Non-Patent Citations (1)
| Title |
|---|
| 洪奔奔 等.基于特征提取与匹配的带钢缺陷检测.《软件》.2018,第39卷(第09期),31-34. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062939A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
| CN108230324B (en) | Visual detection method for microdefect on surface of magnetic shoe | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| Wang et al. | Research on crack detection algorithm of the concrete bridge based on image processing | |
| CN115082418B (en) | Precise identification method for automobile parts | |
| CN109682839B (en) | Online detection method for surface defects of metal arc-shaped workpiece | |
| CN109115800B (en) | Method for rapidly detecting burrs of product and accurately measuring length | |
| CN115375686B (en) | Glass edge flaw detection method based on image processing | |
| Sharifzadeh et al. | Detection of steel defect using the image processing algorithms | |
| CN113962997B (en) | Strip steel edge crack defect detection method and system based on image processing | |
| CN115684176B (en) | Online visual detection system for film surface defects | |
| CN112697803A (en) | Plate strip steel surface defect detection method and device based on machine vision | |
| CN103983426B (en) | The detection of a kind of defect of optical fiber based on machine vision and sorting technique | |
| CN115100206B (en) | Printing defect identification method for textile with periodic pattern | |
| CN104458764B (en) | Curved uneven surface defect identification method based on large-field-depth stripped image projection | |
| CN108020554A (en) | A kind of steel strip surface defect recognition detection method | |
| CN104568956A (en) | Machine vision based detection method for strip steel surface defects | |
| CN115690387A (en) | Alloy surface detection system based on image recognition | |
| CN116228651A (en) | Cloth defect detection method, system, equipment and medium | |
| CN111062939B (en) | Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics | |
| US6232617B1 (en) | Apparatus for detecting surface defects on running metal strip | |
| Tang et al. | Surface inspection system of steel strip based on machine vision | |
| Hashmi et al. | Computer-vision based visual inspection and crack detection of railroad tracks | |
| CN110516725B (en) | Machine vision-based wood board stripe spacing and color detection method | |
| Hu et al. | Heavy rail surface defects detection based on the morphology of multi-scale and dual-structure elements |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |