CN103837098A - Screen test device and method - Google Patents
Screen test device and method Download PDFInfo
- Publication number
- CN103837098A CN103837098A CN201210486574.5A CN201210486574A CN103837098A CN 103837098 A CN103837098 A CN 103837098A CN 201210486574 A CN201210486574 A CN 201210486574A CN 103837098 A CN103837098 A CN 103837098A
- Authority
- CN
- China
- Prior art keywords
- screen
- straight line
- image
- information
- module
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a screen test device which includes an image acquisition module, a preprocessing module, an edge extraction module, a line extraction module and a test module. The image acquisition module acquires an image of a to-be-tested screen; the preprocessing module grays the image to obtain a gray image; the edge extraction module extracts edge information from the gray image; the line extraction module extracts line information from the edge information; and according to the line information, the test module determines whether an edge corner of a screen is qualified. According to the screen test device and method of the invention, compared with the prior art, the screen test method combining the computer vision and the pattern recognition is adopted, so that the computation time is reduced and the system processing speed is accelerated.
Description
Technical field
The present invention relates to a kind of industrial detection field, relate in particular to a kind of screen monitoring device and method.
Background technology
In industrial detection, usually to detect the making fineness of mobile phone screen.In the mobile phone screen testing process of prior art, the multiple camera joint-detection of some employings, this method depends on resolution and the sharpness of camera, and accuracy of detection is uncontrollable; The method that some employing computer vision and pattern-recognition combine detects screen shape, and the algorithm complex of this method is higher, and testing process relatively expends time in, and is difficult for promoting in large batch of commercial production.
Summary of the invention
The present invention is intended to solve above-mentioned problems of the prior art, proposes a kind of screen pick-up unit and method.
The screen pick-up unit that one aspect of the present invention proposes comprises: image collection module, pretreatment module, edge extracting module, straight line extraction module and detection module.Wherein, described image collection module is obtained the image of screen to be detected; Described pretreatment module, by described image gray processing, obtains gray level image; Described edge extracting module extracts marginal information from described gray level image; Described straight line extraction module extracts straight line information from described marginal information; Described detection module judges that according to described straight line information whether described screen edges and corners are qualified.
The screen detection method that the present invention proposes on the other hand comprises the following steps: the image that obtains screen to be detected; Described image is carried out to gray processing processing, obtain gray level image; From described gray level image, extract marginal information; From described marginal information, extract straight line information; Judge that whether described screen edges and corners are qualified.
The screen pick-up unit that the present invention proposes and method, than the screen detection method of available technology adopting computer vision binding pattern identification, have reduced operation time, have accelerated system processing speed.
Accompanying drawing explanation
Fig. 1 is the screen structure of the detecting device figure of one embodiment of the invention;
Fig. 2 is the screen detection method process flow diagram of one embodiment of the invention.
Embodiment
In order to make object of the present invention, technical scheme and advantage more clear, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Whether screen pick-up unit and method that the present invention proposes be qualified for detection of electronic equipment screen corner technique, and particularly, whether described screen pick-up unit and method be vertical for detection of two straight lines that form described screen edges and corners.
One aspect of the present invention discloses a kind of screen pick-up unit.Figure 1 shows that the screen pick-up unit of one embodiment of the invention, described screen pick-up unit comprises: image collection module 100, pretreatment module 200, edge extracting module 300, straight line extraction module 400 and detection module 500.
Wherein, described image collection module 100 is obtained the image of screen to be detected.Particularly, described image collection module 100 is CCD camera, and described image collection module 100 is taken described electronic equipment screen, obtains the image of described electronic equipment screen.
Described pretreatment module 200 is carried out gray processing processing to above-mentioned image, obtains gray level image.In the present embodiment, in described gray level image the gray-scale value of each pixel in scope 0~255.In a preferred embodiment, first described pretreatment module 200 carries out filtering processing to described image, filtering noise information, then by described image gray processing, obtain gray level image.
Described edge extracting module 300 extracts marginal information from described gray level image.In the present embodiment, the program of Boundary extracting algorithm that described edge extracting module 300 is pre-stored, described Boundary extracting algorithm is the one in Canny, Sobel, Prewitt scheduling algorithm.
Described straight line extraction module 400 extracts straight line information from described marginal information.The program of Straight Line Extraction that described straight line extraction module 400 is pre-stored, in the present embodiment, adopts Hough algorithm from described marginal information, to extract described straight line information.Because screen pick-up unit of the present invention is whether two straight lines to forming described screen edges and corners vertically detect, therefore, 400 of described straight line extraction modules need extract level of approximation and approximately perpendicular straight line from described marginal information.Particularly, adopt Hough algorithm that the described marginal information in polar coordinate space is converted into (ρ, θ) parameter space extracting after straight line information, obtains a series of original straight line information, and described original straight line information and horizontal are mutually certain angle.In the present embodiment, the θ value scope of straight line to be extracted is arranged on 90 ° ± 3 ° and 0 ° ± 3 ° by described straight line extraction module 400, and then from described original straight line information, obtain being less than one group of straight line A of 3 ° and the one group of straight line B that is less than 3 ° with vertical direction angle with horizontal direction angle, wherein, above-mentioned straight line group A is corresponding to the perpendicular edge that forms screen edges and corners to be detected, and straight line group B is corresponding to the horizontal sides that forms screen edges and corners to be detected.
Described detection module 500 judges that according to above-mentioned straight line group A, B whether described screen edges and corners are qualified.Particularly, described detection module 500 finds whether there are orthogonal two straight lines in described straight line group A and straight line group B, if having, shows to form between two straight lines of described screen edges and corners to be detected mutually vertical, and described screen edges and corners technique to be detected is qualified; If nothing, shows to form between two straight lines of described screen edges and corners to be detected out of plumb mutually, described screen edges and corners technique to be detected is defective.
The present invention discloses a kind of screen detection method on the other hand.Figure 2 shows that the screen detection method of an embodiment.
Step S100 is the image that obtains screen to be detected.In the present embodiment, adopt CCD camera to take described electronic equipment screen, obtain the image of described electronic equipment screen.
Step S200, for above-mentioned image is carried out to gray processing processing, obtains gray level image.In the present embodiment, in described gray level image the gray-scale value of each pixel in scope 0~255.In a preferred embodiment, first described image is carried out to filtering processing, filtering noise information, then by described image gray processing, obtain gray level image.
Step S300 for to extract marginal information from described gray level image.In the present embodiment, adopt the one in the edge detection algorithms such as Canny, Sobel, Prewitt to extract marginal information from described gray level image.
Step S400 for extracting straight line information from described marginal information.In the present embodiment, adopt Hough algorithm from described marginal information, to extract described straight line information.The screen detection method proposing due to the present invention is whether two straight lines to forming described screen edges and corners vertically detect, and therefore, only need from described marginal information, extract level of approximation and approximately perpendicular straight line.Particularly, adopt Hough algorithm that the described marginal information in polar coordinate space is converted into (ρ, θ) parameter space extracting after straight line information, obtains a series of original straight line information, and described original straight line information and horizontal are mutually certain angle.In the present embodiment, the scope of θ value is arranged on 90 ° ± 3 ° and 0 ° ± 3 °, and then from described original straight line information, obtain being less than one group of straight line A of 3 ° and the one group of straight line B that is less than 3 ° with vertical direction angle with horizontal direction angle, wherein, above-mentioned straight line group A is corresponding to the perpendicular edge that forms screen edges and corners to be detected, and straight line group B is corresponding to the horizontal sides that forms screen edges and corners to be detected.
Step S500 is for to judge that according to above-mentioned straight line group A, B whether described screen edges and corners are qualified.Particularly, in described straight line group A and straight line group B, find whether there are orthogonal two straight lines, if having, show to form between two straight lines of described screen edges and corners to be detected mutually vertical, described screen edges and corners technique to be detected is qualified; If nothing, shows to form between two straight lines of described screen edges and corners to be detected out of plumb mutually, described screen edges and corners technique to be detected is defective.
The screen pick-up unit that the present invention proposes and method can be used for big batch and detect.Particularly, the electronic equipment screen to be detected of some is placed on a displacement platform, and described image collection module 100 timings are taken each piece electronic equipment screen, then carry out a series of subsequent detection operations again, concrete grammar as described above, does not repeat them here.
The screen pick-up unit that the present invention proposes and method are than the screen detection method of available technology adopting computer vision binding pattern identification, algorithm and flow process are simple, and in described straight line extraction module 400 and step S400 the scope of angle θ value be arranged on one more among a small circle in, reduce operation time, accelerated system processing speed.
Although the present invention is described with reference to current preferred embodiments; but those skilled in the art will be understood that; above-mentioned preferred embodiments is only used for illustrating the present invention; not be used for limiting protection scope of the present invention; any within the spirit and principles in the present invention scope; any modification of doing, equivalent replacement, improvement etc., within all should being included in the scope of the present invention.
Claims (12)
1. a screen pick-up unit, is characterized in that, comprising: image collection module, pretreatment module, edge extracting module, straight line extraction module and detection module, wherein,
Described image collection module is obtained the image of screen to be detected;
Described pretreatment module, by described image gray processing, obtains gray level image;
Described edge extracting module extracts marginal information from described gray level image;
Described straight line extraction module extracts straight line information from described marginal information;
Described detection module judges that according to described straight line information whether described screen edges and corners are qualified.
2. screen pick-up unit according to claim 1, is characterized in that, described image collection module is CCD camera.
3. screen pick-up unit according to claim 1, is characterized in that, described pretreatment module is carried out filtering processing to described image, filtering noise information, then by described image gray processing, obtain gray level image.
4. screen pick-up unit according to claim 1, is characterized in that, described edge extracting module adopts Canny edge detection algorithm from described gray level image, to extract described marginal information.
5. screen pick-up unit according to claim 1, it is characterized in that, described straight line extraction module adopts Hough algorithm, from described marginal information, extract original straight line information, from described original straight line information, extract described straight line information again, wherein, the straight line in described straight line information and the angle of horizontal or vertical direction are less than 3 degree.
6. screen pick-up unit according to claim 1, is characterized in that, described detection module judges that according to described straight line information whether two straight lines of the described screen edges and corners of formation are vertical.
7. a screen detection method, is characterized in that, comprises the following steps:
Obtain the image of screen to be detected;
Described image is carried out to gray processing processing, obtain gray level image;
From described gray level image, extract marginal information;
From described marginal information, extract straight line information;
Judge that whether described screen edges and corners are qualified.
8. screen detection method according to claim 6, is characterized in that, adopts CCD camera to obtain the image of screen to be detected.
9. screen detection method according to claim 6, is characterized in that, before described image is carried out to gray processing processing, described image is carried out to filtering processing, filtering noise information.
10. screen detection method according to claim 6, is characterized in that, adopts Canny edge detection algorithm from described gray level image, to extract described marginal information.
11. screen detection methods according to claim 6, it is characterized in that, adopt Hough mapping algorithm from described marginal information, to extract original straight line information, from described original straight line information, extract described straight line information again, wherein, the straight line in described straight line information and the angle of horizontal or vertical direction are less than 3 degree.
12. screen detection methods according to claim 6, is characterized in that, judge that whether two straight lines of the described screen edges and corners of formation are vertical according to described straight line information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210486574.5A CN103837098A (en) | 2012-11-23 | 2012-11-23 | Screen test device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210486574.5A CN103837098A (en) | 2012-11-23 | 2012-11-23 | Screen test device and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103837098A true CN103837098A (en) | 2014-06-04 |
Family
ID=50800830
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210486574.5A Pending CN103837098A (en) | 2012-11-23 | 2012-11-23 | Screen test device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103837098A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104459101A (en) * | 2014-11-27 | 2015-03-25 | 中国科学院长春光学精密机械与物理研究所 | Enzyme-linked immune spot analysis device and method |
CN109584979A (en) * | 2018-11-07 | 2019-04-05 | 深圳市新起点健康服务有限公司 | A kind of prescription electronization method based on image procossing |
CN114612695A (en) * | 2022-03-11 | 2022-06-10 | 江阴市浩盛电器线缆制造有限公司 | Embedded wiring rule judging system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040165786A1 (en) * | 2003-02-22 | 2004-08-26 | Zhengyou Zhang | System and method for converting whiteboard content into an electronic document |
CN101608924A (en) * | 2009-05-20 | 2009-12-23 | 电子科技大学 | A kind of method for detecting lane lines based on gray scale estimation and cascade Hough transform |
CN102236784A (en) * | 2010-05-07 | 2011-11-09 | 株式会社理光 | Screen area detection method and system |
CN102254159A (en) * | 2011-07-07 | 2011-11-23 | 清华大学深圳研究生院 | Interpretation method for digital readout instrument |
-
2012
- 2012-11-23 CN CN201210486574.5A patent/CN103837098A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040165786A1 (en) * | 2003-02-22 | 2004-08-26 | Zhengyou Zhang | System and method for converting whiteboard content into an electronic document |
CN101608924A (en) * | 2009-05-20 | 2009-12-23 | 电子科技大学 | A kind of method for detecting lane lines based on gray scale estimation and cascade Hough transform |
CN102236784A (en) * | 2010-05-07 | 2011-11-09 | 株式会社理光 | Screen area detection method and system |
CN102254159A (en) * | 2011-07-07 | 2011-11-23 | 清华大学深圳研究生院 | Interpretation method for digital readout instrument |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104459101A (en) * | 2014-11-27 | 2015-03-25 | 中国科学院长春光学精密机械与物理研究所 | Enzyme-linked immune spot analysis device and method |
CN109584979A (en) * | 2018-11-07 | 2019-04-05 | 深圳市新起点健康服务有限公司 | A kind of prescription electronization method based on image procossing |
CN114612695A (en) * | 2022-03-11 | 2022-06-10 | 江阴市浩盛电器线缆制造有限公司 | Embedded wiring rule judging system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102393397B (en) | System and method for detecting surface defects of magnetic shoe | |
CN109839385B (en) | Self-adaptive PCB defect visual positioning detection and classification system | |
CN109752392B (en) | PCB defect type detection system and method | |
CN108982512A (en) | A kind of circuit board detecting system and method based on machine vision | |
CN104506857A (en) | Camera position deviation detection method and device | |
CN101995223A (en) | Chip appearance detection method and system | |
CN110111330B (en) | Mobile phone screen detection method | |
CN113030121B (en) | Automatic optical detection method, system and equipment for circuit board components | |
CN109781737B (en) | Detection method and detection system for surface defects of hose | |
CN111815565B (en) | Wafer backside detection method, equipment and storage medium | |
CN109785294A (en) | A kind of pcb board defective locations detection system and method | |
CN111223078B (en) | Method for determining flaw level and storage medium | |
CN106815830B (en) | Image defect detection method | |
CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
JP6197340B2 (en) | Image processing apparatus, image processing method, and program | |
CN111257329A (en) | Smartphone camera defect detection method and detection system | |
CN110807765A (en) | Suspension insulator string inclination detection method and system based on image processing | |
CN105205803A (en) | Display panel defect detection method | |
US20170125271A1 (en) | Position detection apparatus, position detection method, information processing program, and storage medium | |
CN113850786A (en) | Method and device for detecting vehicle door gap parameters and measuring equipment | |
CN103837098A (en) | Screen test device and method | |
CN114998217A (en) | Method for determining defect grade of glass substrate, computer device and storage medium | |
CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
CN112419225B (en) | SOP type chip detection method and system based on pin segmentation | |
CN113177941A (en) | Steel coil edge crack identification method, system, medium and terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20140604 |