CN111242894A - Visual identification method for water pump impeller blades - Google Patents
Visual identification method for water pump impeller blades Download PDFInfo
- Publication number
- CN111242894A CN111242894A CN201911399429.1A CN201911399429A CN111242894A CN 111242894 A CN111242894 A CN 111242894A CN 201911399429 A CN201911399429 A CN 201911399429A CN 111242894 A CN111242894 A CN 111242894A
- Authority
- CN
- China
- Prior art keywords
- chuck
- contour
- center
- image
- circle
- 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.)
- Granted
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Abstract
The invention discloses a visual identification method for a water pump impeller blade, which comprises the following steps: s1, collecting an original image of the water pump impeller chuck horizontal plane; s2, converting the collected original image into a gray image; s3, intercepting a rectangular image area in the original image to obtain the position of the center of a circle of the chuck; s4, creating a CV _8UC1 image matrix which has the same size as the original image and the gray value of 0; converting the coordinates of the center position of the chuck into the image matrix through coordinates, acquiring a mask template, and processing the original image through the mask template to obtain a segmented image; s5, binarizing and morphologically processing the segmentation image, and then retrieving the contour to obtain a final contour; s6, drawing the final contour obtained in the step S5 in the original image, and judging whether the impeller blade is inserted into the chuck or not according to the final contour; the method automatically identifies the impeller blades, avoids human factors and facilitates subsequent stamping and spot welding operation.
Description
Technical Field
The invention relates to the technical field of water pump manufacturing, in particular to a visual identification method for a water pump impeller blade.
Background
In the pump body manufacturing industry, the impeller is the core component of the pump body. The water pump impeller is made of cast iron. The blades on the water pump impeller play a main role. In actual production, generally, the pump body impeller blade is placed in a blade groove of a chuck tooling of a production line through manual operation, and corresponding stamping and spot welding operation is carried out after the blade is placed in the groove. Whether the blades are placed in the blade grooves of the chuck tooling or not is generally checked by visual inspection of human eyes, so that the efficiency is low, a large number of unqualified products are caused by error easily, and material waste and damage on benefits are caused.
Disclosure of Invention
The invention aims to provide a visual identification method for water pump impeller blades, which can automatically identify the impeller blades, avoid human factors and facilitate subsequent stamping and spot welding operation.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a visual identification method for water pump impeller blades comprises the following steps:
s1, acquiring an original image of the water pump impeller chuck horizontal plane by using an industrial camera;
s2, converting the collected original image into a gray image;
s3, intercepting a rectangular image area in the original image, wherein the rectangular image area contains a chuck center circle, and retrieving the contour of the chuck center circle;
s4, creating a CV _8UC1 image matrix which has the same size as the original image and the gray value of 0, converting the central position coordinates of the chuck to obtain a mask template, and processing the original image through the mask template to obtain a segmented image;
s5, traversing the screened contours, and performing minimum rectangle surrounding on the screened contour set to obtain parameters of each contour surrounding rectangle;
and S6, drawing the final contour obtained in the step S5 in the original image, and judging whether the impeller blade is inserted into the chuck or not according to the final contour.
Further, when the contour of the chuck center circle is searched in step S3, binarization and morphological processing are performed on the rectangular image region, then the contour is searched, contour information of the outermost circle of the chuck center of the rectangular image region is obtained by screening according to a contour size threshold method, and then minimum peripheral circle processing is performed on the obtained contour information to obtain the center coordinates of the minimum peripheral circle, i.e., the position of the center of the chuck.
Further, when the coordinates of the center of the chuck are converted in step S4, the coordinates of the center of the chuck are converted into the image matrix by coordinates; drawing a circle by taking the coordinate of the center of the chuck as the center and r1 as the radius, and performing flooding algorithm processing with the filling color being white by taking the coordinate of the center of the chuck as a seed point; drawing a circle by taking the coordinate of the center of the chuck as the center and r2 as the radius, and performing flood algorithm processing with black filling color by taking the coordinate of the center of the circle as a seed point to obtain a mask template, wherein r1 is more than r 2;
further, step S5 is executed to binarize and morphologically process the segmented image, then retrieve the contour, and traverse all the contours; and (4) screening and eliminating the interference contour according to a contour size threshold value method.
Further, step S5 is executed to perform minimum rectangle bounding on the filtered outline set, so as to obtain parameters of each outline bounding rectangle.
Further, step S5 is executed to re-screen the contour according to the aspect ratio threshold and the area threshold of the minimum bounding rectangle, so as to obtain the final contour.
The method has the advantages that whether the impeller blade is inserted into the chuck or not can be judged finally by acquiring the image of the chuck and performing a series of identification and processing on the image, and the method automatically identifies the impeller blade, avoids human factors and facilitates subsequent stamping and spot welding operation.
Drawings
The invention is further illustrated with reference to the following figures and examples:
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic diagram of step S1 of the present invention;
FIG. 3 is a schematic diagram of step S3 of the present invention;
FIG. 4 is a schematic representation of step S4 of the present invention;
FIGS. 5 and 6 are schematic diagrams of step S5 according to the present invention;
fig. 7 is a schematic diagram of step S6 of the present invention.
Detailed Description
As shown in fig. 1, the invention provides a visual identification method for a water pump impeller blade, which comprises the following steps:
s1, collecting an original image of the water pump impeller chuck horizontal plane by using an industrial camera in combination with the image shown in the figure 2;
s2, converting the collected original image into a gray image;
s3, with reference to the diagram in FIG. 3, a rectangular image area is cut out from the original image, and the rectangular image area contains a chuck center circle; carrying out binarization and morphological processing on a rectangular image area, then retrieving a contour, screening according to a contour size threshold value method to obtain contour information of the outermost circle of the chuck center of the rectangular image area, and carrying out minimum peripheral circle processing on the obtained contour information to obtain the center coordinates of the minimum peripheral circle, namely the position of the center of the chuck;
s4, in combination with the method shown in FIG. 4, creating a CV _8UC1 image matrix with the same size as the original image and the gray value of 0; converting the coordinates of the circle center position of the chuck into the image matrix through coordinates;
drawing a circle by taking the coordinate of the center of the chuck as the center and r1 as the radius, and performing flooding algorithm processing with the filling color being white by taking the coordinate of the center of the chuck as a seed point;
drawing a circle by taking the coordinate of the center of the chuck as the center and r2 as the radius, and performing flood algorithm processing with black filling color by taking the coordinate of the center of the circle as a seed point to obtain a mask template, wherein r1 is more than r 2;
processing an original image through a mask template to obtain a segmented image;
s5, combining with the figure 5, binarizing and morphologically processing the segmentation image, then retrieving the contour, and traversing all the contours; screening and eliminating interference contours according to a contour size threshold method;
carrying out minimum rectangle surrounding on the screened contour set to obtain parameters of each contour surrounding rectangle;
referring to fig. 6, the contour is screened again according to the aspect ratio threshold and the area threshold of the minimum bounding rectangle, so as to obtain a final contour;
s6, as shown in fig. 7, the final contour obtained in step S5 is drawn in the original image, and it is determined whether or not the impeller blade is inserted into the chuck based on the final contour.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner; those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent replacement, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention.
Claims (6)
1. A visual identification method for water pump impeller blades is characterized by comprising the following steps:
s1, acquiring an original image of the water pump impeller chuck horizontal plane by using an industrial camera;
s2, converting the collected original image into a gray image;
s3, intercepting a rectangular image area in the original image, wherein the rectangular image area contains a chuck center circle, and retrieving the contour of the chuck center circle;
s4, creating a CV _8UC1 image matrix which has the same size as the original image and the gray value of 0, converting the central position coordinates of the chuck to obtain a mask template, and processing the original image through the mask template to obtain a segmented image;
s5, traversing the screened contours, and performing minimum rectangle surrounding on the screened contour set to obtain parameters of each contour surrounding rectangle;
and S6, drawing the final contour obtained in the step S5 in the original image, and judging whether the impeller blade is inserted into the chuck or not according to the final contour.
2. The visual identification method for the water pump impeller blade according to claim 1, characterized in that when the contour of the chuck center circle is retrieved in step S3, binarization and morphological processing are performed on a rectangular image region, then the contour is retrieved, contour information of the outermost circle of the chuck center of the rectangular image region is obtained by screening according to a contour size threshold method, and then minimum peripheral circle processing is performed on the obtained contour information to obtain the center coordinates of the minimum peripheral circle, i.e. the position of the center of the chuck.
3. The visual identification method for the water pump impeller blade according to claim 1, characterized in that when the coordinates of the center of the circle of the chuck are converted in the step S4, the coordinates of the center of the circle of the chuck are converted into the image matrix through coordinates; drawing a circle by taking the coordinate of the center of the chuck as the center and r1 as the radius, and performing flooding algorithm processing with the filling color being white by taking the coordinate of the center of the chuck as a seed point; and drawing a circle by taking the coordinate of the center of the chuck as the center and r2 as the radius, and performing flood algorithm processing on the black filling color by taking the coordinate of the center of the chuck as a seed point to obtain a mask template, wherein r1 is more than r 2.
4. The visual identification method for the water pump impeller blade according to claim 1, wherein step S5 is performed by binarizing and morphologically processing the segmentation image, then retrieving contours, and traversing all contours; and (4) screening and eliminating the interference contour according to a contour size threshold value method.
5. The visual identification method for the water pump impeller blades according to claim 1, wherein step S5 is performed to perform minimum rectangle bounding on the filtered contour set, so as to obtain parameters of each contour bounding rectangle.
6. The visual identification method for the water pump impeller blades according to claim 5, wherein the step S5 is executed to perform re-screening on the contour according to the aspect ratio threshold and the area threshold of the minimum bounding rectangle to obtain the final contour.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911399429.1A CN111242894B (en) | 2019-12-30 | 2019-12-30 | Visual identification method for water pump impeller blades |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911399429.1A CN111242894B (en) | 2019-12-30 | 2019-12-30 | Visual identification method for water pump impeller blades |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111242894A true CN111242894A (en) | 2020-06-05 |
CN111242894B CN111242894B (en) | 2022-12-16 |
Family
ID=70877611
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911399429.1A Active CN111242894B (en) | 2019-12-30 | 2019-12-30 | Visual identification method for water pump impeller blades |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111242894B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009052917A (en) * | 2007-08-23 | 2009-03-12 | Daido Steel Co Ltd | Visual inspection device and visual inspection method |
JP2009097922A (en) * | 2007-10-15 | 2009-05-07 | Daido Steel Co Ltd | Visual inspection method and apparatus |
US20140340509A1 (en) * | 2013-05-16 | 2014-11-20 | Kevin P Fairbairn | System and Method for Real Time Positioning of a Substrate in a Vacuum Processing System |
CN104535586A (en) * | 2014-11-18 | 2015-04-22 | 华东理工大学 | Strip steel edge defect detection identification method |
CN107292310A (en) * | 2017-06-19 | 2017-10-24 | 电子科技大学 | A kind of circular pointer dial plate vision positioning and automatic reading method |
CN108876777A (en) * | 2018-06-14 | 2018-11-23 | 重庆科技学院 | A kind of visible detection method and system of wind electricity blade end face of flange characteristic size |
CN109064440A (en) * | 2018-06-19 | 2018-12-21 | 广东工业大学 | A kind of speaker voice coil bonding wire recognition methods based on machine vision |
CN109544513A (en) * | 2018-10-24 | 2019-03-29 | 广州霞光技研有限公司 | A kind of steel pipe end surface defect extraction knowledge method for distinguishing |
-
2019
- 2019-12-30 CN CN201911399429.1A patent/CN111242894B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009052917A (en) * | 2007-08-23 | 2009-03-12 | Daido Steel Co Ltd | Visual inspection device and visual inspection method |
JP2009097922A (en) * | 2007-10-15 | 2009-05-07 | Daido Steel Co Ltd | Visual inspection method and apparatus |
US20140340509A1 (en) * | 2013-05-16 | 2014-11-20 | Kevin P Fairbairn | System and Method for Real Time Positioning of a Substrate in a Vacuum Processing System |
CN104535586A (en) * | 2014-11-18 | 2015-04-22 | 华东理工大学 | Strip steel edge defect detection identification method |
CN107292310A (en) * | 2017-06-19 | 2017-10-24 | 电子科技大学 | A kind of circular pointer dial plate vision positioning and automatic reading method |
CN108876777A (en) * | 2018-06-14 | 2018-11-23 | 重庆科技学院 | A kind of visible detection method and system of wind electricity blade end face of flange characteristic size |
CN109064440A (en) * | 2018-06-19 | 2018-12-21 | 广东工业大学 | A kind of speaker voice coil bonding wire recognition methods based on machine vision |
CN109544513A (en) * | 2018-10-24 | 2019-03-29 | 广州霞光技研有限公司 | A kind of steel pipe end surface defect extraction knowledge method for distinguishing |
Non-Patent Citations (2)
Title |
---|
LONG WANG 等: ""A Two-Stage Data-Driven Approach for Image-Based Wind Turbine Blade Crack Inspections"", 《IEEE/ASME TRANSACTIONS ON MECHATRONICS》 * |
仇梓峰 等: ""基于无人机图像的风力发电机叶片缺陷识别"", 《发电技术》 * |
Also Published As
Publication number | Publication date |
---|---|
CN111242894B (en) | 2022-12-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113822890B (en) | Microcrack detection method, device and system and storage medium | |
CN111179225A (en) | Test paper surface texture defect detection method based on gray gradient clustering | |
CN109874313A (en) | Text line detection method and line of text detection device | |
CN107301368B (en) | Recognition method of DataMatrix two-dimensional code | |
CN105260693A (en) | Laser two-dimensional code positioning method | |
CN109767445B (en) | High-precision PCB defect intelligent detection method | |
CN112330598B (en) | Method, device and storage medium for detecting stiff yarn defects on chemical fiber surface | |
CN113658150A (en) | Chromosome automatic segmentation and classification method based on deep learning | |
CN107153067A (en) | A kind of surface defects of parts detection method based on MATLAB | |
CN115661157B (en) | Panel circle defect detection method, device, medium, equipment and program product | |
CN110852315A (en) | Method and device for quickly identifying annular characters | |
CN112465809B (en) | Mold defect detection method based on image recognition, computer readable storage medium and device | |
CN112132153B (en) | Tomato fruit identification method and system based on clustering and morphological processing | |
CN116862913B (en) | Machine vision-based defect detection method and system for composite nickel-copper heat dissipation bottom plate | |
CN114627116A (en) | Fabric defect identification method and system based on artificial intelligence | |
CN111242894B (en) | Visual identification method for water pump impeller blades | |
CN115100648B (en) | Method and device for filtering multi-channel fluorescent impurities in cell microscopic image | |
CN116433978A (en) | Automatic generation and automatic labeling method and device for high-quality flaw image | |
CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
CN112991284B (en) | Temperature controller guide frame defect detection method and system | |
CN114627463B (en) | Non-contact power distribution data identification method based on machine identification | |
CN115908261A (en) | Casting X-ray image-based defect rating method and system | |
CN101719273A (en) | On-line self-adaptation extraction method of metallurgy strip surface defect based on one-dimension information entropy | |
CN113210264B (en) | Tobacco sundry removing method and device | |
CN104504702A (en) | Cement notch pavement crack recognition method based on square lattice searching method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |