CN107084666B - Comprehensive detection method for size of brake pad based on machine vision - Google Patents
Comprehensive detection method for size of brake pad based on machine vision Download PDFInfo
- Publication number
- CN107084666B CN107084666B CN201710332039.7A CN201710332039A CN107084666B CN 107084666 B CN107084666 B CN 107084666B CN 201710332039 A CN201710332039 A CN 201710332039A CN 107084666 B CN107084666 B CN 107084666B
- Authority
- CN
- China
- Prior art keywords
- image
- brake pad
- size
- standard template
- machine vision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/028—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring lateral position of a boundary of the object
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a brake pad size comprehensive detection method based on machine vision, which comprises the following steps of designing a brake pad size tolerance band diagram as a standard template diagram according to a size tolerance principle and a brake pad drawing. And secondly, a machine vision system collects the brake block image to be detected, and filtering, binarization processing, edge detection and image scaling are carried out to obtain the pixel size standard which is the same as the standard template image. Thirdly, carrying out Hough transformation on the zoomed images to obtain two circle center coordinates to determine a rotation angle so that the brake pad to be detected in the images is in a horizontal state, simultaneously carrying out Hough transformation on the standard template drawing to obtain two circle center coordinates, taking the midpoint of the connecting line of the circle center coordinates of the two drawings as an intercepting center, intercepting the two images with the same size, carrying out addition operation, counting the number of white pixels, and comparing the number of the white pixels with the number of the white pixels of the standard template drawing to obtain a detection result. The invention has the advantages of high detection speed and high precision, and can detect all sizes to be detected of the brake pad.
Description
Technical Field
The invention belongs to the field of brake pad detection, and particularly relates to a brake pad size comprehensive detection method based on machine vision.
Background
In the braking system of an automobile, a brake pad is the most critical safety part, the quality of all braking effects plays a decisive role, the quality of the brake pad directly influences the life and property safety of a driver, and whether the size of the brake pad is qualified is one of important factors for evaluating the quality of the brake pad. It is particularly important to detect the respective dimensions of the brake pad.
At present, the size detection method of the brake pad mainly comprises a manual detection method and an image processing detection method. The manual detection method mainly depends on dimension measurement instruments such as a vernier caliper, a micrometer and the like to measure the dimension, and in recent years, with the rapid development of computer science and digital image processing technology, the general image processing is also used for detecting the dimension of the brake pad.
The general manual detection has low efficiency, the detection result is greatly influenced by human, the precision is low, the method is not suitable for the development of the modern technology, but the general image processing detection size is limited, and the general image processing method can only detect partial sizes of an object to be detected, such as the maximum length and width and the diameter of a circle, and cannot detect whether the sizes of other curves or arcs and the like are qualified or not.
Disclosure of Invention
The invention provides a comprehensive detection method for the size of a brake pad based on machine vision, aiming at the problems in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: the method comprises the following steps of 1) designing a brake pad size tolerance band diagram as a standard template diagram according to a size tolerance principle and a brake pad drawing; 2) a machine vision system collects an image of a brake pad to be detected, and the image is filtered, binarized, edge detected and zoomed to obtain a pixel size standard which is the same as that of a standard template image; 3) and carrying out Hough transformation on the zoomed image to obtain two circle center coordinates, determining a rotation angle so that the brake pad to be detected in the image is in a horizontal state, simultaneously carrying out Hough transformation on the standard template drawing to obtain two circle center coordinates, taking the midpoint of the connecting line of the circle center coordinates of the two drawings as an intercepting center, intercepting the two images with the same size, carrying out addition operation, and counting the number of white pixels and the number of white pixels of the standard template drawing to compare so as to obtain a detection result.
According to the technical scheme, in the step 1), the principle of dimensional tolerance mainly comprises the principle of limit size of holes and shafts and the principle of allowable variation of linear size.
According to the technical scheme, in the step 1), the drawing of the brake pad is provided by a brake pad manufacturer, and the design of the dimensional tolerance band diagram of the brake pad is designed by CAD drawing software and stored in a bmp image format as a standard template diagram.
According to the technical scheme, in the step 2), the machine vision system specifically comprises a CCD high-resolution gigabit network camera, a lens, an annular light source and a computer.
According to the above technical solution, in the step 2), the binarization processing specifically includes that an original image f (x, y) is determined to find a proper gray value in f (x, y) as a threshold t by OTSU threshold segmentation, and then the segmented image is:
according to the technical scheme, in the step 2), the edge detection is realized by using a robert edge detection operator.
According to the technical scheme, in the step 2), the image scaling is performed by determining the scaling factor by using a minimum circumscribed rectangle algorithm, the binary image and the standard image are subjected to minimum circumscribed rectangles to obtain the length and width characteristics of the two minimum circumscribed rectangles, the length and width difference between the binary image and the standard image is obtained to determine the scaling factor of the binary image, and the binary image is scaled, so that the pixel size standard identical to that of the standard template image is obtained.
According to the technical scheme, in the step 3), the zoomed image is subjected to Hough transformation to obtain two circle center coordinates, the rotation angle is determined, so that the rotation angle of the brake pad to be detected in the image is in a horizontal state, the rotation angle is determined by utilizing the difference between the horizontal coordinates of the two circle centers, and the horizontal coordinates of the two circle centers are equal after the image is rotated.
The invention has the following beneficial effects: the invention fully considers the limitations of manual and general image processing methods for detecting the size of the brake pad, provides a comprehensive detection method for the size of the brake pad based on machine vision, effectively realizes the detection of the size of the brake pad with rapider speed and higher precision, and can detect whether all sizes to be detected are qualified or not.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a schematic flow chart of a comprehensive detection method for the size of a brake pad according to an embodiment of the invention;
FIG. 2 is a diagram of a tolerance band of brake pad dimensions (standard template) in an embodiment of the present invention;
FIG. 3 is an image after edge detection in an embodiment of the invention;
FIG. 4 is a diagram of a qualified brake pad image detection result in an embodiment of the present invention;
FIG. 5 is a diagram of the result of the defective brake pad image detection in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a brake pad size comprehensive detection method based on machine vision, which comprises the following steps of 1) designing a brake pad size tolerance band diagram as a standard template diagram according to a size tolerance principle and a brake pad drawing; 2) a machine vision system collects an image of a brake pad to be detected, and the image is filtered, binarized, edge detected and zoomed to obtain a pixel size standard which is the same as that of a standard template image; 3) and carrying out Hough transformation on the zoomed image to obtain two circle center coordinates, determining a rotation angle so that the brake pad to be detected in the image is in a horizontal state, simultaneously carrying out Hough transformation on the standard template drawing to obtain two circle center coordinates, taking the midpoint of the connecting line of the circle center coordinates of the two drawings as an intercepting center, intercepting the two images with the same size, carrying out addition operation, and counting the number of white pixels and the number of white pixels of the standard template drawing to compare so as to obtain a detection result.
In the step 1), the principle of dimensional tolerance mainly comprises the principle of limit size of the hole and the shaft and the principle of allowable variation of linear size.
Further, in the step 1), the drawing of the brake pad is provided by a brake pad manufacturer, and the design of the dimensional tolerance band diagram of the brake pad is designed by CAD drawing software and stored in a bmp image format as a standard template diagram.
In the step 2), the machine vision system specifically comprises a CCD high-resolution gigabit network camera, a lens, an annular light source and a computer.
Further, in the step 2), the binarization processing specifically includes that, if the original image f (x, y) finds a suitable gray value in f (x, y) by OTSU threshold segmentation as the threshold t, the segmented image is:
further, in the step 2), the edge detection is implemented by using a robert edge detection operator.
Further, in the step 2), the image scaling is performed by determining the scaling factor by using a minimum circumscribed rectangle algorithm, the binary image and the standard image are subjected to minimum circumscribed rectangles to obtain the length and width characteristics of two minimum circumscribed rectangles, and the length and width differences of the two minimum circumscribed rectangles are obtained to determine the scaling factor of the binary image and perform scaling, so that the binary image obtains the same pixel size standard as the standard template image.
In the step 3), after the image is zoomed, hough transformation is carried out on the image to obtain two circle center coordinates to determine a rotation angle, so that the rotation angle is determined by using the difference between the horizontal coordinates of the two circle centers when the brake pad to be detected in the image is in a horizontal state, and the horizontal coordinates of the two circle centers are equal after the image is rotated.
In a preferred embodiment of the present invention, as shown in fig. 1, a dimension tolerance band diagram of a brake pad is first designed by using CAD drawing software according to the dimension tolerance principle and a brake pad drawing provided by a brake pad manufacturer and stored in a bmp image format as a standard template drawing, and fig. 2 is a dimension tolerance band (standard template) drawing of a brake pad in an embodiment of the present invention.
Secondly, a CCD high-resolution gigabit network camera in a machine vision system is utilized to collect a picture of a brake pad to be detected, filtering, binarization processing, edge detection and image scaling processing are carried out, the process is that firstly, filtering and binarization processing are carried out, an original image f (x, y) is set, an appropriate gray value is found in f (x, y) by utilizing OTSU threshold segmentation as a threshold value t, and then the segmented image is as follows:
in this embodiment, the threshold t is preferably 60.
And (3) obtaining a binary image, and performing robert edge detection to obtain an edge contour map, wherein fig. 3 is the image after the edge detection in the embodiment of the invention.
And simultaneously, the binary image and the standard template image obtain the length and width characteristics of the minimum circumscribed rectangle by using a minimum circumscribed rectangle algorithm, the ratio of the length of the two images to the width of the two images determines the zoom multiple of the binary image, the binary image is zoomed, and simultaneously, the edge images are zoomed by the same multiple, so that the pixel size standard which is the same as that of the standard template image is obtained.
Finally, after the two figures are in a unified pixel standard, the edge figure is subjected to Hough transform to obtain coordinates of two circle centers, the difference of the horizontal coordinates of the two circle centers determines the rotation angle, the horizontal coordinates of the two circle centers after rotation are the same, meanwhile, the standard template figure is also subjected to Hough transform to obtain coordinates of the two circle centers, then two images with the same size are intercepted by taking the middle point of the connecting line of the coordinates of the circle centers of the two figures as an intercepting center, and the number of white pixel points is counted by addition operation, the number of the white pixel points of the acquired added images is compared with the number of the white pixel points of the standard template figure, if the two images are equal, namely the white pixel points of the edge figure are all located in the white pixel points of the standard template figure, the brake pad; if the two are not equal, namely the white pixel points of the edge map are not all located in the white pixel points of the standard template map, the size of the brake pad to be detected is unqualified, for example, fig. 5 is a detection result map of an unqualified brake pad image in the embodiment of the invention, and the detection is finished. The brake pad size comprehensive detection method based on machine vision realizes the detection of the brake pad size more quickly and with higher precision, and can detect whether all sizes to be detected are qualified or not.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined by the appended claims.
Claims (4)
1. A brake pad size comprehensive detection method based on machine vision is characterized by comprising the following steps of 1) designing a brake pad size tolerance band diagram as a standard template diagram according to a size tolerance principle and a brake pad drawing; 2) a machine vision system collects an image of a brake pad to be detected, and the image is filtered, binarized, edge detected and zoomed to obtain a pixel size standard which is the same as that of a standard template image; 3) carrying out Hough transformation on the zoomed image to obtain two circle center coordinates, determining a rotation angle so that the brake pad to be detected in the image is in a horizontal state, simultaneously carrying out Hough transformation on the standard template drawing to obtain two circle center coordinates, taking the midpoint of the connecting line of the circle center coordinates of the two drawings as an intercepting center, intercepting the two images with the same size, carrying out addition operation, counting the number of white pixels, and comparing the number of the white pixels with the number of the white pixels of the standard template drawing to obtain a detection result;
in the step 1), the principle of dimensional tolerance mainly comprises the principle of limit size of holes and shafts and the principle of allowable variation of linear size;
in the step 1), a brake pad drawing is provided by a brake pad manufacturer, and a design brake pad size tolerance band diagram is designed by CAD drawing software and stored in a bmp image format as a standard template diagram;
in the step 2), the image zooming is to determine the zooming multiple by using a minimum circumscribed rectangle algorithm, the binary image and the standard image are subjected to minimum circumscribed rectangles to obtain the length and width characteristics of the two minimum circumscribed rectangles, the length and width difference between the two is obtained to determine the zooming multiple of the binary image and zoom, so that the binary image obtains the pixel size standard which is the same as that of the standard template image;
in the step 3), after the image is zoomed, Hough transformation is carried out on the image to obtain two circle center coordinates to determine a rotation angle, so that the rotation angle is determined by utilizing the difference between the horizontal coordinates of the two circle centers when the brake pad to be detected in the image is in a horizontal state, and the horizontal coordinates of the two circle centers are equal after the image is rotated.
2. The comprehensive detection method for the dimension of the brake pad based on the machine vision is characterized in that in the step 2), the machine vision system specifically comprises a CCD high-resolution gigabit-capable camera, a lens, an annular light source and a computer.
3. The method for comprehensively detecting the size of the brake pad based on machine vision according to claim 1, wherein in the step 2), the binarization processing specifically includes that if an original image f (x, y) finds a proper gray value in f (x, y) by OTSU threshold segmentation as a threshold t, the segmented image is:
4. the integrated machine-vision-based brake pad size detection method according to claim 1, wherein in the step 2), the edge detection is implemented by using a robert edge detection operator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710332039.7A CN107084666B (en) | 2017-05-10 | 2017-05-10 | Comprehensive detection method for size of brake pad based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710332039.7A CN107084666B (en) | 2017-05-10 | 2017-05-10 | Comprehensive detection method for size of brake pad based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107084666A CN107084666A (en) | 2017-08-22 |
| CN107084666B true CN107084666B (en) | 2020-08-28 |
Family
ID=59613072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710332039.7A Active CN107084666B (en) | 2017-05-10 | 2017-05-10 | Comprehensive detection method for size of brake pad based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107084666B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN108287250A (en) * | 2018-02-01 | 2018-07-17 | 中国计量大学 | Escalator step speed-measuring method based on machine vision |
| CN108662977A (en) * | 2018-03-14 | 2018-10-16 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
| CN108460776B (en) * | 2018-04-12 | 2022-03-25 | 广东工业大学 | Brake pad size detection method and device based on machine vision |
| CN109099818A (en) * | 2018-06-27 | 2018-12-28 | 武汉理工大学 | Portable micron order high definition range-measurement system |
| CN109174674A (en) * | 2018-07-26 | 2019-01-11 | 昆山睿力得软件技术有限公司 | A kind of detection device for automotive brake pads |
| CN109087292B (en) * | 2018-07-27 | 2022-03-11 | 广东工业大学 | Thermal transfer film glue deviation detection method based on machine vision |
| CN109211110A (en) * | 2018-09-18 | 2019-01-15 | 佛山科学技术学院 | A kind of flat-type workpiece size detection system and method based on machine vision |
| CN110008955B (en) * | 2019-04-01 | 2020-12-15 | 中国计量大学 | Method for testing character imprinting quality of surface of automobile brake pad |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000161921A (en) * | 1998-12-01 | 2000-06-16 | Dainippon Printing Co Ltd | Dimension measuring device |
| CN103914827A (en) * | 2013-09-06 | 2014-07-09 | 贵州大学 | Method for visual inspection of shortages of automobile sealing strip profile |
| CN104711784A (en) * | 2015-04-01 | 2015-06-17 | 华中科技大学 | Method for obtaining sewing path of cut pieces |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751572A (en) * | 2008-12-05 | 2010-06-23 | 比亚迪股份有限公司 | Pattern detection method, device, equipment and system |
| CN104298993B (en) * | 2014-01-09 | 2018-11-09 | 郑州金惠计算机***工程有限公司 | A kind of bar number positioning and recognition methods suitable under complex scene along track |
| CN103793712B (en) * | 2014-02-19 | 2017-02-08 | 华中科技大学 | Image recognition method and system based on edge geometric features |
| CN105381961A (en) * | 2015-12-23 | 2016-03-09 | 胡琳丽 | Comprehensive detection device for brake blocks |
| CN106568385B (en) * | 2016-01-29 | 2018-12-07 | 中国计量学院 | A kind of automotive brake pads dimensional machines vision automatic measurement system based on double camera |
-
2017
- 2017-05-10 CN CN201710332039.7A patent/CN107084666B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000161921A (en) * | 1998-12-01 | 2000-06-16 | Dainippon Printing Co Ltd | Dimension measuring device |
| CN103914827A (en) * | 2013-09-06 | 2014-07-09 | 贵州大学 | Method for visual inspection of shortages of automobile sealing strip profile |
| CN104711784A (en) * | 2015-04-01 | 2015-06-17 | 华中科技大学 | Method for obtaining sewing path of cut pieces |
Non-Patent Citations (1)
| Title |
|---|
| 《Precision size measurement instrument for irregular objects》;Wanji Liu 等;《2015 International Conference on Advanced Mechatronic Systems》;20151005;第513-518页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107084666A (en) | 2017-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107084666B (en) | Comprehensive detection method for size of brake pad based on machine vision | |
| CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
| CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
| CN108364311B (en) | Automatic positioning method for metal part and terminal equipment | |
| CN115861291B (en) | Chip circuit board production defect detection method based on machine vision | |
| CN117351008A (en) | Smart phone panel surface defect detection method | |
| CN107367241B (en) | Automobile tire pattern recognition method based on machine vision | |
| CN108088381B (en) | Non-contact type micro gap width measuring method based on image processing | |
| CN110544231B (en) | Lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| CN109378279B (en) | Wafer detection method and wafer detection system | |
| JP2009259036A (en) | Image processing device, image processing method, image processing program, recording medium, and image processing system | |
| CN108037142B (en) | Mask optical defect detection method based on image gray value | |
| CN108918093B (en) | Optical filter mirror surface defect detection method and device and terminal equipment | |
| CN112001917A (en) | Machine vision-based geometric tolerance detection method for circular perforated part | |
| CN114279357A (en) | Die casting burr size measurement method and system based on machine vision | |
| CN115375629A (en) | Method for detecting line defect and extracting defect information in LCD screen | |
| CN116128873A (en) | Bearing retainer detection method, device and medium based on image recognition | |
| CN113066088A (en) | Detection method, detection device and storage medium in industrial detection | |
| CN114897881A (en) | Crystal grain defect detection method based on edge characteristics | |
| JP2011007728A (en) | Method, apparatus and program for defect detection | |
| CN114693651A (en) | Rubber ring flow mark detection method and device based on image processing | |
| CN114485433A (en) | Three-dimensional measurement system, method and device based on pseudo-random speckles | |
| CN116563298B (en) | Cross line center sub-pixel detection method based on Gaussian fitting | |
| CN113129260A (en) | Automatic detection method and device for internal defects of lithium battery cell |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Zhiling Inventor after: Hu Linli Inventor before: Hu Linli Inventor before: Xu Zhiling |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |