CN104239950A - Piston ring counting system based on machine vision and counting method of piston ring counting system based on machine vision - Google Patents
Piston ring counting system based on machine vision and counting method of piston ring counting system based on machine vision Download PDFInfo
- Publication number
- CN104239950A CN104239950A CN201410442239.4A CN201410442239A CN104239950A CN 104239950 A CN104239950 A CN 104239950A CN 201410442239 A CN201410442239 A CN 201410442239A CN 104239950 A CN104239950 A CN 104239950A
- Authority
- CN
- China
- Prior art keywords
- piston ring
- machine vision
- number system
- point
- mentioned
- 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
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a piston ring counting system based on the machine vision and a counting method of the piston ring counting system based on the machine vision. The piston ring counting system based on the machine vision comprises a central processing unit (1), a camera shooting device (4), a light source (5) and a piston ring positioning mechanism (6), wherein a piston ring is installed on the piston ring positioning mechanism (6), the light source (5) is installed on the side of the piston ring and can irradiate the position where the piston ring is located, the camera shooting device (4) is installed on the side of the piston ring and can shoot the position where the piston ring is located, the camera shooting device (4) is connected with the central processing unit (1) through a connecting line (2), and the camera shooting device (4), the light source (5) and the piston ring positioning mechanism (6) are installed in a camera obscura (3). By means of the piston ring counting system based on the machine vision, the counting speed can be increased, the counting accuracy can be improved, the operating cost is reduced, the piston ring counting system is easy to operate and high in efficiency, and the labor intensity of workers can be reduced. The counting method of the piston ring counting system based on the machine vision is convenient to use and practical.
Description
Technical field
The present invention is a kind of piston ring based on machine vision point number system and method for counting thereof, belongs to the innovative technology of piston ring point number system based on machine vision and method of counting thereof.
Background technology
Piston ring in process of production, needs to count its production quantity, during packing and selling, also needs to count its quantity, and the quantity of each packaging must be accurately.At present, the counting of piston ring is rely on to have counted one by one manually substantially.Because piston ring not only labour intensity of counting manually is large, efficiency is low, and as easy as rolling off a logly occurs mistake, and often occur inaccurate situation of counting, the quantity of some packaging has more the quantity of regulation, causes the operating cost of manufacturing enterprise to increase, profit decline; The quantity of some packaging is less than the quantity of regulation, causes the continuous complaint of client.
Summary of the invention
The object of the invention is to consider the problems referred to above and provide one can improve the speed of counting and accuracy, reduce the point of the piston ring based on the machine vision number system of operating cost.The present invention is simple to operate, and efficiency is high, and can reduce the labour intensity of workman.
Another object of the present invention is to the method for counting that a kind of convenient and practical piston ring based on machine vision point number system is provided.
Technical scheme of the present invention is: the point of the piston ring based on machine vision number system of the present invention, include central processing unit, camera head, light source, piston ring detent mechanism, wherein piston ring is installed on piston ring detent mechanism, light source is installed in the side of piston ring and can be irradiated on the position of piston ring, camera head is installed in the side of piston ring and can photographs on the position of piston ring, camera head is connected with central processing unit by connecting line, and camera head, light source, piston ring detent mechanism are all installed in camera bellows.
The present invention is based on the method for counting of the piston ring point number system of machine vision, comprise the steps:
1) image acquisition;
2) image filtering;
3) image enhaucament;
4) binary conversion treatment;
5) Morphological scale-space;
6) rim detection;
7) result of calculation.
Piston ring based on machine vision point number system of the present invention includes central processing unit owing to adopting, camera head, light source, the structure of piston ring detent mechanism, wherein piston ring is installed on piston ring detent mechanism, light source is installed in the side of piston ring, and can be irradiated on the position of piston ring, camera head is installed in the side of piston ring, and can photograph on the position of piston ring, camera head is connected with central processing unit by connecting line, the present invention not only can improve the speed of counting and accuracy, and can operating cost be reduced, simple to operate, efficiency is high, the labour intensity of workman can be reduced, in addition, camera head, light source, piston ring detent mechanism is all installed in camera bellows, camera bellows can stop the interference of ambient light to system, for system provides a stable testing environment.The present invention is that a kind of design is ingenious, function admirable, the convenient and practical point of the piston ring based on machine vision number system.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of the piston ring point number system that the present invention is based on machine vision;
Fig. 2 is the process flow diagram of the method for counting of the piston ring point number system that the present invention is based on machine vision.
Embodiment
Embodiment:
Schematic diagram of the present invention as shown in Figure 1, piston ring based on machine vision point number system of the present invention, include central processing unit 1, camera head 4, light source 5, piston ring detent mechanism 6, wherein piston ring is installed on piston ring detent mechanism 6, light source 5 is installed in the side of piston ring, and can be irradiated on the position of piston ring, camera head 4 is installed in the side of piston ring, and can photograph on the position of piston ring, camera head 4 is connected with central processing unit 1 by connecting line 2, camera head 4, light source 5, piston ring detent mechanism 6 is all installed in camera bellows 3.Camera head 4, light source 5, piston ring detent mechanism 6 are all placed in camera bellows 3, and camera bellows 3 can stop the interference of ambient light to system, for system provides a stable testing environment.
In the present embodiment, above-mentioned light source 5 is LED light source.LED light source provides uniform and stable illumination, because piston ring surface reflective function is good, and gap reflective function between piston ring and piston ring is poor, so when using LED light source direct irradiation piston ring, the minutia in gap between piston ring surface and piston ring can be given prominence to.
Above-mentioned camera head 4 is industrial camera.Industrial camera and LED light source angled, industrial camera gathers the surface image of piston ring 7, and by image transmitting on central processing unit 1.
In the present embodiment, two fixed legs that above-mentioned piston ring detent mechanism 6 comes by being separated by form, and the distance between two fixed legs is less than the diameter of piston ring.Distance between above-mentioned two fixed legs and camera head 4 is fixed.Be placed into by piston ring 7 between two fixed legs, two fixed legs can fixed piston ring 7, and each piston ring 7 placed is consistent to the distance between camera head 4.In the present embodiment, two fixed legs are iron prop.
In the present embodiment, above-mentioned central processing unit 1 is computing machine.
The present invention is based on the method for counting of the piston ring point number system of machine vision, comprise the steps:
1) image acquisition;
2) image filtering;
3) image enhaucament;
4) binary conversion treatment;
5) Morphological scale-space;
6) rim detection;
7) result of calculation.
Above-mentioned steps 4) the method for binary conversion treatment be overall grey relevant dynamic matrix.
Above-mentioned steps 5) the process of Morphological scale-space be: etching operation, open operation, closed operation.
Above-mentioned 6) method of rim detection is Lapalace edge detection algorithm.
Above-mentioned 7) process of result of calculation is: in fixing region, add up amount of edge, edge calculation centre coordinate, edge calculation spacing, thus calculate spacing data between actual amount of edge and edge.
The method of counting that the present invention is based on the piston ring point number system of machine vision is integrated use image filtering, image enhaucament, Binary Sketch of Grey Scale Image, Morphological scale-space, rim detection scheduling algorithm, graphical analysis and process are done to the video sequence that camera captures, calculate piston ring quantity, then result of calculation is shown.
Image filtering is indispensable operation in Image semantic classification, and it can suppress the noise of target image under the condition as far as possible retaining image detail feature, and the quality of its treatment effect will directly have influence on the reliability of successive image process and analysis.
Image enhancement technique can strengthen information useful in image, it can be the process of a distortion, its objective is the visual effect will improving image, for the application scenario of Given Graph picture, on purpose strengthen entirety or the local feature of image, original unsharp image is become clear, or emphasize some interested feature, difference in expanded view picture between different objects feature, abundant information amount.
Binary Sketch of Grey Scale Image is exactly that the gray-scale value of the pixel on image is set to 0 or 1, and whole image is presented obvious black-white visual effect, is target object and background by Iamge Segmentation, extracts interested target.
Morphologic filtering be for binary conversion treatment after image, major part trickle illumination effect all may be removed, when still there is much little grain noise in image, in moving mass, also may there is some little cavities.At this moment just noise can be removed by the method for morphologic filtering.Morphologic filtering comprises two kinds of computings, and one is named expansion (dilation), and one is named corrosion (erosion).These two kinds of computings can obtain again other two kinds of computings by the combination of different sequencings, and one is called opening operation, and one is named closed operation.Opening operation expands after first doing corrosion, generally removes noise with it.Expansion post-etching is first done in closed operation, generally removes the cavity in foreground blocks with it.
Rim detection is the basic problem in image procossing, its objective is and identifies the obvious point of luminance transformation in digital picture.Rim detection decreases data volume significantly, and eliminates incoherent information, retains the structure attribute that image is important.
Claims (10)
1. the point of the piston ring based on a machine vision number system, it is characterized in that including central processing unit (1), camera head (4), light source (5), piston ring detent mechanism (6), wherein piston ring is installed on piston ring detent mechanism (6), light source (5) is installed in the side of piston ring, and can be irradiated on the position of piston ring, camera head (4) is installed in the side of piston ring, and can photograph on the position of piston ring, camera head (4) is connected with central processing unit (1) by connecting line (2), camera head (4), light source (5), piston ring detent mechanism (6) is all installed in camera bellows (3).
2. the point of the piston ring based on machine vision number system according to claim 1, is characterized in that above-mentioned light source (5) is LED light source.
3. the point of the piston ring based on machine vision number system according to claim 1, is characterized in that above-mentioned camera head (4) is industrial camera.
4. the point of the piston ring based on machine vision number system according to claim 1, is characterized in that above-mentioned piston ring detent mechanism (6) is made up of two fixed legs come of being separated by.
5. the point of the piston ring based on machine vision number system according to claim 4, is characterized in that the distance between above-mentioned two fixed legs is less than the diameter of piston ring.
6. the point of the piston ring based on machine vision number system according to claim 4, is characterized in that the distance of above-mentioned two fixed legs and camera head (4) is fixed.
7. the point of the piston ring based on the machine vision number system according to any one of claim 1 to 6, is characterized in that above-mentioned central processing unit (1) is computing machine.
8., based on a method of counting for the piston ring point number system of machine vision, it is characterized in that comprising the steps:
1) image acquisition;
2) image filtering;
3) image enhaucament;
4) binary conversion treatment;
5) Morphological scale-space;
6) rim detection;
7) result of calculation.
9. the method for counting of the point of the piston ring based on machine vision number system according to claim 8, is characterized in that above-mentioned steps 4) the method for binary conversion treatment be overall grey relevant dynamic matrix.
10. the method for counting of the point of the piston ring based on machine vision number system according to claim 8, is characterized in that above-mentioned steps 5) the process of Morphological scale-space be: etching operation, open operation, closed operation;
Above-mentioned 6) method of rim detection is Lapalace edge detection algorithm;
Above-mentioned 7) process of result of calculation is: in fixing region, add up amount of edge, edge calculation centre coordinate, edge calculation spacing, thus calculate spacing data between actual amount of edge and edge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410442239.4A CN104239950B (en) | 2014-09-02 | 2014-09-02 | A kind of piston ring point number system and its method of counting based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410442239.4A CN104239950B (en) | 2014-09-02 | 2014-09-02 | A kind of piston ring point number system and its method of counting based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104239950A true CN104239950A (en) | 2014-12-24 |
| CN104239950B CN104239950B (en) | 2017-07-14 |
Family
ID=52227972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410442239.4A Active CN104239950B (en) | 2014-09-02 | 2014-09-02 | A kind of piston ring point number system and its method of counting based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104239950B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109579735A (en) * | 2018-12-03 | 2019-04-05 | 广州沧恒自动控制科技有限公司 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
| CN109919926A (en) * | 2019-03-05 | 2019-06-21 | 长春工业大学 | A kind of piston ring image rapid counting method |
| CN110473174A (en) * | 2019-07-26 | 2019-11-19 | 东南大学 | A method of pencil exact number is calculated based on image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175166A (en) * | 2011-02-16 | 2011-09-07 | 武汉理工大学 | Device for detecting thickness of oil film between cylinder sleeve and piston ring of diesel engine |
| CN102226688A (en) * | 2011-04-12 | 2011-10-26 | 翁瑜 | Automatic detection system of engine piston ring |
| CN203642893U (en) * | 2013-12-26 | 2014-06-11 | 无锡信捷电气股份有限公司 | Semi-automatic piston ring detector |
| CN204009998U (en) * | 2014-09-02 | 2014-12-10 | 广州沧恒自动控制科技有限公司 | A kind of piston ring point number system based on machine vision |
-
2014
- 2014-09-02 CN CN201410442239.4A patent/CN104239950B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175166A (en) * | 2011-02-16 | 2011-09-07 | 武汉理工大学 | Device for detecting thickness of oil film between cylinder sleeve and piston ring of diesel engine |
| CN102226688A (en) * | 2011-04-12 | 2011-10-26 | 翁瑜 | Automatic detection system of engine piston ring |
| CN203642893U (en) * | 2013-12-26 | 2014-06-11 | 无锡信捷电气股份有限公司 | Semi-automatic piston ring detector |
| CN204009998U (en) * | 2014-09-02 | 2014-12-10 | 广州沧恒自动控制科技有限公司 | A kind of piston ring point number system based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 王桂棠: "《基于机器视觉的活塞环闭口间隙自动检测》", 《仪器仪表与检测》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109579735A (en) * | 2018-12-03 | 2019-04-05 | 广州沧恒自动控制科技有限公司 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
| CN109919926A (en) * | 2019-03-05 | 2019-06-21 | 长春工业大学 | A kind of piston ring image rapid counting method |
| CN110473174A (en) * | 2019-07-26 | 2019-11-19 | 东南大学 | A method of pencil exact number is calculated based on image |
| CN110473174B (en) * | 2019-07-26 | 2022-02-11 | 东南大学 | Method for calculating accurate number of pencils based on image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104239950B (en) | 2017-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Duan et al. | EventZoom: Learning to denoise and super resolve neuromorphic events | |
| CN108335331B (en) | Binocular vision positioning method and equipment for steel coil | |
| US20170337693A1 (en) | Method and system of real-time image segmentation for image processing | |
| US9542735B2 (en) | Method and device to compose an image by eliminating one or more moving objects | |
| CN111951238A (en) | Product defect detection method | |
| CN104867159A (en) | Stain detection and classification method and device for sensor of digital camera | |
| CN105866136A (en) | Camera module optical filter gluing detection apparatus and method | |
| CN104075965A (en) | Method for measuring granularity of microscopic image particles segmented on basis of watershed | |
| CN114170165A (en) | Chip surface defect detection method and device | |
| CN106156691B (en) | method and device for processing complex background image | |
| CN104239950A (en) | Piston ring counting system based on machine vision and counting method of piston ring counting system based on machine vision | |
| CN105719251B (en) | A kind of compression degraded image restored method that Linear Fuzzy is moved for big picture | |
| Khalid et al. | Image de-fencing using histograms of oriented gradients | |
| CN109001213A (en) | A kind of reel-to-reel ultrathin flexible IC exterior substrate detection method | |
| WO2020168818A1 (en) | Image processing method, system and device, storage medium, and blackboard device | |
| CN112037233B (en) | Image binarization method based on Otsu method and K-means clustering algorithm combined optimization | |
| Yang | A moving objects detection algorithm in video sequence | |
| Jiang et al. | Combining background subtraction and temporal persistency in pedestrian detection from static videos | |
| US10958899B2 (en) | Evaluation of dynamic ranges of imaging devices | |
| Xu et al. | Sports video moving object detection and tracking technology based on hybrid algorithm | |
| CN102880355A (en) | Method and system for extracting touch light spots based on camera positioning | |
| Tao et al. | Measurement algorithm of notch length of plastic parts based on video | |
| CN111738257B (en) | Deep learning-based accurate reasoning system and method for cascading targets of different network models | |
| Zhang et al. | Measurement for blade edge based on machine vision | |
| Yutao et al. | License plate character segmentation from video images: A survey |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |