CN106790898A - A kind of mobile phone screen bad point automatic testing method and system based on significance analysis - Google Patents
A kind of mobile phone screen bad point automatic testing method and system based on significance analysis Download PDFInfo
- Publication number
- CN106790898A CN106790898A CN201611119578.4A CN201611119578A CN106790898A CN 106790898 A CN106790898 A CN 106790898A CN 201611119578 A CN201611119578 A CN 201611119578A CN 106790898 A CN106790898 A CN 106790898A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- phone screen
- image
- bad point
- region
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/24—Arrangements for testing
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of mobile phone screen bad point automatic testing method based on significance analysis, the method determines mobile phone screen region using projection with reference to the method that angle point is analyzed first；Afterwards according to positioning result and mobile phone screen field color information extraction mobile phone screen region image data；Significance analysis are carried out to mobile phone screen area image afterwards and obtains comprehensive notable figure；Salient region is extracted by comprehensive notable figure afterwards；The marking area for extracting is marked using projection mark method afterwards and obtains mobile phone screen bad point region；The last mobile phone screen bad point extracted region bad point information by marking.The invention allows for a kind of mobile phone screen bad point automatic checkout system based on significance analysis, technical solution of the present invention utilizes the conspicuousness feature of bad point, consider the bad point of various yardsticks, using traversal mode, bad point region is enhanced in the comprehensive notable figure for obtaining, ambient noise is effectively inhibited simultaneously, is conducive to improving the verification and measurement ratio of mobile phone screen bad point.
Description
Technical field
The invention belongs to technical field of image processing, more particularly, to a kind of mobile phone screen based on significance analysis
Bad point automatic testing method.
Background technology
Mobile phone screen bad point is one of major defect of mobile phone quality, and manual method inspection is used in conventional mobile phone production line
There is certain subjectivity in mobile phone screen bad point, manual detection, there is the possibility that erroneous judgement is failed to judge, and with mobile phone screen resolution ratio
More and more higher, manual detection efficiency is more and more lower.Using the mobile phone screen bad point automatic testing method of view-based access control model to effectively inspection
Survey mobile phone screen bad point and check that mobile phone screen quality has great significance.
It is few in the prior art of the mobile phone screen dead pixel detection method of view-based access control model, the mobile phone screen of existing view-based access control model
Dead pixel detection method has two classes.One class is the method based on gradation of image statistical nature, i.e., using average, variance, intensity histogram
The first-order statistical properties, such as k- mean clusters dividing method, edge detection method such as figure, this kind of method are calculated compared with simple realization speed
Degree is fast, but in the case where contrast is low, flase drop and missing inspection easily occurs.Another kind of is the method based on transform domain, such as base
In the defect inspection method of Fourier transform, image is transformed to transform domain by this kind of method, the another mistake after transform domain is processed
Spatial domain is transformed to, this kind of method, into line translation and inverse transformation, is calculated and taken very much, it is impossible to meet on-line real-time measuremen due to needing
Requirement.
The content of the invention
For the disadvantages described above or Improvement requirement of prior art, the invention provides a kind of mobile phone based on significance analysis
Screen bad point automatic testing method, its object is to using bad point conspicuousness feature, it is considered to the bad point of various yardsticks, using time
Mode is gone through, bad point region is enhanced in the comprehensive notable figure for obtaining, while effectively inhibiting ambient noise, thus solve existing hand
Machine screen bad point automatic testing method inefficiency, the technology for easily flase drop and missing inspection or processing procedure excessively complicated and time consumption occur are asked
Topic.
To achieve the above object, according to one aspect of the present invention, there is provided a kind of Mobile phone screen based on significance analysis
Curtain bad point automatic testing method, the method is comprised the following steps：
(1) mobile phone screen region is determined with the method that angle point analysis is combined using projection to mobile phone screen picture；
(2) according to mobile phone screen region and mobile phone screen color extraction mobile phone screen region image data；
(3) significance analysis are carried out to mobile phone screen area view data and obtains comprehensive notable figure；
(4) salient region is extracted by comprehensive notable figure；
(5) reprojection is carried out to salient region and marks mobile phone screen bad point region；
(6) the mobile phone screen bad point extracted region bad point information by marking.
Further, the step (1) includes following sub-step：
(11) row threshold division is entered to mobile phone screen picture and obtains binary image；
(12) projection for being carried out respectively to binary image both horizontally and vertically obtains projection both horizontally and vertically
Curve；
(13) endpoint location and peak of drop shadow curve both horizontally and vertically are obtained；
(14) endpoint location and peak of drop shadow curve both horizontally and vertically are combined and obtain image angle
Point coordinates；
(15) neighborhood information of each angular coordinate is analyzed, mobile phone screen angular coordinate is determined.
Further, the step (2) includes following sub-step：
(21) mobile phone screen angle of inclination is calculated according to mobile phone screen angular coordinate；
(22) mobile phone screen image rotation respective angles；
(23) the mobile phone screen region image data conduct of the color extraction respective color passage according to mobile phone screen region
Follow-up pending view data.
Further, the step (3) includes following sub-step：
(31) the integral image R of the pending view data of calculated for subsequent；
(32) the interior window size IN of conspicuousness operator is set；
(33) the yardstick s of conspicuousness operator is set；
(34) the exterior window size OUT of the dimension calculation conspicuousness operator according to setting；
(35) by the pending image upper left corner, inside and outside window center is overlapped, and interior window gradation of image is calculated by integral image R
Average and exterior window gradation of image average, calculate the difference of interior exterior window gray average as the saliency value of inside and outside window center coordinate position,
Travel through the notable figure that interior window size IN yardsticks s is obtained after pending image；
(36) value of adjustment yardstick s, repeat step (34) to (35) calculates interior window size IN's until completing all yardsticks
The average image of the notable figure of all yardstick s as interior window size IN notable figure；
(37) window size IN in adjusting, repeat step (33) to (36) is calculated until all interior window size for completing to set
The average image of all interior window size notable figures is used as comprehensive notable figure S.
It is another aspect of this invention to provide that there is provided a kind of mobile phone screen bad point automatic detection system based on significance analysis
System, the system is included with lower module：
Screen locating module, for determining mobile phone with the method that angle point analysis is combined using projection to mobile phone screen picture
Screen area；
On-screen data extraction module, for according to mobile phone screen region and mobile phone screen color extraction mobile phone screen administrative division map
As data；
Notable figure determining module, obtains comprehensive notable for carrying out significance analysis to mobile phone screen area view data
Figure；
Marking area determining module, for extracting salient region by comprehensive notable figure；
Bad point mark module, mobile phone screen bad point region is marked for carrying out reprojection to salient region；
Bad point information extraction modules, for the mobile phone screen bad point extracted region bad point information by marking.
Further, the screen locating module is included with lower unit：
Binarization unit, binary image is obtained for entering row threshold division to mobile phone screen picture；
Projecting cell, the projection for being carried out respectively to binary image both horizontally and vertically obtains horizontal and vertical side
To drop shadow curve；
Extreme value determining unit, endpoint location and peak for obtaining drop shadow curve both horizontally and vertically；
Corner character unit, for the endpoint location and peak of drop shadow curve both horizontally and vertically to be carried out into group
Conjunction obtains image angular coordinate；
Screen positioning unit, the neighborhood information for analyzing each angular coordinate, determines mobile phone screen angular coordinate.
Further, the on-screen data extraction module is included with lower unit：
Inclination angle determining unit, for calculating mobile phone screen angle of inclination according to mobile phone screen angular coordinate；
Rotary unit, for mobile phone screen image rotation respective angles；
Image data extraction unit, for the mobile phone screen of the color extraction respective color passage according to mobile phone screen region
Region image data is used as follow-up pending view data.
Further, the notable figure determining module is included with lower unit：
Integral image computing unit, for the integral image R of the pending view data of calculated for subsequent；
Interior window size setting unit, the interior window size IN for setting conspicuousness operator；
Yardstick setup unit, the yardstick s for setting conspicuousness operator；
Exterior window dimension calculating unit, for the exterior window size OUT of the dimension calculation conspicuousness operator according to setting；
Image traversal unit, for by the pending image upper left corner, inside and outside window center overlaps, and is counted by integral image R
Window gradation of image average and exterior window gradation of image average in calculating, calculate the difference of interior exterior window gray average as inside and outside window center coordinate
The saliency value of position, obtains the notable figure of interior window size IN yardsticks s after the pending image of traversal；
Yardstick Traversal Unit, the value for adjusting yardstick s, repeat step (34) to (35) is until completing all yardsticks, meter
In calculating the average image of the notable figure of all yardstick s of window size IN as interior window size IN notable figure；
Interior window size Traversal Unit, for adjusting interior window size IN, repeat step (33) to (36) is until completing setting
All interior window sizes, calculate the average image of all interior window size notable figures as comprehensive notable figure S.
In general, by the contemplated above technical scheme of the present invention compared with prior art, it is special with following technology
Levy and beneficial effect：
(1) present invention is quickly positioned using the method that projection and angle point analysis are combined to mobile phone screen area；With
Prior art is compared, and the present invention combines angle point analysis method by projecting, and can improve interception mobile phone screen region
Reliability and processing speed.
(2) in its significance analysis treatment of the invention, using the conspicuousness feature of bad point, it is considered to the bad point of various yardsticks,
Using traversal mode, bad point region is enhanced in the comprehensive notable figure for obtaining, while effectively inhibiting ambient noise, be conducive to carrying
The verification and measurement ratio of high mobile phone screen bad point.
Brief description of the drawings
Fig. 1 is a kind of mobile phone screen dead pixel detection method flow chart based on significance analysis of the embodiment of the present invention；
Fig. 2 is the mobile phone screen area image of extraction in the embodiment of the present invention；
Fig. 3 is the mobile phone screen region image data of extraction in the embodiment of the present invention；
Fig. 4 is the method flow diagram of significance analysis in the embodiment of the present invention；
Fig. 5 is the comprehensive notable figure being calculated in the embodiment of the present invention；
Fig. 6 is the marking area obtained in the embodiment of the present invention；
Fig. 7 is mobile phone screen bad point mark result in the embodiment of the present invention；
Fig. 8 is mobile phone screen bad point information in the embodiment of the present invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as additionally, technical characteristic involved in invention described below each implementation method
Not constituting conflict each other can just be mutually combined.
Fig. 1 is the method flow diagram of the embodiment of the present invention, and the inventive method is comprised the following steps：
(1) mobile phone screen region is determined with the method that angle point analysis is combined using projection to mobile phone screen picture；
In the present embodiment, step (1) is specific to be divided into following sub-step again：
(11) row threshold division is entered to mobile phone screen picture and obtains binary image；
(12) projection for being carried out respectively to binary image both horizontally and vertically obtains projection both horizontally and vertically
Curve；
(13) endpoint location and peak of drop shadow curve both horizontally and vertically are obtained；
(14) endpoint location and peak of drop shadow curve both horizontally and vertically are combined as candidate's hand
Machine screen area angular coordinate, i.e., obtain 4 Y direction coordinates by horizontal direction projection, and 4 X are obtained by vertical direction projection
Direction coordinate, each X-direction coordinate obtains candidate angular coordinate (x, y) with each Y-direction combinatorial coordinates；
(15) neighborhood information of each candidate angular coordinate is analyzed, mobile phone screen angular coordinate is determined.
(2) according to mobile phone screen region and mobile phone screen color extraction mobile phone screen region image data；
In the present embodiment, step (2) is specific to be divided into following sub-step again：
(21) mobile phone screen angle of inclination is calculated according to mobile phone screen angular coordinate, that is, takes the mobile phone screen upper left corner and upper right
Two, angle angular coordinate (xl, yl) and (xr, yr), according to formulaCalculate screen inclination angle；
(22) mobile phone screen image rotation respective angles, gained mobile phone screen area image is shown in Fig. 2；
(23) the mobile phone screen region image data conduct of the color extraction respective color passage according to mobile phone screen region
Follow-up pending view data.In the present embodiment, view data is rgb format, mobile phone screen region may for red, green or
Blueness, such as mobile phone screen region are red, then R channel datas are taken in view data as follow-up pending view data, with ash
Degree image shows sees Fig. 3.
(3) significance analysis are carried out to mobile phone screen area view data and obtains comprehensive notable figure；
As shown in figure 4, in the present embodiment, step (3) is specific to be divided into following sub-step again：
(31) the integral image R of pending view data is calculated；
(32) the interior window size IN of conspicuousness operator is set；
(33) the yardstick s of conspicuousness operator is set；
(34) the exterior window size OUT of the dimension calculation conspicuousness operator according to setting；
(35) by the pending image upper left corner, inside and outside window center is overlapped, and interior window gradation of image is calculated by integral image R
Average and exterior window gradation of image average, calculate the difference of interior exterior window gray average as the saliency value of inside and outside window center coordinate position,
Travel through the notable figure that interior window size IN yardsticks s is obtained after pending image；
(36) value of adjustment yardstick s, repeat step (34) to (35) calculates interior window size IN's until completing all yardsticks
The average image of the notable figure of all yardstick s obtains the notable figure of interior window size IN；
(37) window size IN in adjusting, repeat step (33) to (36) is calculated until all interior window size for completing to set
The average image of all interior window size notable figures obtains comprehensive notable figure S, as shown in Figure 5.
(4) salient region is extracted by comprehensive notable figure；
Step (4) selection enters row threshold division using k averaging methods to comprehensive notable figure in the present embodiment, i.e., by formula Th=
μ+k σ calculate segmentation threshold, and wherein μ is the average of comprehensive notable figure, and σ is the variance of comprehensive notable figure, and k is selected coefficient, point
Salient region is obtained after cutting, as shown in Figure 6.
(5) reprojection is carried out to salient region and marks mobile phone screen bad point region；
Step (5) selection is entered using projection mark method twice to the segmentation result image that step (4) is obtained in the present embodiment
Line flag, carries out horizontal direction projection to the bianry image obtained after segmentation first, obtains horizontal direction drop shadow curve, it is determined that throwing
Nonzero value curved section in shadow curve, then each nonzero value curved section carry out vertical direction projection, determine vertical direction project
Nonzero value curved section in curve, so as to obtain first time projection mark region, then repeats said process in each marked region,
Final projection mark result is obtained, as shown in Figure 7.
(6) the mobile phone screen bad point extracted region bad point information by marking；
Step (6) is to the mobile phone screen bad point range statistics bad point area that marks in the present embodiment, and according to following public affairs
Formula calculates the centre of form coordinate of bad point,
Wherein xiAnd yiMobile phone screen bad point area pixel coordinate in the x and y directions is represented, Area represents bad point area
Domain pixel total number, is illustrated in figure 8 bad point information.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, it is all in essence of the invention
Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.
Claims (8)
1. a kind of mobile phone screen bad point automatic testing method based on significance analysis, it is characterised in that the method includes：
(1) mobile phone screen region is determined with the method that angle point analysis is combined using projection to mobile phone screen picture；
(2) according to mobile phone screen region and mobile phone screen color extraction mobile phone screen region image data；
(3) significance analysis are carried out to mobile phone screen area view data and obtains comprehensive notable figure；
(4) salient region is extracted by comprehensive notable figure；
(5) reprojection is carried out to salient region and marks mobile phone screen bad point region；
(6) the mobile phone screen bad point extracted region bad point information by marking.
2. a kind of mobile phone screen bad point automatic testing method based on significance analysis according to claim 1, its feature
It is that the step (1) includes following sub-step：
(11) row threshold division is entered to mobile phone screen picture and obtains binary image；
(12) projection for being carried out respectively to binary image both horizontally and vertically obtains drop shadow curve both horizontally and vertically；
(13) endpoint location and peak of drop shadow curve both horizontally and vertically are obtained；
(14) endpoint location and peak of drop shadow curve both horizontally and vertically are combined and obtain image angle point seat
Mark；
(15) neighborhood information of each angular coordinate is analyzed, mobile phone screen angular coordinate is determined.
3. a kind of mobile phone screen bad point automatic testing method based on significance analysis according to claim 1, its feature
It is that the step (2) includes following sub-step：
(21) mobile phone screen angle of inclination is calculated according to mobile phone screen angular coordinate；
(22) mobile phone screen image rotation respective angles；
(23) the mobile phone screen region image data of the color extraction respective color passage according to mobile phone screen region is used as follow-up
Pending view data.
4. a kind of mobile phone screen bad point automatic testing method based on significance analysis according to claim 1, its feature
It is that the step (3) includes following sub-step：
(31) the integral image R of the pending view data of calculated for subsequent；
(32) the interior window size IN of conspicuousness operator is set；
(33) the yardstick s of conspicuousness operator is set；
(34) the exterior window size OUT of the dimension calculation conspicuousness operator according to setting；
(35) by the pending image upper left corner, inside and outside window center is overlapped, and interior window gradation of image average is calculated by integral image R
With exterior window gradation of image average, the difference of interior exterior window gray average is calculated as the saliency value of inside and outside window center coordinate position, traversal
The notable figure of interior window size IN yardsticks s is obtained after pending image；
(36) value of adjustment yardstick s, repeat step (34) to (35) calculates all of interior window size IN until completing all yardsticks
The average image of the notable figure of yardstick s as interior window size IN notable figure；
(37) window size IN in adjusting, repeat step (33) to (36) calculates all until all interior window size for completing to set
The average image of interior window size notable figure is used as comprehensive notable figure S.
5. a kind of mobile phone screen bad point automatic checkout system based on significance analysis, it is characterised in that the system includes following
Module：
Screen locating module, for determining mobile phone screen with the method that angle point analysis is combined using projection to mobile phone screen picture
Region；
On-screen data extraction module, for according to mobile phone screen region and mobile phone screen color extraction mobile phone screen area image number
According to；
Notable figure determining module, comprehensive notable figure is obtained for carrying out significance analysis to mobile phone screen area view data；
Marking area determining module, for extracting salient region by comprehensive notable figure；
Bad point mark module, mobile phone screen bad point region is marked for carrying out reprojection to salient region；
Bad point information extraction modules, for the mobile phone screen bad point extracted region bad point information by marking.
6. a kind of mobile phone screen bad point automatic checkout system based on significance analysis according to claim 5, its feature
It is that the screen locating module is included with lower unit：
Binarization unit, binary image is obtained for entering row threshold division to mobile phone screen picture；
Projecting cell, the projection for being carried out respectively to binary image both horizontally and vertically is obtained both horizontally and vertically
Drop shadow curve；
Extreme value determining unit, endpoint location and peak for obtaining drop shadow curve both horizontally and vertically；
Corner character unit, for the endpoint location and peak of drop shadow curve both horizontally and vertically to be combined
To image angular coordinate；
Screen positioning unit, the neighborhood information for analyzing each angular coordinate, determines mobile phone screen angular coordinate.
7. a kind of mobile phone screen bad point automatic checkout system based on significance analysis according to claim 5, its feature
It is that the on-screen data extraction module is included with lower unit：
Inclination angle determining unit, for calculating mobile phone screen angle of inclination according to mobile phone screen angular coordinate；
Rotary unit, for mobile phone screen image rotation respective angles；
Image data extraction unit, for the mobile phone screen region of the color extraction respective color passage according to mobile phone screen region
View data is used as follow-up pending view data.
8. a kind of mobile phone screen bad point automatic checkout system based on significance analysis according to claim 5, its feature
It is that the notable figure determining module is included with lower unit：
Integral image computing unit, for the integral image R of the pending view data of calculated for subsequent；
Interior window size setting unit, the interior window size IN for setting conspicuousness operator；
Yardstick setup unit, the yardstick s for setting conspicuousness operator；
Exterior window dimension calculating unit, for the exterior window size OUT of the dimension calculation conspicuousness operator according to setting；
Image traversal unit, for by the pending image upper left corner, inside and outside window center overlaps, and calculates interior by integral image R
Window gradation of image average and exterior window gradation of image average, calculate the difference of interior exterior window gray average as inside and outside window center coordinate position
Saliency value, travel through the notable figure that interior window size IN yardsticks s is obtained after pending image；
Yardstick Traversal Unit, the value for adjusting yardstick s, repeat step (34) to (35) calculates interior until completing all yardsticks
The average image of the notable figure of all yardstick s of window size IN as interior window size IN notable figure；
Interior window size Traversal Unit, for adjusting interior window size IN, repeat step (33) to (36) is until completing all of setting
Interior window size, calculates the average image of all interior window size notable figures as comprehensive notable figure S.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611119578.4A CN106790898B (en) | 2016-12-08 | 2016-12-08 | A kind of mobile phone screen bad point automatic testing method and system based on significance analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611119578.4A CN106790898B (en) | 2016-12-08 | 2016-12-08 | A kind of mobile phone screen bad point automatic testing method and system based on significance analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106790898A true CN106790898A (en) | 2017-05-31 |
| CN106790898B CN106790898B (en) | 2019-06-18 |
Family
ID=58882369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611119578.4A Active CN106790898B (en) | 2016-12-08 | 2016-12-08 | A kind of mobile phone screen bad point automatic testing method and system based on significance analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106790898B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109801322A (en) * | 2017-11-16 | 2019-05-24 | 合肥欣奕华智能机器有限公司 | A kind of light leak test method and device |
| CN110084801A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of detection method of terminal screen, device, portable terminal and storage medium |
| CN110418124A (en) * | 2019-08-05 | 2019-11-05 | 歌尔股份有限公司 | Projected image detection method, device, equipment and computer readable storage medium |
| CN111046869A (en) * | 2019-11-27 | 2020-04-21 | 北京联合大学 | Salient region extraction method and system based on deep learning |
| CN117078672A (en) * | 2023-10-13 | 2023-11-17 | 深圳市凯尔文电子有限公司 | Intelligent detection method for mobile phone screen defects based on computer vision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1510997A1 (en) * | 2003-08-25 | 2005-03-02 | Agfa-Gevaert | Method and user interface for detecting dead pixels in a display device. |
| CN101446695A (en) * | 2007-11-26 | 2009-06-03 | 均豪精密工业股份有限公司 | Bad point detection and addressing method of liquid crystal display panel |
| CN106093066A (en) * | 2016-06-24 | 2016-11-09 | 安徽工业大学 | A kind of magnetic tile surface defect detection method based on the machine vision attention mechanism improved |
-
2016
- 2016-12-08 CN CN201611119578.4A patent/CN106790898B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1510997A1 (en) * | 2003-08-25 | 2005-03-02 | Agfa-Gevaert | Method and user interface for detecting dead pixels in a display device. |
| CN101446695A (en) * | 2007-11-26 | 2009-06-03 | 均豪精密工业股份有限公司 | Bad point detection and addressing method of liquid crystal display panel |
| CN106093066A (en) * | 2016-06-24 | 2016-11-09 | 安徽工业大学 | A kind of magnetic tile surface defect detection method based on the machine vision attention mechanism improved |
Non-Patent Citations (2)
| Title |
|---|
| 刘波: "手机屏幕图像缺陷检测方法的研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 赵敏岑: "基于计算机视觉的驾驶员疲劳检测技术的研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109801322A (en) * | 2017-11-16 | 2019-05-24 | 合肥欣奕华智能机器有限公司 | A kind of light leak test method and device |
| CN110084801A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of detection method of terminal screen, device, portable terminal and storage medium |
| CN110418124A (en) * | 2019-08-05 | 2019-11-05 | 歌尔股份有限公司 | Projected image detection method, device, equipment and computer readable storage medium |
| CN111046869A (en) * | 2019-11-27 | 2020-04-21 | 北京联合大学 | Salient region extraction method and system based on deep learning |
| CN111046869B (en) * | 2019-11-27 | 2023-09-29 | 北京腾信软创科技股份有限公司 | Salient region extraction method and system based on deep learning |
| CN117078672A (en) * | 2023-10-13 | 2023-11-17 | 深圳市凯尔文电子有限公司 | Intelligent detection method for mobile phone screen defects based on computer vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106790898B (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106790898B (en) | A kind of mobile phone screen bad point automatic testing method and system based on significance analysis | |
| CN109615611B (en) | Inspection image-based insulator self-explosion defect detection method | |
| CN105957059B (en) | Electronic component missing detection method and system | |
| CN106340044B (en) | Join automatic calibration method and caliberating device outside video camera | |
| WO2019080229A1 (en) | Chess piece positioning method and system based on machine vision, storage medium, and robot | |
| CN103927741B (en) | SAR image synthesis method for enhancing target characteristics | |
| CN109447067B (en) | Bill direction detection and correction method and automatic bill checking system | |
| CN104568986A (en) | Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm | |
| CN103810491B (en) | Head posture estimation interest point detection method fusing depth and gray scale image characteristic points | |
| CN109460762B (en) | Answer sheet scoring method based on image recognition | |
| CN109671068B (en) | Abdominal muscle labeling method and device based on deep learning | |
| CN109409190A (en) | Pedestrian detection method based on histogram of gradients and Canny edge detector | |
| CN106803286A (en) | Mutual occlusion real-time processing method based on multi-view image | |
| CN102629322B (en) | Character feature extraction method based on stroke shape of boundary point and application thereof | |
| CN102609941A (en) | Three-dimensional registering method based on ToF (Time-of-Flight) depth camera | |
| CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
| CN104616275A (en) | Defect detecting method and defect detecting device | |
| CN103345755A (en) | Chessboard angular point sub-pixel extraction method based on Harris operator | |
| CN106778737A (en) | A kind of car plate antidote, device and a kind of video acquisition device | |
| CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
| CN109145708A (en) | A kind of people flow rate statistical method based on the fusion of RGB and D information | |
| CN105869085A (en) | Transcript inputting system and method for processing images | |
| CN101533466B (en) | Image processing method for positioning eyes | |
| CN110473184A (en) | A kind of pcb board defect inspection method | |
| CN107239743B (en) | automatic detection method for scale mark reading based on projection 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 |