CN108279241A - A kind of workpiece configurations detection method based on machine vision - Google Patents
A kind of workpiece configurations detection method based on machine vision Download PDFInfo
- Publication number
- CN108279241A CN108279241A CN201810072125.3A CN201810072125A CN108279241A CN 108279241 A CN108279241 A CN 108279241A CN 201810072125 A CN201810072125 A CN 201810072125A CN 108279241 A CN108279241 A CN 108279241A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- image
- detected
- template
- edge
- 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
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 Analysis (AREA)
- Image Processing (AREA)
Abstract
The workpiece configurations detection method based on machine vision that the present invention relates to a kind of whether there is defect for detecting the workpiece configurations produced, the method includes：Establish the edge-detected image template of workpiece；Workpiece image to be detected is acquired, and initialization process is carried out to the workpiece image to be detected after acquisition；By edge-detected image template, workpiece image to be detected carries out bianry image morphology operations with treated, judges that workpiece configurations whether there is defect according to operation result.Compared with prior art, the present invention has many advantages, such as to detect automatically, be easy to implement and detection efficiency is high.
Description
Technical field
The present invention relates to workpiece sensing fields, more particularly, to a kind of workpiece configurations detection method based on machine vision.
Background technology
Workpiece, as manufacturing foundation stone through each field of aviation, automobile, shipbuilding etc., after being processed to it
Quality determining method then becomes the one of the important signs that for weighing a national manufacturing industry level height, only more precise and high efficiency
Workpiece inspection method can just produce the workpiece of better quality.
During the quality testing of workpiece, whether detection workpiece configurations comply with standard, and often most basic is also most heavy
It wants.Existing workpiece configurations detection method is by manufacturing the matching template to match with workpiece configurations, then by work mostly
Part is combined with matching template, judges matching degree by visually, so that it is determined that whether workpiece configurations comply with standard.
Such detection method brings following problem：
(1) judge matching degree by visually, lead to the disunity of examination criteria, so that eventually by detection
Workpiece configurations quality is irregular, results in the need for secondary detection further to eliminate defect ware, time-consuming and laborious and quality is difficult to
To guarantee；
(2) it realizes the mutual cooperation of workpiece and matching template by manually, not only consumes human resources, but also be difficult to ensure
Detection speed.
Invention content
The purpose of the present invention is provide a kind of workpiece configurations detection method based on machine vision regarding to the issue above.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of workpiece configurations detection method based on machine vision, for detecting the workpiece configurations produced with the presence or absence of scarce
It falls into, the method includes：
1) the edge-detected image template of workpiece is established；
2) workpiece image to be detected is acquired, and initialization process is carried out to the workpiece image to be detected after acquisition；
3) by treated in the edge-detected image template and step 2) that are obtained in step 1) workpiece image to be detected into
Row bianry image morphology operations judge that workpiece configurations whether there is defect according to operation result.
Preferably, the edge-detected image template for establishing workpiece includes：The matches criteria template of workpiece is built, and right
Matching template carries out Image Acquisition, obtains the edge-detected image template of workpiece.
Preferably, the edge-detected image template for establishing workpiece includes：According to the normal data value of workpiece, pass through meter
Calculation machine Image Rendering tool is directly drawn and obtains the edge-detected image template of workpiece.
Preferably, the step 2) includes：
21) workpiece image to be detected is acquired；
22) workpiece image to be detected after acquisition is coordinately transformed, realize acquisition after workpiece image to be detected with
The coordinate unification of edge-detected image template, the workpiece image to be detected that obtains that treated.
5. the workpiece configurations detection method according to claim 4 based on machine vision, which is characterized in that the step
It is rapid 22) to include：
221) the first coordinate value of feature holes in the workpiece image to be detected after acquisition is read, while reading edge detection graph
As the second coordinate value of corresponding feature holes in template；
222) image transformation parameter is determined according to the second coordinate value of the first coordinate value of feature holes and feature holes；
223) the image transformation parameter obtained according to step 222) carries out coordinate change to the workpiece image to be detected after acquisition
It changes, the workpiece image to be detected that obtains that treated.
Preferably, described image transformation parameter includes scale transformation parameter, rotation transformation parameter and translation transformation parameter.
Preferably, the coordinate transform is specially：
Wherein, (xw,yw) it is treated workpiece image coordinate to be detected, (xi,yi) be acquisition after workpiece figure to be detected
As coordinate, s is scale transformation parameter, and θ is rotation transformation parameter, x0And y0It is translation transformation parameter.
Preferably, the step 3) includes：
31) by treated in the edge-detected image template and step 2) that are obtained in step 1), workpiece figure to be detected carries out
Subtraction in bianry image morphology obtains difference output image；
32) judge to whether there is obvious shortcoming image in difference output image, if then showing workpiece configurations existing defects,
If otherwise showing, obvious shortcoming is not present in workpiece.
Preferably, the obvious shortcoming image is specially：Absolute growth is more than the high brightness lines of defined threshold.
Compared with prior art, the invention has the advantages that：
(1) by acquiring workpiece image to be detected, and it is matched with edge-detected image template, passes through machine
Vision carries out the comparison between image, eventually by binary morphology image operation obtains an accurate specific workpiece configurations
Difference between template quantifies the standard of detection compared with manually matching and naked eyes identify, thus overcomes
Of low quality, the problem of needing secondary detection is detected in the prior art.
(2) profile measurement of workpiece, this detection mode are carried out by images match and bianry image morphology operations
It can be operated completely via machine, be participated in without artificial, on the one hand save human resources, on the other hand also improve detection effect
Rate, to improve the production efficiency of workpiece.
(3) edge detection template of workpiece include to carrying out Image Acquisition after manufacturer's standard matching template, can also be direct
It is drawn by machine, template generation mode is various, can be chosen according to actual conditions, and operation is flexible.
(4) it when carrying out the matching of workpiece image and template image, needs to unify the two onto the same coordinate system, to
Ensure the order of accuarcy of images match, improves detection quality.
(5) during carrying out coordinate unification, scaling, rotation and translation transformation parameter are considered respectively, are considered comprehensively,
Improve the order of accuarcy of detection.
Description of the drawings
Fig. 1 is the flow chart of the workpiece configurations detection method based on machine vision；
Fig. 2 is scale transformation schematic diagram；
Fig. 3 is rotation transformation schematic diagram；
Fig. 4 is the output image schematic diagram of edge-detected image template；
Fig. 5 is the output image schematic diagram after bianry image morphology operations.
Specific implementation mode
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, give detailed embodiment and specific operating process, but protection scope of the present invention is not limited to
Following embodiments.
The present embodiment proposes a kind of workpiece configurations detection method based on machine vision, for detecting the workpiece produced
Shape whether there is defect, as shown in Figure 1, this method includes：
1) the edge-detected image template for establishing workpiece, specifically includes：The matches criteria template of workpiece is built, and to matching
Template carries out Image Acquisition, obtains the edge-detected image template of workpiece；Or the normal data value according to workpiece, pass through computer
Image Rendering tool is directly drawn and obtains the edge-detected image template of workpiece；
2) workpiece image to be detected is acquired, and initialization process is carried out to the workpiece image to be detected after acquisition, including：
21) workpiece image to be detected is acquired；
22) workpiece image to be detected after acquisition is coordinately transformed, realize acquisition after workpiece image to be detected with
The coordinate unification of edge-detected image template, the workpiece image to be detected that obtains that treated, including：
221) the first coordinate value of feature holes in the workpiece image to be detected after acquisition is read, while reading edge detection graph
As the second coordinate value of corresponding feature holes in template；
222) determine that (scaling becomes image transformation parameter according to the second coordinate value of the first coordinate value of feature holes and feature holes
Change parameter, rotation transformation parameter and translation transformation parameter)；
223) the image transformation parameter obtained according to step 222) carries out coordinate change to the workpiece image to be detected after acquisition
It changes, the workpiece image to be detected that obtains that treated, specially：
Wherein, (xw,yw) it is treated workpiece image coordinate to be detected, (xi,yi) be acquisition after workpiece figure to be detected
As coordinate, s is scale transformation parameter, and θ is rotation transformation parameter, x0And y0It is translation transformation parameter；
3) by treated in the edge-detected image template and step 2) that are obtained in step 1) workpiece image to be detected into
Row bianry image morphology operations judge that workpiece configurations whether there is defect according to operation result, including：
31) by treated in the edge-detected image template and step 2) that are obtained in step 1), workpiece figure to be detected carries out
Subtraction in bianry image morphology obtains difference output image；
32) judge that (specially absolute growth is more than defined threshold with the presence or absence of obvious shortcoming image in difference output image
High brightness lines), if then showing workpiece configurations existing defects, if otherwise show workpiece be not present obvious shortcoming.
About in the above method, image is coordinately transformed, based on principle be specially 2D matching techniques, at 2D
With being known as 2D transformation or geometric transformation etc. from the mapping of 2D coordinate spaces to another 2D coordinate space in technology.It is defined
Formula is：
The invertible mapping relationship between the point on point and image I in above-mentioned expression model M, and by function g and h in mould
Correspondence is set up between type point [x, y] and picture point [r, c], the characteristic point in such model can be found in the picture
Its corresponding position.Also need to use the image registration techniques in 2D matchings in Work Piece Verification System Based, so-called image registration, just
It is the approximate viewpoint about same scene, the two images of different coordinates carry out geometric transformation so that two width figures to picture point
Character pair point coordinate having the same after the conversion as in.And in process of image registration, most important need are to be applied
It is exactly affine transformation technology.
In the present embodiment, scaling, rotation and the translation in selective analysis affine transformation.Scaling, scaling are discussed first
It is a kind of most commonly seen graph transformation technology.The scaling in proportion applied in the present system is exactly coefficient at equivalent ratios
Change all coordinates, is exactly that the coordinate of the point, which is multiplied by a zoom factor come table, to be indicated by one to the scaling of 2D points in fact
Show, as shown in Fig. 2, its formula is as follows
Twiddle operation in affine transformation is then expressed as the rotation in the spaces 2D, and mathematical formulae is as follows, by multiplying
A upper angular transformation matrix can easily represent rotation of the 2D points around origin.Its meaning is as shown in figure 3, what is indicated is
2D point P=[x, y] obtain a new point P'=[x', y'] after rotating the angles θ counterclockwise around origin.
And shift operations more maximum difference compared with above-mentioned scaling and twiddle operation be exactly shift operations is non-linear
, while the translation of image is unusual generally existing in the exploitation of body member detecting system.Shift operations are it is well understood that as follows
It states shown in formula, effect is translated to point [x, y].
Matching technique in machine vision as benchmark has been extremely important effect in practical applications with reference to property due to it
's.Usually, the matching technique in machine vision is divided into 2D matchings and is matched with 3D.Affine transformation technology contracting in 2D matchings
It is the basic operation for constituting image registration to put, rotate and translate.These three transform operations are being carried out point among the above
Analysis, it is contemplated that this system design actual environment application, the present embodiment be 2D match, provide herein 2D match in by this three
Formula after kind transformation is integrated, point P can be completed at two coordinate systems (world coordinate system and image coordinate system) by the formula
Between transformation.
For the matching template of the present embodiment, the purpose for designing and developing it is exactly to carry out mesh using machine vision technique
Mark not with positioning.And according to 2D matching principles, the effect of matching template just acts as object module, by matching template and target
Image is that captured workpiece image is matched, and the feature that matching template is extracted passes through scaling, rotation and translation etc.
It is converted into coordinate system identical with big web image, that is, the aspect of model is transformed into characteristics of image, by matching carry out machine
Comparison and identification technology applied in device vision.Feature holes in object model are converted to the feature holes detected, Ke Yili
Solution, it is only necessary to know the correspondence between two picture points, so that it may to calculate affine change between object module and target image
Three parameters such as scaling, rotation, translation in changing.
As long as table 1 illustrates to know that any a pair of of point is imitative to calculating in two tables by feature recognition with table 2
Three parameters such as scaling, rotation, translation of transformation are penetrated, can be realized by object module to target image by these three parameters
Between mapping, to realize the required matching identification of workpiece configurations detection.
Distance between the position and each hole of 1 model mesoporous of table
| Point | Coordinate | To the distance of A | To the distance of B | To the distance of C |
| A | (9,18) | 0 | 12 | 21 |
| B | (17,27) | 12 | 0 | 26 |
| C | (23,2) | 21 | 26 | 0 |
Distance between the position and each hole of 2 image mesoporous of table
| Point | Coordinate | To H1Distance | To H2Distance | To H3Distance |
| H1 | (32,10) | 0 | 21 | 26 |
| H2 | (11,13) | 21 | 0 | 12 |
| H3 | (11,25) | 26 | 12 | 0 |
Based on above-mentioned principle, the present embodiment is carried out by taking the big web of the tailplane in aircraft components as an example outside specific workpiece
Shape detection operation, process are as follows：
It is the profile measurement figure that establish big web matching template first for workpiece configurations detection design technology
Then picture carries out Image Acquisition in the fixed position of established matching template profile measurement image to big web, will acquire big
Web image also carries out same profile measurement, is then matched by the profile measurement of the two images to check big web profile
It is whether consistent with matching template, detect whether the shape of big web is consistent with technological specification with this.
According to foregoing description, workpiece configurations inspection software is to carry out Image Acquisition and processing to matching template to be formed first
Edge-detected image template then carries out Image Acquisition to big web with the same manner and processing forms edge contour detection figure
Then picture carries out match cognization to this two images and examines big web profile with this.It is defeated that this software module needs are provided first
The matching template image use-case entered, this is also the input starting point of the design exploitation.By running the software, workpiece configurations detection
Matching template the profile measurement output such as Fig. 4 of software module.Image Acquisition is carried out to big web in the same fashion in same location
And workpiece configurations edge-detected image is formed, the subtraction in binary morphology then is carried out to this two images, according to shape
State principle of operation can generate high brightness lines in the output image of generation if big web profile is defective in fault location.
Claims (9)
1. a kind of workpiece configurations detection method based on machine vision, for detecting the workpiece configurations produced with the presence or absence of scarce
It falls into, which is characterized in that the method includes：
1) the edge-detected image template of workpiece is established；
2) workpiece image to be detected is acquired, and initialization process is carried out to the workpiece image to be detected after acquisition；
3) by treated in the edge-detected image template and step 2) that are obtained in step 1), workpiece image to be detected carries out two
It is worth morphological image operation, judges that workpiece configurations whether there is defect according to operation result.
2. the workpiece configurations detection method according to claim 1 based on machine vision, which is characterized in that described to establish work
The edge-detected image template of part includes：The matches criteria template of workpiece is built, and Image Acquisition is carried out to matching template, is obtained
The edge-detected image template of workpiece.
3. the workpiece configurations detection method according to claim 1 based on machine vision, which is characterized in that described to establish work
The edge-detected image template of part includes：According to the normal data value of workpiece, by computer picture drawing tool, directly draw
Obtain the edge-detected image template of workpiece.
4. the workpiece configurations detection method according to claim 1 based on machine vision, which is characterized in that the step 2)
Including：
21) workpiece image to be detected is acquired；
22) workpiece image to be detected after acquisition is coordinately transformed, realizes the workpiece image and edge to be detected after acquisition
The coordinate unification of detection image template, the workpiece image to be detected that obtains that treated.
5. the workpiece configurations detection method according to claim 4 based on machine vision, which is characterized in that the step
22) include：
221) the first coordinate value of feature holes in the workpiece image to be detected after acquisition is read, while reading edge-detected image mould
Second coordinate value of corresponding feature holes in plate；
222) image transformation parameter is determined according to the second coordinate value of the first coordinate value of feature holes and feature holes；
223) the image transformation parameter obtained according to step 222) is coordinately transformed the workpiece image to be detected after acquisition,
The workpiece image to be detected that obtains that treated.
6. the workpiece configurations detection method according to claim 5 based on machine vision, which is characterized in that described image becomes
It includes scale transformation parameter, rotation transformation parameter and translation transformation parameter to change parameter.
7. the workpiece configurations detection method according to claim 6 based on machine vision, which is characterized in that
The coordinate transform is specially：
Wherein, (xw,yw) it is treated workpiece image coordinate to be detected, (xi,yi) sat for the workpiece image to be detected after acquisition
Mark, s are scale transformation parameter, and θ is rotation transformation parameter, x0And y0It is translation transformation parameter.
8. the workpiece configurations detection method according to claim 1 based on machine vision, which is characterized in that the step 3)
Including：
31) by treated in the edge-detected image template and step 2) that are obtained in step 1), workpiece figure to be detected carries out two-value
Subtraction in morphological image obtains difference output image；
32) judge to whether there is obvious shortcoming image in difference output image, if then showing workpiece configurations existing defects, if not
Then show that obvious shortcoming is not present in workpiece.
9. the workpiece configurations detection method according to claim 8 based on machine vision, which is characterized in that described apparent scarce
Sunken image is specially：Absolute growth is more than the high brightness lines of defined threshold.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2017109851101 | 2017-10-20 | ||
| CN201710985110 | 2017-10-20 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108279241A true CN108279241A (en) | 2018-07-13 |
Family
ID=62805056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810072125.3A Pending CN108279241A (en) | 2017-10-20 | 2018-01-25 | A kind of workpiece configurations detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108279241A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991338A (en) * | 2021-04-27 | 2021-06-18 | 湖南大捷智能装备有限公司 | Defect detection method and device for laser cutting part |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01227910A (en) * | 1988-03-08 | 1989-09-12 | Hitachi Constr Mach Co Ltd | Optical inspection device |
| CN102509300A (en) * | 2011-11-18 | 2012-06-20 | 深圳市宝捷信科技有限公司 | Defect detection method and system |
| CN102680478A (en) * | 2012-04-25 | 2012-09-19 | 华南农业大学 | Detection method and device of surface defect of mechanical part based on machine vision |
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN106897994A (en) * | 2017-01-20 | 2017-06-27 | 北京京仪仪器仪表研究总院有限公司 | A kind of pcb board defect detecting system and method based on layered image |
| CN107084666A (en) * | 2017-05-10 | 2017-08-22 | 中国计量大学 | Brake block dimension synthesis detection method based on machine vision |
| CN107192716A (en) * | 2017-04-26 | 2017-09-22 | 广东工业大学 | A kind of workpiece, defect quick determination method based on contour feature |
| CN107248159A (en) * | 2017-08-04 | 2017-10-13 | 河海大学常州校区 | A kind of metal works defect inspection method based on binocular vision |
-
2018
- 2018-01-25 CN CN201810072125.3A patent/CN108279241A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01227910A (en) * | 1988-03-08 | 1989-09-12 | Hitachi Constr Mach Co Ltd | Optical inspection device |
| CN102509300A (en) * | 2011-11-18 | 2012-06-20 | 深圳市宝捷信科技有限公司 | Defect detection method and system |
| CN102680478A (en) * | 2012-04-25 | 2012-09-19 | 华南农业大学 | Detection method and device of surface defect of mechanical part based on machine vision |
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN106897994A (en) * | 2017-01-20 | 2017-06-27 | 北京京仪仪器仪表研究总院有限公司 | A kind of pcb board defect detecting system and method based on layered image |
| CN107192716A (en) * | 2017-04-26 | 2017-09-22 | 广东工业大学 | A kind of workpiece, defect quick determination method based on contour feature |
| CN107084666A (en) * | 2017-05-10 | 2017-08-22 | 中国计量大学 | Brake block dimension synthesis detection method based on machine vision |
| CN107248159A (en) * | 2017-08-04 | 2017-10-13 | 河海大学常州校区 | A kind of metal works defect inspection method based on binocular vision |
Non-Patent Citations (9)
| Title |
|---|
| HONG HANMEI等: "Visual quality detection of aquatic products using machine vision", 《AQUACULTURAL ENGINEERING》 * |
| 宾鸿赞等: "《先进加工过程技术》", 30 September 2009, 华中科技大学出版社 * |
| 年雷等: "基于机器视觉的自由曲面轮廓度检测***", 《电子科技》 * |
| 张玉娟等: "《遥感数字图像处理》", 31 July 2016, 哈尔滨工程大学出版社 * |
| 李继桢等: "《位置误差测量》", 30 November 1993, 中国计量出版社 * |
| 王建等: "《汽车现代测试技术》", 31 May 2013, 国防工业出版社 * |
| 王魁生等: "浅谈图像仿射变换的应用", 《信息技术与信息化》 * |
| 赵相伟等: "《MATLAB与测量数据处理》", 31 March 2014, 中国矿业大学出版社 * |
| 高宏伟等: "《电子制造装备技术》", 30 September 2015, 西安电子科技大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991338A (en) * | 2021-04-27 | 2021-06-18 | 湖南大捷智能装备有限公司 | Defect detection method and device for laser cutting part |
| CN112991338B (en) * | 2021-04-27 | 2021-07-27 | 湖南大捷智能装备有限公司 | Defect detection method and device for laser cutting part |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Da et al. | Sub-pixel edge detection based on an improved moment | |
| CN107341802B (en) | Corner sub-pixel positioning method based on curvature and gray scale compounding | |
| CN103292701B (en) | The online dimension measurement method of accurate device based on machine vision | |
| CN107862690B (en) | Circuit board component positioning method and device based on feature point matching | |
| CN108335331B (en) | Binocular vision positioning method and equipment for steel coil | |
| CN102999886B (en) | Image Edge Detector and scale grating grid precision detection system | |
| CN111862037A (en) | Method and system for detecting geometric characteristics of precision hole type part based on machine vision | |
| CN108389184A (en) | A kind of workpiece drilling number detection method based on machine vision | |
| CN105894002B (en) | A kind of instrument registration recognition methods based on machine vision | |
| CN101063660B (en) | Method for detecting textile defect and device thereof | |
| CN112037203A (en) | Side surface defect detection method and system based on complex workpiece outer contour registration | |
| CN105975979B (en) | A kind of instrument detecting method based on machine vision | |
| CN106340010B (en) | A kind of angular-point detection method based on second order profile difference | |
| US11080892B2 (en) | Computer-implemented methods and system for localizing an object | |
| JP2018152055A (en) | System and method for scoring color candidate poses against color image in vision system | |
| CN107036530A (en) | The calibration system and method for the location of workpiece | |
| CN104819915A (en) | Testing method for circularity and sphericity of fracturing proppant | |
| CN106529548A (en) | Sub-pixel level multi-scale Harris corner point detection algorithm | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN108279241A (en) | A kind of workpiece configurations detection method based on machine vision | |
| CN114936997A (en) | Detection method, detection device, electronic equipment and readable storage medium | |
| CN113744252A (en) | Method, apparatus, storage medium and program product for marking and detecting defects | |
| CN106169079B (en) | A kind of pressure vessel quantity recognition methods based on computer vision | |
| CN201081763Y (en) | Textile defect detector | |
| CN110322395B (en) | Part outline shape detection method and device based on image processing and affine transformation |
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: 20180713 |