CN104036510A - Novel image segmentation system and method - Google Patents
Novel image segmentation system and method Download PDFInfo
- Publication number
- CN104036510A CN104036510A CN201410277696.2A CN201410277696A CN104036510A CN 104036510 A CN104036510 A CN 104036510A CN 201410277696 A CN201410277696 A CN 201410277696A CN 104036510 A CN104036510 A CN 104036510A
- Authority
- CN
- China
- Prior art keywords
- image
- target image
- triangle gridding
- target
- edge contour
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000003709 image segmentation Methods 0.000 title abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 239000000284 extract Substances 0.000 claims description 9
- 238000004064 recycling Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012790 confirmation Methods 0.000 abstract 1
- 238000005192 partition Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a novel image segmentation system and a novel image segmentation method. The novel image segmentation system comprises a gathering module used to gather original images, an outline confirmation module used to confirm edge outlines of the original images, a target image generation module used to generate target images, an image triangular meshing module used to perform triangular meshing processing on the target images and a feature vector extraction module used to extract the target images after the triangular meshing processing is performed on the target images. By adopting the technical scheme, not only is image segmentation efficiency improved, but also noise interference in the images are reduced, good robustness is achieved, an over-segmentation phenomenon generated by a traditional segmentation method is overcome, and overall effects of the images after being segmented are improved.
Description
Technical field
The present invention relates to image Segmentation Technology field, particularly a kind of New Image segmenting system and method.
Background technology
Along with the development of image digitazation, the use of image technique is more and more extensive.Especially often need to extract a part of image wherein at image, video field, and image, video are edited and revised, this just need to use image Segmentation Technology.
But existing image partition method is mainly the image partition method based on Bayesian network.This dividing method is only that the color and gradient feature vector of eight pixels to single pixel field formation carries out pre-service vector, and sets up on this basis Markov random field, utilizes related algorithm to carry out bayes decision, obtains segmentation result.This way is very poor for the segmentation effect of the image of background structure complexity.
And, the method more complicated that current picture segmentation scheme adopts, it is lower that image is cut apart efficiency, and segmentation effect is to be improved.
Summary of the invention
The object of the invention is: propose a kind of New Image segmenting system and method, it is high that it not only cuts apart efficiency, and effect after cutting apart is better.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of New Image segmenting system, this system comprises:
For gathering the acquisition module of original image;
For determining the profile determination module of original image edge contour;
For generating the target image generation module of target image;
For the image triangle gridding module that target image is carried out to triangle gridding processing;
And for extracting the proper vector extraction module of the target image after triangle gridding.
A kind of New Image dividing method, the method comprises:
Step S1: original image is carried out to image acquisition, and carry out pre-service and obtain, pretreatment image;
Step S2: pretreatment image is carried out to computing, draw the edge contour of image;
Step S3: taking the edge contour of image as basis, set up view data module, and generate target image;
Step S4: by the center of calculative determination target image;
Step S5: taking the center of target image as basic point, image is carried out to triangle gridding processing;
Step S6: extract the target image proper vector after trigonometric ratio.
Further, described pretreatment image is identical with the pixel size of institute original image.
Further, the image-region of described target image comprises the edge contour of described pretreatment image.
Further, the border of described target image is the rectangular shaped rim of drawing with the edge contour scope of pretreatment image.
Further, the concrete steps of described triangle gridding are: utilize polygon growth algorithm, extract polygonal summit as initial point set, recycling Lawson algorithm connection features point forms initial triangle gridding.
Further, described step S6 specifically also comprises the object or the color region that comprise described in the elementary area of triangle gridding is marked off, extracts these characteristics of image, and sets up index.
Beneficial effect of the present invention: adopt scheme provided by the invention not only to improve the efficiency that image is cut apart, more reduce the noise in image, there is good robustness, overcome the over-segmentation phenomenon that classic method is cut apart generation, improved the whole structure after image is cut apart.
Brief description of the drawings
Fig. 1 is system architecture schematic diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described.
As shown in Figure 1, system architecture of the present invention comprises: for gathering the acquisition module of original image; For determining the profile determination module of original image edge contour; For generating the target image generation module of target image; For the image triangle gridding module that target image is carried out to triangle gridding processing; And for extracting the proper vector extraction module of the target image after triangle gridding.
Be below a kind of New Image dividing method for said system, it comprises the following steps: original image is carried out to image acquisition, and carry out pre-service and obtain, pretreatment image; Again pretreatment image is carried out to computing, draw the edge contour of image; Then,, taking the edge contour of image as basis, set up view data module, and generate target image; Again by the center of calculative determination target image; Taking the center of target image as basic point, image is carried out to triangle gridding processing, and extract the target image proper vector after trigonometric ratio again.
In above-mentioned treatment step, described pretreatment image is identical with the pixel size of institute's original image.
In above-mentioned treatment step, the image-region of described target image comprises the edge contour of described pretreatment image.
In above-mentioned treatment step, the border of described target image is the rectangular shaped rim of drawing with the edge contour scope of pretreatment image.
In above-mentioned treatment step, the concrete steps of described triangle gridding are: utilize polygon growth algorithm, extract polygonal summit as initial point set, recycling Lawson algorithm connection features point forms initial triangle gridding.
In above-mentioned treatment step, the concrete steps that described proper vector is extracted are: the object or the color region that described in the elementary area of triangle gridding is marked off, comprise, extract these characteristics of image, and set up index.
More than show and described ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; that in above-described embodiment and instructions, describes just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.The claimed scope of the present invention is defined by appending claims and equivalent thereof.
Claims (7)
1. a New Image segmenting system, is characterized in that, this system comprises:
For gathering the acquisition module of original image;
For determining the profile determination module of original image edge contour;
For generating the target image generation module of target image;
For the image triangle gridding module that target image is carried out to triangle gridding processing;
And for extracting the proper vector extraction module of the target image after triangle gridding.
2. a New Image dividing method, is characterized in that, the method comprises:
Step S1: original image is carried out to image acquisition, and carry out pre-service and obtain, pretreatment image;
Step S2: pretreatment image is carried out to computing, draw the edge contour of image;
Step S3: taking the edge contour of image as basis, set up view data module, and generate target image;
Step S4: by the center of calculative determination target image;
Step S5: taking the center of target image as basic point, image is carried out to triangle gridding processing;
Step S6: extract the target image proper vector after trigonometric ratio.
3. a kind of New Image dividing method as claimed in claim 2, is characterized in that, described pretreatment image is identical with the pixel size of institute's original image.
4. a kind of New Image dividing method as claimed in claim 2, is characterized in that, the image-region of described target image comprises the edge contour of described pretreatment image.
5. a kind of New Image dividing method as claimed in claim 2, is characterized in that, the border of described target image is the rectangular shaped rim of drawing with the edge contour scope of pretreatment image.
6. a kind of New Image dividing method as claimed in claim 2, it is characterized in that, the concrete steps of described triangle gridding are: utilize polygon growth algorithm, extract polygonal summit as initial point set, recycling Lawson algorithm connection features point forms initial triangle gridding.
7. a kind of New Image dividing method as claimed in claim 2, is characterized in that, described step S6 specifically also comprises the object or the color region that comprise described in the elementary area of triangle gridding is marked off, extracts these characteristics of image, and sets up index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410277696.2A CN104036510A (en) | 2014-06-20 | 2014-06-20 | Novel image segmentation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410277696.2A CN104036510A (en) | 2014-06-20 | 2014-06-20 | Novel image segmentation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104036510A true CN104036510A (en) | 2014-09-10 |
Family
ID=51467269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410277696.2A Pending CN104036510A (en) | 2014-06-20 | 2014-06-20 | Novel image segmentation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104036510A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1477589A (en) * | 2002-07-31 | 2004-02-25 | ������������ʽ���� | Image processing method and device |
| CN101502119A (en) * | 2006-08-02 | 2009-08-05 | 汤姆逊许可公司 | Adaptive geometric partitioning for video decoding |
| US20130135305A1 (en) * | 2010-08-05 | 2013-05-30 | Koninklijke Philips Electronics N.V. | In-plane and interactive surface mesh adaptation |
-
2014
- 2014-06-20 CN CN201410277696.2A patent/CN104036510A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1477589A (en) * | 2002-07-31 | 2004-02-25 | ������������ʽ���� | Image processing method and device |
| CN101502119A (en) * | 2006-08-02 | 2009-08-05 | 汤姆逊许可公司 | Adaptive geometric partitioning for video decoding |
| US20130135305A1 (en) * | 2010-08-05 | 2013-05-30 | Koninklijke Philips Electronics N.V. | In-plane and interactive surface mesh adaptation |
Non-Patent Citations (2)
| Title |
|---|
| 万琳: "基于三角网格额图像表示方法研究", 《中国优秀博士学位论文全文数据库 信息科技辑》 * |
| 彭丽: "基于边缘信息的阈值图像分割", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104050682B (en) | Image segmentation method fusing color and depth information | |
| CN103559719B (en) | A kind of interactive image segmentation method | |
| CN111767920B (en) | Method, device, electronic device and storage medium for extracting region of interest | |
| CN105513105B (en) | Image background weakening method based on notable figure | |
| EP2874097A3 (en) | Automatic scene parsing | |
| CN104837000B (en) | The virtual visual point synthesizing method that a kind of utilization profile is perceived | |
| CN104408445A (en) | Automatic real-time human body detecting method | |
| CN104182750A (en) | Extremum connected domain based Chinese character detection method in natural scene image | |
| EP2816529A3 (en) | Automatic water area segmentation method and device for SAR image of complex terrain | |
| JP2010205067A (en) | Device, method and program for extracting area | |
| CN107657625A (en) | Merge the unsupervised methods of video segmentation that space-time multiple features represent | |
| CN112270745B (en) | Image generation method, device, equipment and storage medium | |
| CN103177260A (en) | Color image boundary extraction method | |
| CN108596919A (en) | A kind of Automatic image segmentation method based on depth map | |
| EP2500865A3 (en) | Image segmentation apparatus, method and program | |
| CN102663700A (en) | Segmentation method for adhering grain binary image | |
| CN104915952B (en) | Local protrusion object extraction method based on multiway tree in a kind of depth image | |
| KR20070117393A (en) | A method for extracting an object from a digital image using dictionary shape information, and a system for performing the method | |
| CN106897989B (en) | A Fingerprint Image Segmentation Method Based on Linear Density Calculation | |
| CN104778673B (en) | A kind of improved gauss hybrid models depth image enhancement method | |
| CN107578419A (en) | A Stereo Image Segmentation Method Based on Consistent Contour Extraction | |
| CN114723883A (en) | Three-dimensional scene reconstruction method, device, equipment and storage medium | |
| CN107610126A (en) | A kind of interactive image segmentation method based on local prior distribution | |
| JP2016075993A (en) | Image processing apparatus, control method of the same, and program | |
| CN105374021B (en) | It is a kind of based on lines butt to pictograph image partition method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140910 |
|
| RJ01 | Rejection of invention patent application after publication |