CN201583506U - Mechanical part surface defect detecting device based on image texture and fractal dimension - Google Patents
Mechanical part surface defect detecting device based on image texture and fractal dimension Download PDFInfo
- Publication number
- CN201583506U CN201583506U CN2009202017340U CN200920201734U CN201583506U CN 201583506 U CN201583506 U CN 201583506U CN 2009202017340 U CN2009202017340 U CN 2009202017340U CN 200920201734 U CN200920201734 U CN 200920201734U CN 201583506 U CN201583506 U CN 201583506U
- Authority
- CN
- China
- Prior art keywords
- infrared sensor
- ccd sensor
- fractal dimension
- sensor
- signal output
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The utility model relates to a mechanical part surface defect detecting device based on image texture and fractal dimension. The prior art is low in detection efficiency and low in accuracy. In the mechanical part surface defect detecting device, an infrared sensor and a CCD sensor are disposed on the same side of a conveyor belt, wherein a distance between the infrared sensor and the conveyor belt is smaller than a distance between the CCD sensor and the conveyor belt, a connecting line of the infrared sensor and the CCD sensor is perpendicular to a moving direction of the conveyor belt, a signal output end of the infrared sensor is connected with an input end of a PLC controller, an output end of the PLC controller is connected with one end of an I/O data interface, the other end of the I/O data interface is connected with a serial port of a computer, a signal output end of the CCD sensor is connected with a signal input end of an image acquisition card, and a signal output end of the image acquisition card is connected with a parallel port of the computer. The mechanical part surface defect detecting device based on image texture and fractal dimension can realize automatic outline by calculating fractal dimension characteristics according to external characteristics of defect textures of surfaces of mechanical parts, and the process is nondestructive detection.
Description
Technical field
The utility model belongs to the machine vision technique field, is specifically related to a kind of surface defects of mechanical parts pick-up unit based on image texture and fractal dimension.
Background technology
Along with the fast development of Chinese manufacturing, no matter be large-scale leading enterprise, or small business all is faced with labor problem.And production run often has unacceptable product and produces, and for guaranteeing that unacceptable product does not dispatch from the factory, enterprise must drop into a large amount of labours and be engaged in product and examine entirely.Except cost, hand inspection also has following shortcoming: efficient is low, and accuracy rate is low.
The repeatability of considering rapidity computing machine, reliability, result combines with the height intellectuality and the abstracting power of human vision, replacing human eye to do with machine measures and judgement, information extraction and handle, analyze from the image of objective things finally realizes actual detection, measurement and control.
Summary of the invention
The utility model provides a kind of surface defects of mechanical parts pick-up unit based on image texture and fractal dimension at the deficiencies in the prior art.
The utility model comprises ccd sensor, computing machine, infrared sensor, light source, image pick-up card, PLC controller, I/O data-interface.Infrared sensor and ccd sensor are arranged on the homonymy of travelling belt, and wherein the distance of infrared sensor and travelling belt is less than the distance of ccd sensor and travelling belt, and infrared sensor is vertical with the conveyer belt direction with the line of ccd sensor.The signal output part of infrared sensor is connected with PLC controller input end, and the PLC controller output end is connected with I/O data-interface one end, and the I/O data-interface other end is connected with serial ports of computers.The signal input part of ccd sensor signal output part and image pick-up card be connected, the signal output part of image pick-up card is connected with computer parallel port.The corresponding mechanical component setting to be checked of light source.
The beneficial effects of the utility model are: can press the surface of surface defects of mechanical parts texture, utilize calculating fractal dimension feature to realize automatic classification, and process be Non-Destructive Testing.
Description of drawings
Fig. 1 is a work synoptic diagram of the present utility model.
Embodiment
The utility model is described in further detail below in conjunction with accompanying drawing.
As shown in Figure 1, a kind of surface defects of mechanical parts pick-up unit based on image texture and fractal dimension comprises ccd sensor 1, computing machine 2, infrared sensor 3, light source 4, image pick-up card 5, PLC controller 6, I/O data-interface 7.
The signal output part of infrared sensor 3 is connected with PLC controller 6 input ends, and PLC controller 6 output terminals are connected with I/O data-interface 7 one ends, and I/O data-interface 7 other ends are connected with computing machine 2 serial ports.
The signal input part of ccd sensor 1 signal output part and image pick-up card 5 be connected, the signal output part of image pick-up card 5 is connected with computing machine 2 parallel ports.
Light source 4 corresponding mechanical component 8 to be checked are provided with, and the light that light source 4 sends covers the surface of mechanical component 8.
Ccd sensor in the present embodiment is gathered the texture image of piece surface, and through processes such as Flame Image Process and analyses, extracts image feature value and then evaluating parts surface imperfection.Thereby image processing techniques and evaluation index be the core technology in the whole surface defects of mechanical parts testing process, is directly connected to the accuracy and the high efficiency of piece surface defects detection.Utilize fractal dimension and the evaluation index of the voidage parameter that characterizes subjective perception, make evaluation procedure simple, satisfy the actual observation result of human eye simultaneously again as the machine vision quality.
The concrete course of work of present embodiment is: in the monitoring chamber, computing machine at first loads machinery part surface texture image storehouse, travelling belt transmits part, when part arrives infrared sensor, infrared sensor signal generation saltus step, be attached thereto the PLC controller that connects thus and send enabling signal to computing machine, and startup ccd sensor, ccd sensor is gathered current machinery part surface texture image in real time, image pick-up card amplifies the image that ccd sensor collected, filtering, pre-service such as sampling, pretreated machinery part surface texture image is sent in the internal memory of computing machine, by machinery part surface detection software systems texture image is handled then and obtained fractal dimension and voidage feature, then above-mentioned two features are merged, standardized element pattern feature in the last and mechanical component database is mated and is compared, and obtains the evaluation index of this mechanical component defective.In conjunction with the classification nominal value of setting, the defective of machinery part surface is carried out range again.On display, show testing result at last.
Claims (1)
1. based on the surface defects of mechanical parts pick-up unit of image texture and fractal dimension, comprise ccd sensor, computing machine, infrared sensor, light source, image pick-up card, PLC controller, I/O data-interface, it is characterized in that: infrared sensor and ccd sensor are arranged on the homonymy of travelling belt, wherein the distance of infrared sensor and travelling belt is less than the distance of ccd sensor and travelling belt, and infrared sensor is vertical with the conveyer belt direction with the line of ccd sensor; The signal output part of infrared sensor is connected with PLC controller input end, and the PLC controller output end is connected with I/O data-interface one end, and the I/O data-interface other end is connected with serial ports of computers; The signal input part of ccd sensor signal output part and image pick-up card be connected, the signal output part of image pick-up card is connected with computer parallel port; The corresponding mechanical component setting to be checked of light source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009202017340U CN201583506U (en) | 2009-12-02 | 2009-12-02 | Mechanical part surface defect detecting device based on image texture and fractal dimension |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009202017340U CN201583506U (en) | 2009-12-02 | 2009-12-02 | Mechanical part surface defect detecting device based on image texture and fractal dimension |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201583506U true CN201583506U (en) | 2010-09-15 |
Family
ID=42725510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009202017340U Expired - Fee Related CN201583506U (en) | 2009-12-02 | 2009-12-02 | Mechanical part surface defect detecting device based on image texture and fractal dimension |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN201583506U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383730A (en) * | 2013-06-03 | 2013-11-06 | 上海索广映像有限公司 | Automatic BNC terminal detecting machine and work method thereof |
-
2009
- 2009-12-02 CN CN2009202017340U patent/CN201583506U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383730A (en) * | 2013-06-03 | 2013-11-06 | 上海索广映像有限公司 | Automatic BNC terminal detecting machine and work method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018103130A1 (en) | Online quality inspection method for molded products | |
| CN103808734B (en) | Auto-parts fully-automated synthesis equipment | |
| CN204924967U (en) | Image acquisition mechanism of full -automatic AOI complete machine | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN102928340A (en) | Image analysis-based method and special equipment for simultaneously determining content of maceral and vitrinite reflectance of coal | |
| CN104677782A (en) | Machine vision online detection system and method for electric connector shell | |
| CN203235694U (en) | High-precision vision measurement system of electronic connector | |
| CN104316033A (en) | Visual inspection system for automobile parts | |
| CN102854195B (en) | Method for detecting defect coordinates on color filter | |
| CN201141839Y (en) | Device for detecting tiny bearing surface defect by computer vision technology | |
| CN112268910A (en) | Visual detection system and method for cigarette appearance defects | |
| CN104833925A (en) | Fuel cell bipolar plate detection method and system based on machine vision | |
| CN202119397U (en) | Non-contact vision detection system for sampling inspection | |
| CN104931505A (en) | Machine visual surface detection system | |
| CN104807397A (en) | Product detection system and product detection method | |
| CN206056509U (en) | Axial workpiece machine vision size detecting device | |
| CN109557098A (en) | Metal surface detection system based on machine vision | |
| CN208555097U (en) | A kind of workpiece shapes based on computer vision detection and sorting device | |
| CN201583506U (en) | Mechanical part surface defect detecting device based on image texture and fractal dimension | |
| CN104096686A (en) | Product packing box surface printing quality automatic detection device | |
| CN103439620A (en) | Automatic detecting device and detecting method for piezoelectric ceramics buzzer electric performance | |
| CN102735689A (en) | Paper defect detection system based on image pattern recognition | |
| CN117409005A (en) | Defective product detection system and method for plate receiving machine based on image | |
| CN102980536B (en) | Brake block steel back flatness detection system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100915 Termination date: 20121202 |