CN103996015B - A kind of method and device to 3D rendering identification - Google Patents
A kind of method and device to 3D rendering identification Download PDFInfo
- Publication number
- CN103996015B CN103996015B CN201310443404.3A CN201310443404A CN103996015B CN 103996015 B CN103996015 B CN 103996015B CN 201310443404 A CN201310443404 A CN 201310443404A CN 103996015 B CN103996015 B CN 103996015B
- Authority
- CN
- China
- Prior art keywords
- rendering
- image
- angle point
- corner detection
- algorithm
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N2013/0074—Stereoscopic image analysis
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of method and device to 3D rendering identification, wherein, method includes flow process: a. input picture；B. by image procossing be left and right gray level image；C. by Corner Detection Algorithm, left and right gray level image is sought angle point respectively；D. with corner correspondence, the angle point of two width images is mated；E. with the coupling angle point rejecting algorithm rejecting mistake；F. judging that logarithm that the angle point of two width images matches whether >=N, the most described image is 3D rendering, if it is not, the most described image is non-3D rendering.By the way, the method and device to 3D rendering identification that the present invention provides can automatic distinguishing 3D rendering and non-3D rendering, it is not necessary to user the most with the naked eye differentiates, and can save time and the muscle power of user.
Description
Technical field
The present invention relates to image procossing and field of image recognition, particularly relate to a kind of to 3D rendering
The method and device identified.
Background technology
Existing algorithm does not provide knows method for distinguishing, Ren Menxu to 3D rendering and non-3D rendering
Be 3D rendering with visually observing differentiation, this method takes time and effort.
For solving above-mentioned technical problem, the present invention provides the method and device of a kind of full-automation to come district
Divide 3D rendering and non-3D rendering, it is not necessary to go carefully to differentiate by people's naked eyes again.
Summary of the invention
The present invention provides a kind of method and device to 3D rendering identification, by by image procossing being
Left and right gray level image, to conversion after left and right gray level image carry out Corner Detection, corners Matching and mistake
The rejecting of angle point by mistake, a number of correct coupling angle point logarithm of final acquisition, then by matching angle
The minimum corners Matching logarithm N putting logarithm corresponding with 3D rendering compares, automatic distinguishing 3D
Image and non-3D rendering, it is not necessary to user the most with the naked eye judges, can save user time and
Muscle power.
For solving above-mentioned technical problem, first technical scheme that the present invention provides is to provide a kind of right
3D rendering knows method for distinguishing, including flow process:
A. input picture；
B. by image procossing be left and right gray level image；
C. by Corner Detection Algorithm, left images asked respectively angle point;
D. with corner correspondence, the angle point of two width images is mated;
E. with the coupling angle point rejecting algorithm rejecting mistake;
F. judging that logarithm that the angle point of two width images matches whether >=N, the most described image is
3D rendering, if it is not, the most described image is non-3D rendering；
Wherein, N be image be the coupling angle point logarithm of the required constantly left images of 3D rendering
Minimum of a value.
Wherein, described Corner Detection Algorithm includes Harris Corner Detection Algorithm.
Wherein, described rejecting algorithm includes light-stream adjustment.
According to the method described in above-mentioned any one, when the pixel of described image is 480*640, right
The N=50 answered.
For solving above-mentioned technical problem, second technical scheme that the present invention provides is to provide a kind of right
The device of 3D rendering identification, including:
Image conversion module, the gray level image about by the image procossing of input being；
Corner Detection module, electrically connects with described image conversion module, is used for utilizing Corner Detection to calculate
Left images is sought angle point by method respectively；
Corners Matching module, electrically connects with described Corner Detection module, is used for utilizing corners Matching to calculate
The angle point of two width images is mated by method, and utilizes the coupling angle point rejecting algorithm rejecting mistake；
Judge module, electrically connects with described corners Matching module, for judging the angle point of two width images
The logarithm matched whether >=N, the most described image is 3D rendering, if it is not, the most described figure
Seem non-3D rendering, and export described judged result；
Wherein, N is the coupling angle point logarithm of the left images required when being 3D rendering of image
Minimum of a value.Wherein, described Corner Detection Algorithm includes Harris Corner Detection Algorithm.Wherein, institute
State rejecting algorithm and include light-stream adjustment.
According to the description to the device of 3D rendering identification of the above-mentioned any one, the pixel of described image
During for 480*640, corresponding N=50.
The invention has the beneficial effects as follows: by the imagery exploitation transfer algorithm of input is converted into left and right
Gray level image, then carries out the rejecting of Corner Detection, corners Matching and error corner point, finally obtains
The angle point logarithm of a number of correct coupling, then by relative with 3D rendering for coupling angle point logarithm
The minimum corners Matching logarithm N answered compares, automatic distinguishing 3D rendering and non-3D rendering,
The most with the naked eye judging without user, time and the muscle power that can save user are tested.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet that 3D rendering is known an embodiment of method for distinguishing by the present invention.
Fig. 2 is the present invention structural representation to an embodiment of the device of 3D rendering identification.
Detailed description of the invention
Referring to Fig. 1, Fig. 1 is the stream that 3D rendering is known an embodiment of method for distinguishing by the present invention
Journey schematic diagram.As it is shown in figure 1, the present embodiment includes flow process:
A. input picture；
B. by the gray level image that image procossing is left and right,
Automatically the image of input is converted to gray level image by translation arithmetic, and by after conversion
Image split into left and right picture format；
C. by Corner Detection Algorithm, left and right gray level image is sought angle point respectively,
In an embodiment of the present invention, preferred Corner Detection Algorithm includes that Harris Corner Detection is calculated
Method, but other can also be used can to reach the Corner Detection Algorithm of same purpose, the present invention couple
This is not restricted;
D. with corner correspondence, the angle point of two width images is mated,
When the current location utilizing Corner Detection Algorithm to detect angle point, program recalls angle point
Join algorithm the angle point of two width images is mated;
E. wrong with rejecting algorithm rejecting coupling angle point,
Owing to some angle point does not matches that, utilize rejecting algorithm can reject the matching angle of mistake
Point, leaves behind a number of correct coupling angle point, and concrete rejecting algorithm includes bundle adjustment
Method, can also use other can realize the rejecting algorithm of same purpose certainly in concrete application
Reaching the purpose of the present invention, this is not limited by the present invention;
F. judging that logarithm that the angle point of two width images matches whether >=N, the most described image is
3D rendering, if it is not, the most described image is non-3D rendering,
The image determined for a width pixel, if 3D rendering, the then matching angle of this image
Point logarithm have to be larger than equal to a constant being associated with image pixel, in embodiments of the invention
Representing this constant by parameter N, N is also the images match that image is corresponding when being 3D rendering
The minimum of a value of angle point logarithm.Such as, if pixel 480*640 of image time, corresponding N=50,
In the case of the match point logarithm of the two width images being divided into is more than or equal to 50, corresponding image is
3D rendering, in this process step, this constant N will be utilized to judge, and whether the image of input is
3D rendering, specifically: judge that logarithm that the angle point of two width images matches is whether >=N, if so,
The most described image is 3D rendering, if it is not, image is then non-3D rendering.
Referring to Fig. 2, Fig. 2 is the present invention signal to an embodiment of the device of 3D rendering identification
Graph structure.As in figure 2 it is shown, the device 20 to 3D rendering identification of the present embodiment includes that image turns
Die change block 21, Corner Detection module 22, corners Matching module 23 and judge module 24.Wherein,
Image conversion module 21 electrically connects with Corner Detection module 22, Corner Detection module 22 and angle point
Matching module 23 electrically connects, and corners Matching module 23 electrically connects with judge module 24, data from
Image conversion module 21 flows to Corner Detection module 22, corners Matching module 23 successively and judges mould
Block 24.
In the present embodiment, after image conversion module 21 receives the image of input, image is led to
Cross transfer algorithm and be converted to the gray level image of left and right.Then, gray level image is transferred to Corner Detection mould
Block 22, Corner Detection module 22 utilizes Corner Detection Algorithm that left and right gray level image is asked angle point respectively
Obtain the position coordinates of angle point.Corner Detection module 22 utilizes corner correspondence to two width images
Angle point mate, and utilize and reject algorithm and reject the coupling angle point of mistake, and then obtain certain
The coupling angle point logarithm that quantity is correct.Judge module 24 judges what the angle point of two width images matched
Logarithm whether >=N, the most described image is 3D rendering, if it is not, the most described image is non-3D
Image, and export described judged result, wherein, N is the left side that image is required when being 3D rendering
The minimum of a value of the coupling angle point logarithm of right image.
In the preferred embodiment of the present invention, Corner Detection Algorithm includes Harris Corner Detection
Algorithm.In the preferred embodiment of the present invention, reject algorithm and include light-stream adjustment.Certainly,
In other embodiments of the invention, it is also possible to the Corner Detection of the object of the invention can be realized with other
Algorithm and rejecting algorithm, the present invention is without limitation.
In a preferred embodiment of the device to 3D rendering identification of the present invention, if image conversion
When the image pixel that module 21 receives is 480*640, corresponding N=50, therefore for pixel be
480*640 image, when the angle point logarithm matched of left and right gray level image is more than or equal to 50, image
Just for 3D rendering, being otherwise non-3D rendering, the device to 3D rendering identification of the present invention is with this
Judge whether image is 3D rendering.
By the way, the method and device to 3D rendering identification that the present invention provides can be accurate
True identifies 3D rendering and non-3D rendering, it is not necessary to user visually observes and then whether judges image
For 3D rendering, can save manpower and time.
The foregoing is only embodiments of the invention, not thereby limit the scope of the claims of the present invention,
Every equivalent structure utilizing description of the invention and accompanying drawing content to be made or equivalence flow process conversion, or
Directly or indirectly being used in other relevant technical fields, the patent being the most in like manner included in the present invention is protected
In the range of protecting.
Claims (8)
1. one kind 3D rendering is known method for distinguishing, it is characterised in that described method includes flow process:
A. input picture；
B. by image procossing be left and right gray level image；
C. by Corner Detection Algorithm, left and right gray level image is sought angle point respectively；
D. with corner correspondence, the angle point of two width images is mated；
E. with the coupling angle point rejecting algorithm rejecting mistake；
F. judging that logarithm that the angle point of two width images matches whether >=N, the most described image is
3D rendering, if it is not, the most described image is non-3D rendering；
Wherein, N is the coupling angle point logarithm of the left images required when being 3D rendering of image
Minimum of a value, the value of N determines according to the pixel of described image.
Method the most according to claim 1, it is characterised in that described Corner Detection Algorithm
Including Harris Corner Detection Algorithm.
Method the most according to claim 1, it is characterised in that described rejecting algorithm includes
Light-stream adjustment.
4. according to the method described in claim 1-3 any one, it is characterised in that described image
Pixel when being 480*640, corresponding N=50.
5. the device to 3D rendering identification, it is characterised in that described device includes:
Image conversion module, the gray level image about by the image procossing of input being；
Corner Detection module, electrically connects with described image conversion module, is used for utilizing Corner Detection to calculate
Left and right gray level image is sought angle point by method respectively；
Corners Matching module, electrically connects with described Corner Detection module, is used for utilizing corners Matching to calculate
The angle point of two width images is mated by method, and utilizes the coupling angle point rejecting algorithm rejecting mistake；
Judge module, electrically connects with described corners Matching module, for judging the angle point of two width images
The logarithm matched whether >=N, the most described image is 3D rendering, if it is not, the most described figure
Seem non-3D rendering, and export described judged result；
Wherein, N is the coupling angle point logarithm of the left images required when being 3D rendering of image
Minimum of a value, the value of N determines according to the pixel of described image.
Device the most according to claim 5, it is characterised in that described Corner Detection Algorithm
Including Harris Corner Detection Algorithm.
Device the most according to claim 5, it is characterised in that described rejecting algorithm includes
Light-stream adjustment.
8. according to the device described in claim 5-7 any one, it is characterised in that described image
Pixel when being 480*640, corresponding N=50.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310443404.3A CN103996015B (en) | 2013-09-26 | 2013-09-26 | A kind of method and device to 3D rendering identification |
| PCT/CN2014/082899 WO2015043301A1 (en) | 2013-09-26 | 2014-07-24 | Method and apparatus for recognizing 3d image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310443404.3A CN103996015B (en) | 2013-09-26 | 2013-09-26 | A kind of method and device to 3D rendering identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103996015A CN103996015A (en) | 2014-08-20 |
| CN103996015B true CN103996015B (en) | 2016-09-07 |
Family
ID=51310177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310443404.3A Expired - Fee Related CN103996015B (en) | 2013-09-26 | 2013-09-26 | A kind of method and device to 3D rendering identification |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN103996015B (en) |
| WO (1) | WO2015043301A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106023171B (en) * | 2016-05-12 | 2019-05-14 | 惠州学院 | A kind of image angular-point detection method based on turning radius |
| CN108475341B (en) * | 2017-04-11 | 2021-08-17 | 深圳市柔宇科技股份有限公司 | Three-dimensional image recognition method and terminal |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625768A (en) * | 2009-07-23 | 2010-01-13 | 东南大学 | Three-dimensional human face reconstruction method based on stereoscopic vision |
| CN102074015A (en) * | 2011-02-24 | 2011-05-25 | 哈尔滨工业大学 | Two-dimensional image sequence based three-dimensional reconstruction method of target |
| CN103177468A (en) * | 2013-03-29 | 2013-06-26 | 渤海大学 | Three-dimensional motion object augmented reality registration method based on no marks |
| CN103247053A (en) * | 2013-05-16 | 2013-08-14 | 大连理工大学 | Accurate part positioning method based on binocular microscopy stereo vision |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8773430B2 (en) * | 2009-12-09 | 2014-07-08 | Thomson Licensing | Method for distinguishing a 3D image from a 2D image and for identifying the presence of a 3D image format by feature correspondence determination |
| CN101799939A (en) * | 2010-04-02 | 2010-08-11 | 天津大学 | Rapid and self-adaptive generation algorithm of intermediate viewpoint based on left and right viewpoint images |
| CN102395037B (en) * | 2011-06-30 | 2014-11-05 | 深圳超多维光电子有限公司 | Format recognition method and device |
| CN103051913A (en) * | 2013-01-05 | 2013-04-17 | 北京暴风科技股份有限公司 | Automatic 3D (three-dimensional) film source identification method |
-
2013
- 2013-09-26 CN CN201310443404.3A patent/CN103996015B/en not_active Expired - Fee Related
-
2014
- 2014-07-24 WO PCT/CN2014/082899 patent/WO2015043301A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625768A (en) * | 2009-07-23 | 2010-01-13 | 东南大学 | Three-dimensional human face reconstruction method based on stereoscopic vision |
| CN102074015A (en) * | 2011-02-24 | 2011-05-25 | 哈尔滨工业大学 | Two-dimensional image sequence based three-dimensional reconstruction method of target |
| CN103177468A (en) * | 2013-03-29 | 2013-06-26 | 渤海大学 | Three-dimensional motion object augmented reality registration method based on no marks |
| CN103247053A (en) * | 2013-05-16 | 2013-08-14 | 大连理工大学 | Accurate part positioning method based on binocular microscopy stereo vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103996015A (en) | 2014-08-20 |
| WO2015043301A1 (en) | 2015-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8098276B2 (en) | Stereo vision system and control method thereof | |
| CN103530599A (en) | Method and system for distinguishing real face and picture face | |
| CN104036480B (en) | Quick elimination Mismatching point method based on surf algorithm | |
| CN105913093A (en) | Template matching method for character recognizing and processing | |
| CN107578403A (en) | The stereo image quality evaluation method of binocular view fusion is instructed based on gradient information | |
| SG169287A1 (en) | Apparatus, method and article for evaluating a stack of objects in an image | |
| CN106127690A (en) | A kind of quick joining method of unmanned aerial vehicle remote sensing image | |
| CN103729631B (en) | Vision-based connector surface feature automatically-identifying method | |
| CN102799867A (en) | Meter pointer angle identification method based on image processing | |
| CN107832806A (en) | A kind of car plate type identification method and system | |
| CN104766072A (en) | Recognition device for human face of living body and use method thereof | |
| CN104978575A (en) | Fingerprint identification system and operation method thereof | |
| CN104899609A (en) | Image registration-based mechanical meter identification method | |
| CN103512892A (en) | Method for detecting electromagnetic wire film wrapping | |
| RU2015153562A (en) | METHOD, SERVER DEVICE AND TERMINAL DEVICE FOR IMAGE PROVISION | |
| CN103996015B (en) | A kind of method and device to 3D rendering identification | |
| CN102998095B (en) | The detection method of a kind of naked-eye stereoscopic display and device | |
| CN102567969B (en) | Color image edge detection method | |
| CN102378041B (en) | A kind of picture quality detection method and device | |
| CN103185546A (en) | Width measuring method and system | |
| CN107818583A (en) | Cross searching detection method and device | |
| CN111127494A (en) | Expressway truck weight limit identification method based on image processing | |
| CN105550706A (en) | Method of recognizing 2D image and 3D image | |
| CN102663441B (en) | Error match removal method based on point-line relation consistency | |
| CN105631887B (en) | Based on the adaptive two step parallax modification methods and system for supporting weight matching algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160907 Termination date: 20200926 |