CN108896577A - A kind of automatic testing method of brake block profile defects - Google Patents
A kind of automatic testing method of brake block profile defects Download PDFInfo
- Publication number
- CN108896577A CN108896577A CN201810535607.8A CN201810535607A CN108896577A CN 108896577 A CN108896577 A CN 108896577A CN 201810535607 A CN201810535607 A CN 201810535607A CN 108896577 A CN108896577 A CN 108896577A
- Authority
- CN
- China
- Prior art keywords
- image
- operator
- brake block
- template
- testing 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of automatic testing method of brake block profile defects, transmission module is placed on the brake block onwards transmission of transmission belt surface by artificial loading mode, controls conveyer belt rotation by the signal close to switch.Described image acquisition module passes through program triggering collection brake block contour images.Described image processing module mainly uses Human computer interface to embed HALCON function library, carries out processing and result judgement to each collected picture and then carries out substandard product rejecting by sorting mechanism.The present invention is based on the brake block profile defects detection methods of HALCON, and brake picture to be detected can be made quick and precisely to complete to be aligned, and improves brake block detection efficiency by roughing and selected mode.
Description
Technical field
The present invention relates to a kind of automatic testing methods of brake block profile defects, belong to automatic measurement technique field.
Background technique
Currently, automobile brake perfrmance is to guarantee one of most important performance of traffic safety.Brake block in braking system is but
There is mass defects, and the event of automotive safety hidden danger is brought to happen occasionally.
Whether brake block has defect as key part, profile, is one of most important instruction of quality of production detection,
How to realize that quickly automatic detection is that technical problems to be solved are badly in need of in each cart enterprise.
HALCON is a extremely powerful machine vision processing software, wherein covering image comprising more than 1000 operators
Acquisition, dimensional measurement, template matching, optical character identification, edge detection, Blob analysis etc..By HALCON and brake block wheel
Wide defects detection process combines, and is strategic structural place of the invention.
Summary of the invention
Purpose:In order to overcome the deficiencies in the prior art, the present invention provides a kind of the automatic of brake block profile defects
Detection method.
Technical solution:In order to solve the above technical problems, the technical solution adopted by the present invention is:
A kind of automatic testing method of brake block profile defects, includes the following steps:
Step 1:Image Acquisition;
Step 2:Camera calibration;
Step 3:Create matching template;
Step 4:Image preprocessing;
Step 5:Template matching;
Step 6:Difference shadow method detection.
Preferably, the step 1 includes the following steps:
1-1:HLACON props up various image pick-up cards and industrial camera by image acquisition interface
It holds;
1-2:Image capture device is opened by open_framegrabber operator, obtains equipment handle;
1-3:Image is obtained by grab_image operator.
Preferably, the step 2 includes the following steps:Scaling board is shot by the calibration assistant of HALCON more
It opens each angle shot to be demarcated, or is demarcated by code load with the image of scaling board, obtained after the completion of calibration
Camera inside and outside parameter.
Preferably, the step 3 includes the following steps:
3-1:Using collected qualified brake block contour images, ROI division is carried out, carries out image using threshold operator
Global threshold segmentation;
3-2:XLD profile is created according to the region of segmentation using gen_contour_region_xld operator;
3-3:It is that following fast Template Matching creates a matching template using creat_shape_model_xld operator.
Preferably, the step 4 includes the following steps:
4-1:Obtain the camera internal parameter that calibration generates;
4-2:Correction parameter is obtained using change_radial_distortion_points operator;
4-3:Distorted image is corrected by change_radial_distortion_image operator, the image after being corrected.
Preferably, the step 5 includes the following steps:
5-1:Brake picture to be detected is obtained by grab_image operator;
5-2:The profile transverse and longitudinal coordinate, angle and the similarity that search in object are obtained by find_shape_model operator;
5-3:The profile coordinate searched and template are calculated in terms of point and angle by vector_angle_to_rigid operator
The affine transformation matrix of coordinate, will be to using the affine transformation matrix obtained using affine_trans_contour_xld operator
Detection image is aligned with template;
5-4:Similarity threshold is set, the profile that similarity is less than threshold value is directly rejected.
Preferably, the step 6 includes the following steps:
6-1:It is poor between image comparison setting picture to be measured and transformation model by prepare_variation_model operator
The threshold value of different minimal gray grade and transformation model grey scale change, prepares for image comparison;
6-2:When detection, brake block profile is found in image to be detected using find_shape_model operator, by return
Coordinate and template coordinate carry out affine transformation, so that image to be detected is aligned with template;
6-3:Image to be detected and trained transformation model are subjected to poor shadow by compare_variation_model operator
Method compares, and obtains defect area;
6-4:By connection operator, connected domain is obtained, number is demarcated by the defect area size of examination criteria defined
According to threshold value is used as after conversion, the defect of threshold value is greater than by select_shape operator selection region, and utilize area_
The area and centre coordinate of center_gray operator acquisition defect.
Beneficial effect:A kind of automatic testing method of brake block profile defects provided by the invention, the brake based on HALCON
Vehicle piece profile defects detection method can make brake picture to be detected quick and precisely complete to be aligned, and pass through roughing and selected
Mode improve brake block detection efficiency.
Detailed description of the invention
Fig. 1 is hardware system structure schematic diagram of the invention;
Fig. 2 is detection method flow chart of the invention.
Specific embodiment
The present invention will be further explained with reference to the accompanying drawing.
As shown in Figure 1, a kind of automatic checkout system of brake block profile defects, including:Transmission module, Image Acquisition mould
Block, image processing module.The transmission module is placed on the brake block onwards transmission of transmission belt surface by artificial loading mode,
Conveyer belt rotation is controlled by the signal close to switch.Described image acquisition module passes through program triggering collection brake block profile diagram
Picture.Described image processing module mainly uses Human computer interface to embed HALCON function library, carries out to each collected picture
Processing and result judgement pass through sorting mechanism in turn and carry out substandard product rejecting.
As shown in Fig. 2, a kind of automatic testing method of brake block profile defects, includes the following steps:
Step 1:Image Acquisition;HLACON is by image acquisition interface to various image pick-up cards and work
Industry camera is supported.Image capture device is opened by open_framegrabber operator, obtains equipment handle.Pass through
Grab_image operator obtains image.
Step 2:Camera calibration;Multiple each angle shots are shot to scaling board by the calibration assistant of HALCON to mark
It is fixed, or demarcated by code load with the image of scaling board, camera inside and outside parameter is obtained after the completion of calibration.
Step 3:Create matching template;Due to being using based on shape(shape-based)Template matching is to be detected
Image carries out rapid alignment, so according to qualified brake block profile drawing template establishment.Utilize collected qualified brake block profile diagram
Picture carries out ROI division, carries out image overall Threshold segmentation using threshold operator, and then utilize gen_contour_
Region_xld operator creates XLD according to the region of segmentation(eXtended Line Descriptions)Profile, followed by
Creat_shape_model_xld operator is that following fast Template Matching creates a matching template.
Step 4:Image preprocessing;
4-1:Image quality is not considered, only by area-of-interest protrusion or decaying, such as mean filter, removal noise;
4-2:The reason of for image deterioration, tries to compensate degraded factor, so that picture is approached original image, for example, passing through calibration
Obtained camera inside and outside parameter correction fault image.
It needs to measure flaw size herein, pattern distortion can have an adverse effect to measurement accuracy, need to figure
Image distortion is corrected.The camera internal parameter that calibration generates is obtained, change_radial_distortion_points is utilized
Operator obtains correction parameter, corrects distorted image by change_radial_distortion_image operator, obtains school
Image after just.
Step 5:Template matching;Brake picture to be detected is obtained by grab_image operator, passes through find_shape_
Model operator obtains profile transverse and longitudinal coordinate, angle and the similarity searched in object.Pass through vector_angle_to_
Rigid operator calculates the affine transformation matrix of the profile coordinate and template coordinate that search in terms of point and angle, utilizes
Image to be detected is aligned by affine_trans_contour_xld operator using the affine transformation matrix obtained with template.Setting
Similarity threshold directly rejects the profile that similarity is less than threshold value, reduces later period difference shadow method and detects workload, improves detection effect
Rate.
Step 6:Difference shadow method detection:It is that image comparison is arranged to mapping by prepare_variation_model operator
The threshold value of the minimal gray grade of difference and transformation model grey scale change between piece and transformation model does standard for image comparison
It is standby.When detection, brake block profile is found in image to be detected using find_shape_model operator, by the coordinate of return with
Template coordinate carries out affine transformation and then passes through compare_variation_model so that image to be detected is aligned with template
Image to be detected compared with trained transformation model carries out difference shadow method, is obtained defect area by operator.Pass through connection
Operator obtains connected domain, by being used as threshold value after the defect area size nominal data conversion of examination criteria defined, passes through
Select_shape operator selection region is greater than the defect of threshold value, and the face of defect is obtained using area_center_gray operator
Long-pending and centre coordinate.
The above is only a preferred embodiment of the present invention, it should be pointed out that:For the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (7)
1. a kind of automatic testing method of brake block profile defects, it is characterised in that:Include the following steps:
Step 1:Image Acquisition;
Step 2:Camera calibration;
Step 3:Create matching template;
Step 4:Image preprocessing;
Step 5:Template matching;
Step 6:Difference shadow method detection.
2. a kind of automatic testing method of brake block profile defects according to claim 1, it is characterised in that:The step
1 includes the following steps:
1-1:HLACON props up various image pick-up cards and industrial camera by image acquisition interface
It holds;
1-2:Image capture device is opened by open_framegrabber operator, obtains equipment handle;
1-3:Image is obtained by grab_image operator.
3. a kind of automatic testing method of brake block profile defects according to claim 1, it is characterised in that:The step
2 include the following steps:Multiple each angle shots are shot to scaling board by the calibration assistant of HALCON to demarcate, or are passed through
Code load is demarcated with the image of scaling board, and camera inside and outside parameter is obtained after the completion of calibration.
4. a kind of automatic testing method of brake block profile defects according to claim 1, it is characterised in that:The step
3 include the following steps:
3-1:Using collected qualified brake block contour images, ROI division is carried out, carries out image using threshold operator
Global threshold segmentation;
3-2:XLD profile is created according to the region of segmentation using gen_contour_region_xld operator;
3-3:It is that following fast Template Matching creates a matching template using creat_shape_model_xld operator.
5. a kind of automatic testing method of brake block profile defects according to claim 1, it is characterised in that:The step
4 include the following steps:
4-1:Obtain the camera internal parameter that calibration generates;
4-2:Correction parameter is obtained using change_radial_distortion_points operator;
4-3:Distorted image is corrected by change_radial_distortion_image operator, the image after being corrected.
6. a kind of automatic testing method of brake block profile defects according to claim 1, it is characterised in that:The step
5 include the following steps:
5-1:Brake picture to be detected is obtained by grab_image operator;
5-2:The profile transverse and longitudinal coordinate, angle and the similarity that search in object are obtained by find_shape_model operator;
5-3:The profile coordinate searched and template are calculated in terms of point and angle by vector_angle_to_rigid operator
The affine transformation matrix of coordinate, will be to using the affine transformation matrix obtained using affine_trans_contour_xld operator
Detection image is aligned with template;
5-4:Similarity threshold is set, the profile that similarity is less than threshold value is directly rejected.
7. a kind of automatic testing method of brake block profile defects according to claim 1, it is characterised in that:The step
6 include the following steps:
6-1:It is poor between image comparison setting picture to be measured and transformation model by prepare_variation_model operator
The threshold value of different minimal gray grade and transformation model grey scale change, prepares for image comparison;
6-2:When detection, brake block profile is found in image to be detected using find_shape_model operator, by return
Coordinate and template coordinate carry out affine transformation, so that image to be detected is aligned with template;
6-3:Image to be detected and trained transformation model are subjected to poor shadow by compare_variation_model operator
Method compares, and obtains defect area;
6-4:By connection operator, connected domain is obtained, number is demarcated by the defect area size of examination criteria defined
According to threshold value is used as after conversion, the defect of threshold value is greater than by select_shape operator selection region, and utilize area_
The area and centre coordinate of center_gray operator acquisition defect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810535607.8A CN108896577A (en) | 2018-05-30 | 2018-05-30 | A kind of automatic testing method of brake block profile defects |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810535607.8A CN108896577A (en) | 2018-05-30 | 2018-05-30 | A kind of automatic testing method of brake block profile defects |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108896577A true CN108896577A (en) | 2018-11-27 |
Family
ID=64343520
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810535607.8A Pending CN108896577A (en) | 2018-05-30 | 2018-05-30 | A kind of automatic testing method of brake block profile defects |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108896577A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109712115A (en) * | 2018-12-03 | 2019-05-03 | 武汉精立电子技术有限公司 | A kind of pcb board automatic testing method and system |
CN109859186A (en) * | 2019-01-31 | 2019-06-07 | 江苏理工学院 | A kind of lithium battery mould group positive and negative anodes detection method based on halcon |
CN110136123A (en) * | 2019-05-17 | 2019-08-16 | 无锡睿勤科技有限公司 | Article detection method, mobile terminal and computer readable storage medium |
CN110930359A (en) * | 2019-10-21 | 2020-03-27 | 浙江科技学院 | Method and system for detecting automobile shifting fork |
CN111340806A (en) * | 2019-12-20 | 2020-06-26 | 长春工业大学 | Brake disc detection method based on Halcon algorithm |
CN111462054A (en) * | 2020-03-18 | 2020-07-28 | 广州大学 | Dispensing quality detection method |
CN113504239A (en) * | 2021-06-10 | 2021-10-15 | 上海西信信息科技股份有限公司 | Quality control data analysis method |
CN113838039A (en) * | 2021-09-29 | 2021-12-24 | 逸美德科技股份有限公司 | Detection method capable of realizing multiple geometric measurement characteristics |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006300663A (en) * | 2005-04-19 | 2006-11-02 | Asahi Glass Co Ltd | Defect detection system |
CN106548173A (en) * | 2016-11-24 | 2017-03-29 | 国网山东省电力公司电力科学研究院 | A kind of improvement no-manned plane three-dimensional information getting method based on classification matching strategy |
CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
CN105678768B (en) * | 2016-01-08 | 2018-11-02 | 杭州电子科技大学 | A kind of tyre surface detection method based on machine vision |
-
2018
- 2018-05-30 CN CN201810535607.8A patent/CN108896577A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006300663A (en) * | 2005-04-19 | 2006-11-02 | Asahi Glass Co Ltd | Defect detection system |
CN105678768B (en) * | 2016-01-08 | 2018-11-02 | 杭州电子科技大学 | A kind of tyre surface detection method based on machine vision |
CN106548173A (en) * | 2016-11-24 | 2017-03-29 | 国网山东省电力公司电力科学研究院 | A kind of improvement no-manned plane three-dimensional information getting method based on classification matching strategy |
CN106548173B (en) * | 2016-11-24 | 2019-04-09 | 国网山东省电力公司电力科学研究院 | A kind of improvement no-manned plane three-dimensional information acquisition method based on classification matching strategy |
CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
Non-Patent Citations (1)
Title |
---|
曾强等: "基于HALCON 的刹车片轮廓缺陷检测方法研究", 《煤矿机械》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109712115A (en) * | 2018-12-03 | 2019-05-03 | 武汉精立电子技术有限公司 | A kind of pcb board automatic testing method and system |
CN109712115B (en) * | 2018-12-03 | 2021-11-23 | 武汉精立电子技术有限公司 | Automatic PCB detection method and system |
CN109859186A (en) * | 2019-01-31 | 2019-06-07 | 江苏理工学院 | A kind of lithium battery mould group positive and negative anodes detection method based on halcon |
CN110136123A (en) * | 2019-05-17 | 2019-08-16 | 无锡睿勤科技有限公司 | Article detection method, mobile terminal and computer readable storage medium |
CN110930359A (en) * | 2019-10-21 | 2020-03-27 | 浙江科技学院 | Method and system for detecting automobile shifting fork |
CN111340806A (en) * | 2019-12-20 | 2020-06-26 | 长春工业大学 | Brake disc detection method based on Halcon algorithm |
CN111462054A (en) * | 2020-03-18 | 2020-07-28 | 广州大学 | Dispensing quality detection method |
CN111462054B (en) * | 2020-03-18 | 2023-04-07 | 广州大学 | Dispensing quality detection method |
CN113504239A (en) * | 2021-06-10 | 2021-10-15 | 上海西信信息科技股份有限公司 | Quality control data analysis method |
CN113838039A (en) * | 2021-09-29 | 2021-12-24 | 逸美德科技股份有限公司 | Detection method capable of realizing multiple geometric measurement characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108896577A (en) | A kind of automatic testing method of brake block profile defects | |
CN111292305B (en) | Improved YOLO-V3 metal processing surface defect detection method | |
CN108520274B (en) | High-reflectivity surface defect detection method based on image processing and neural network classification | |
CN105069790B (en) | A kind of gear open defect fast image detection method | |
CN105548185B (en) | The recognition methods of automotive hub screw hole, covering method and system based on machine vision | |
CN101995223B (en) | Chip appearance detection method and system | |
CN104680519B (en) | Seven-piece puzzle recognition methods based on profile and color | |
CN113221889B (en) | Chip character anti-interference recognition method and device | |
CN108257171A (en) | Car radar assembling aperture detection method based on light vision | |
CN109801267A (en) | Inspection target defect detection method based on characteristic point detection and SVM classifier | |
CN112132828A (en) | Film flaw detection method based on deep learning | |
CN114049624B (en) | Ship cabin intelligent detection method and system based on machine vision | |
CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
CN109358067A (en) | Motor ring varistor defect detecting system based on computer vision and method | |
WO2024002187A1 (en) | Defect detection method, defect detection device, and storage medium | |
CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
CN116612106A (en) | Method for detecting surface defects of optical element based on YOLOX algorithm | |
CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
Fu et al. | Medicine glass bottle defect detection based on machine vision | |
CN116678826A (en) | Appearance defect detection system and method based on rapid three-dimensional reconstruction | |
CN113487570B (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
CN110705553A (en) | Scratch detection method suitable for vehicle distant view image | |
CN112329845B (en) | Method and device for changing paper money, terminal equipment and computer readable storage medium | |
CN113191239A (en) | Vehicle overall dimension dynamic detection system based on computer vision | |
CN114494103A (en) | Defect detection method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |