CN105894496A - Semi-local-texture-feature-based two-stage image segmentation method - Google Patents
Semi-local-texture-feature-based two-stage image segmentation method Download PDFInfo
- Publication number
- CN105894496A CN105894496A CN201610159202.XA CN201610159202A CN105894496A CN 105894496 A CN105894496 A CN 105894496A CN 201610159202 A CN201610159202 A CN 201610159202A CN 105894496 A CN105894496 A CN 105894496A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- segmentation
- feature
- beltrami
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a semi-local-texture-feature-based two-stage image segmentation method. The method comprises: an image is segmented into non-overlapped small blocks with M*M pixels; a texture feature, based on a Beltrami frame and semi-local information, of each block is extracted, block clustering is carried out by using a K-means algorithm, and a picture is divided into four areas; according to a photography composition principle, an optimal position of a target is determined and thus the target is extracted, thereby completing coarse segmentation; and fine segmentation is carried out on the extracted target by using a geometric moving profile model, thereby obtaining a precise segmentation result. According to the invention, the method has the following beneficial effects: a segmentation method carrying out coarse segmentation to extract a target and then carrying out fine segmentation is put forward; and on the basis of the segmentation strategy from the coarse level to the fine level, a picture having a blurred or complicated background can be segmented. A novel texture feature based on the Beltrami frame and the semi-local information is defined; compared with the single feature, the novel texture feature has the high discriminability; the anti-noise capability is high; and the texture feature can be applied to clustering and image segmentation and thus a precise experiment result can be obtained.
Description
Technical field
The present invention relates to image partition method, image procossing, pattern recognition, artificial intelligence field, be specifically related to a kind of two-stage image partition method based on half Local textural feature.
Background technology
Texture Segmentation is a problem the most challenging in image segmentation.Human eye can be easy to tell different textures, but is difficult to be defined texture from the aspect of mathematical term, also therefore is difficult to describe it with a model.Additionally, texture may cause the loss of important edges and the uneven of intensity profile.The definition being widely recognized as at present is: texture is a series of fine characteristic details with periodicity and oscillatory.
Normally used characteristics of image includes: feature, feature based on half local message and feature based on Beltrami framework of based on filtering.Wherein feature such as gradient filtering based on filtering, the filtering of small echo porous have been applied in feature extraction and image segmentation, and the feature extracted by Gabor or Morlet wavelet transformation is to discriminate between the important evidence of the texture of different directions and yardstick;The main method obtaining feature based on half local message is: extracted by the half-tone information of the block adjacent with existing pixel, thus obtain half local message of each pixel, the idea of this block-based characteristic vector proposes first when introducing textures synthesis, later, Buades et al. based on block diversity and non local average proposition to the idea of image noise reduction, Gilboa and Osher framework based on change proposes non local noise reduction model, finally, the diversity that Bresson and Chan is equally based between block proposes a kind of variable unsupervised dividing method;Feature based on Beltrami framework is a kind of new geometric representation of image, characteristics of image is regarded as the Riemann manifold being embedded in higher dimensional space by it, the advantage of this method is that it allows to use different geometry instruments to carry out different image procossing (such as noise reduction and segmentation), and can process the image of any N-dimensional, shortcoming is the most sensitive to noise.Therefore, latter two feature is combined by the present invention, the feature based on half local message extracted is introduced under Beltrami framework by mapping, thus obtains a strongest new textural characteristics of noise immunity.
Being widely known by the people most in image is split and most successful model be exactly the movable contour model first proposed by Kass, Witkin et al., it is successfully applied in medical imaging extraction anatomical structure.But the shortcoming of this model is that the initial position to active contour is very sensitive and bad in the depression boundary convergence of target.Movable contour model is improved by Caselles subsequently, kimmel et al., proposes geometric active contour model (GAC), and this model can obtain preferable segmentation result in image is split, and therefore the segmentation jog section of the present invention just uses this kind of model.
The present invention proposes a kind of dividing method being different from conventional segmentation thinking, is broadly divided into coarse segmentation and two stages are cut in segmentation.First, divide the image into into the non-overlapped block of M × M pixel, extract each piece based on Beltrami framework and the textural characteristics of half local message, then block cluster is carried out with K-means algorithm, picture is divided into four regions, determine the optimum position of target according to photography composition principle, thus extract target, complete coarse segmentation;Finally with geometric active contour model (GAC) target extracted is finely divided and cuts, thus obtain more accurate segmentation result.
Summary of the invention
Present invention is primarily targeted at, propose a kind of first coarse segmentation to go out target object and be finely divided the thought cut again, and combine a kind of based on Beltrami framework with the new textural characteristics of half local message, apply it to cluster and during image splits, obtain segmentation result more accurately.
The object of the invention to solve the technical problems is to the technical scheme is that a kind of two-stage image partition method based on half Local textural feature, including herein below:
If Px,yBe with pixel (x, y) centered by, size is the block of τ × τ, then have
The following X that maps is used to be incorporated into by textural characteristics under Beltrami framework:
X:(x,y)→(X1=x, X2=y, X3=Px,y(I)) (2)
This mapping contains local message (locus) and half topography's information (value of the block of pixels around center pixel).Assume the textured pattern that a given width is complicated, by map the geometry manifold being mounted to higher dimensional space of (2) with we observed to texture be consistent (this hypothesis is all establishment to most natural image).This means that the metric tensor of manifold of identical texture region is identical, metric tensor is used to a variable of the distance in measurement manifold between 2, when the manifold of certain specific region is almost in a plane, in this region, the distance between any two points is all equal, in conjunction with the manifold obtained by mapping (2) knowable to half topography's information almost in plane, therefore there is identical texture in this region.Map corresponding metric tensor in (2) to be defined as:
Finally, textural characteristics describes sub-F and is defined as
Wherein σ > 0 is scale parameter, uses gaussian kernel function as low-pass filtering, controls to describe the degree of image detail.
It addition, for coloured image, derivation is the simplest.Making coloured image is I=(I1,I2,…,IK), wherein k is the dimension of image, and corresponding half local is mapped as:
X:(x,y)→(X1=x, X2=y, X3=Px,y(I1),…,X2+k=Px,y(Ik)) (5)
Corresponding metric tensor is write as following form:
It addition, geometric active contour model can be converted into following minimization problem:
Wherein ds is the length of Euclid's element,Length for curve C.Accordingly, it is capable to functional (7) is, by ds, the function g comprising object boundary information is integrated a new length obtaining in fact, function g is that edge indicator function is for eliminating such asSuch object edge, I0Being original image, β is any normal number.Function E is can get by the calculus of variationsGACEuler-Lagrange equation formula, gradient descent method can minimize E as quickly as possibleGAC:
Wherein,T is the time parameter of artificial regulation, and k, N are respectively curvature and the normal of curve C, the EVOLUTION EQUATION existence and unique solution of the active contour defined in formula (8).The Level Set Method that Osher and Sethian proposes efficiently solves profile extension problem and has processed change in topology problem, and equation (8) can be written as level set form:
Wherein, the active contour C that φ is embedded in constantly developing is (such as C (t)={ x ∈ RN| the level set function of φ (x, t)=0}), based on hyperbolic conservation law, partial differential equation (9) may be used on multiple quantizing and solve, and obtain fairly precise segmentation result.
Compared with prior art, advantages of the present invention and effect are: 1) propose and a kind of first carry out being finely divided after coarse segmentation extracts target object the dividing method cut, this be can be used to split have by the thick segmentation strategy to essence obscure or the picture of complex background.2) define a kind of based on Beltrami framework with the novel textural characteristics of half local message, there is the resolving ability more higher than single feature, and there is the strongest anti-noise ability, this textural characteristics is used in cluster and image segmentation, it is possible to obtain more accurate experimental result.
Accompanying drawing explanation
A kind of two-stage image partition method flow chart based on half Local textural feature of Fig. 1
Detailed description of the invention
As it is shown in figure 1, overall procedure of the present invention is as follows: first, divide the image into into the non-overlapped fritter of M × M pixel;Secondly, extract each piece based on Beltrami framework and the textural characteristics of half local message, then carry out block cluster with K-means algorithm, picture be divided into four regions;Then determine the optimum position of target according to photography composition principle, thus extract target, complete coarse segmentation;Finally with geometric active contour model (GAC) target extracted is finely divided and cuts, thus obtain more accurate segmentation result.
The present invention specifically comprises the following steps that
Step1: divide the image into into the non-overlapped fritter of M × M pixel
Considering the effect of textural characteristics and the time complexity of algorithm, all pictures are standardized as 126 × 189 or 189 × 126, the tile size split is 3 × 3, and therefore every standardized image includes 2646 fritters.
Step2: extract each piece based on Beltrami framework and the textural characteristics of half local message, then carry out block cluster with K-means algorithm, picture be divided into four regions
1) choose with pixel (x, y) centered by, size is the block P of τ × τx,y:
2) the following X that maps is used to be incorporated into by textural characteristics under Beltrami framework:
X:(x,y)→(X1=x, X2=y, X3=Px,y(I)) (11)
This mapping contains local message (locus) and half topography's information (value of the block of pixels around center pixel).Assuming the textured pattern that a given width is complicated, be consistent by mapping the geometry manifold being mounted to higher dimensional space of (11) observed with us to texture, in mapping (11), metric tensor is defined as accordingly:
3) extract each piece based on Beltrami framework and the textural characteristics of half local message
Finally, obtain textural characteristics and describe sub-F be
Wherein σ > 0 is scale parameter, uses gaussian kernel function as low-pass filtering, controls to describe the degree of image detail.
4) cluster by K-means method, image is polymerized to four classes
Step3: determine the optimum position of target according to photography composition principle, thus extract target, complete coarse segmentation
1) result obtained in the previous step is merged
One secondary given image finally has only to be divided into foreground area and background area, merges the region meeting certain similarity in image obtained in the previous step, and similarity measurement is defined as:
Wherein, RiFor texture feature vector, d (Ri,Rj) it is vector RiAnd RjBetween distance, similarity measurement is inversely proportional to distance, therefore merges the region with maximum comparability (minimum range), and the characteristic vector of new combined region to recalculate, until image in leave behind two regions.
2) optimum position of target is determined according to photography composition principle
Photography composition determines that typically there are two kinds of methods optimum position: three points of composition methods and dynamic symmetry method.Three points of composition methods refer to laterally and vertically be respectively divided into image trisection, and in image, the position of four intersection points is the optimum position of target, namely foreground area.Dynamic symmetry method refers to make a diagonal of image, then makees vertical line to this diagonal respectively from two other angle, and in image, the position of two intersection points is the optimum position of target, and other regions are then background area.
3) target object is extracted
First respectively obtaining the bianry image in foreground and background region, then the mask table of three points of composition methods or dynamic symmetry method is done with two width bianry images and operated respectively, the bianry image maximum to pixel count carries out Objective extraction, and another width is defaulted as background area.
Step4: with geometric active contour model the target extracted is finely divided and cuts, thus obtain more accurate segmentation result
1) geometric active contour model (GAC)
Geometric active contour model (GAC) can be converted into following minimization problem:
Wherein ds is the length of Euclid's element,Length for curve C.Accordingly, it is capable to functional (15) is, by ds, the function g comprising object boundary information is integrated a new length obtaining in fact, function g is that edge indicator function is for eliminating such asSuch object edge, I0Being original image, β is any normal number.Function E is can get by the calculus of variationsGACEuler-Lagrange equation formula, gradient descent method can minimize E as quickly as possibleGAC:
Wherein,T is the time parameter of artificial regulation, and k, N are respectively curvature and the normal of curve C, the EVOLUTION EQUATION existence and unique solution of the active contour defined in formula (16).
2) level set function is rewritten
The Level Set Method that Osher and Sethian proposes efficiently solves profile extension problem and has processed change in topology problem, and equation (16) can be written as level set form:
Wherein, the active contour C that φ is embedded in constantly developing is (such as C (t)={ x ∈ RN| the level set function of φ (x, t)=0}), based on hyperbolic conservation law, partial differential equation (17) may be used on multiple quantizing and solve, and obtain fairly precise segmentation result.
3) target object extracting coarse segmentation is finely divided and cuts, and obtains segmentation result.
Claims (5)
1. a two-stage image partition method based on half Local textural feature, it is characterised in that comprise the following steps:
Step 1, divide the image into into the non-overlapped fritter of M × M pixel;
Step 2, extract each piece based on Beltrami framework and the textural characteristics of half local message, then carry out block cluster with K-means algorithm, picture be divided into four regions;
Step 3, determine the optimum position of target according to photography composition principle, thus extract target, complete coarse segmentation;
Step 4, with geometric active contour model the target extracted is finely divided and cuts, thus obtain more accurate segmentation result.
Two-stage image partition method based on half Local textural feature the most according to claim 1, in described step 1, divides the image into into the non-overlapped fritter of M × M pixel, it is characterised in that:
Considering the effect of textural characteristics and the time complexity of algorithm, all pictures are standardized as 126 × 189 or 189 × 126, the tile size split is 3 × 3, and therefore every standardized image includes 2646 fritters.
Two-stage image partition method based on half Local textural feature the most according to claim 1, in described step 2, extract each piece based on Beltrami framework and the textural characteristics of half local message, then block cluster is carried out with K-means algorithm, picture is divided into four regions, it is characterised in that:
1) choose with pixel (x, y) centered by, size is the block P of τ × τx,y:
2) the following X that maps is used to be incorporated into by textural characteristics under Beltrami framework:
X:(x,y)→(X1=x, X2=y, X3=Px,y(I)) (2)
This mapping contains local message (locus) and half topography's information (value of the block of pixels around center pixel).Assuming the textured pattern that a given width is complicated, be consistent by mapping the geometry manifold being mounted to higher dimensional space of (2) observed with us to texture, in mapping (2), metric tensor is defined as accordingly:
3) extract each piece based on Beltrami framework and the textural characteristics of half local message
Finally, obtain textural characteristics and describe sub-F be
Wherein σ > 0 is scale parameter, uses gaussian kernel function as low-pass filtering, controls to describe the degree of image detail.
4) cluster by K-means method, image is polymerized to four classes.
Two-stage image partition method based on half Local textural feature the most according to claim 1, in described step 3, determines the optimum position of target, thus extracts target, complete coarse segmentation according to photography composition principle, it is characterised in that:
1) result obtained in the previous step is merged
One secondary given image finally has only to be divided into foreground area and background area, merges the region meeting certain similarity in image obtained in the previous step, and similarity measurement is defined as:
Wherein, RiFor texture feature vector, d (Ri,Rj) it is vector RiAnd RjBetween distance, similarity measurement is inversely proportional to distance, therefore merges the region with maximum comparability (minimum range), and the characteristic vector of new combined region to recalculate, until image in leave behind two regions.
2) optimum position of target is determined according to photography composition principle
Photography composition determines that typically there are two kinds of methods optimum position: three points of composition methods and dynamic symmetry method.Three points of composition methods refer to laterally and vertically be respectively divided into image trisection, and in image, the position of four intersection points is the optimum position of target, namely foreground area.Dynamic symmetry method refers to make a diagonal of image, then makees vertical line to this diagonal respectively from two other angle, and in image, the position of two intersection points is the optimum position of target, and other regions are then background area.
3) target object is extracted
First respectively obtaining the bianry image in foreground and background region, then the mask table of three points of composition methods or dynamic symmetry method is done with two width bianry images and operated respectively, the bianry image maximum to pixel count carries out Objective extraction, and another width is defaulted as background area.
Two-stage image partition method based on half Local textural feature the most according to claim 1, in described step 4, with geometric active contour model the target extracted is finely divided and cuts, thus obtain more accurate segmentation result, it is characterised in that:
1) geometric active contour model (GAC)
Geometric active contour model (GAC) can be converted into following minimization problem:
Wherein ds is the length of Euclid's element,Ds is the length of curve C.Accordingly, it is capable to functional (6) is, by ds, the function g comprising object boundary information is integrated a new length obtaining in fact, function g is that edge indicator function is for eliminating such asSuch object edge, I0Being original image, β is any normal number.Function E is can get by the calculus of variationsGACEuler-Lagrange equation formula, gradient descent method can minimize E as quickly as possibleGAC:
Wherein,T is the time parameter of artificial regulation, and k, N are respectively curvature and the normal of curve C, the EVOLUTION EQUATION existence and unique solution of the active contour defined in formula (7).
2) level set function is rewritten
The Level Set Method that Osher and Sethian proposes efficiently solves profile extension problem and has processed change in topology problem, and equation (7) can be written as level set form:
Wherein, the active contour C that φ is embedded in constantly developing is (such as C (t)={ x ∈ RN| the level set function of φ (x, t)=0}), based on hyperbolic conservation law, partial differential equation (8) may be used on multiple quantizing and solve, and obtain fairly precise segmentation result.
3) target object extracting coarse segmentation is finely divided and cuts, and obtains segmentation result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610159202.XA CN105894496A (en) | 2016-03-18 | 2016-03-18 | Semi-local-texture-feature-based two-stage image segmentation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610159202.XA CN105894496A (en) | 2016-03-18 | 2016-03-18 | Semi-local-texture-feature-based two-stage image segmentation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105894496A true CN105894496A (en) | 2016-08-24 |
Family
ID=57013876
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610159202.XA Pending CN105894496A (en) | 2016-03-18 | 2016-03-18 | Semi-local-texture-feature-based two-stage image segmentation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105894496A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107480593A (en) * | 2017-07-12 | 2017-12-15 | 广东交通职业技术学院 | Beltrami flows and the hyperspectral image classification method of recursive filtering |
CN110264482A (en) * | 2019-05-10 | 2019-09-20 | 河南科技大学 | Active contour dividing method based on middle intelligence set transformation matrix factorisation |
CN112967202A (en) * | 2021-03-12 | 2021-06-15 | 华北水利水电大学 | Denoising method for encrypted image with privacy protection by hyperbolic partial differential equation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101447076A (en) * | 2008-12-02 | 2009-06-03 | 浙江大学 | Method for partitioning interested areas in WEB image |
CN101673345A (en) * | 2009-07-01 | 2010-03-17 | 北京交通大学 | Method for extracting target closed contour based on shape prior |
CN103413332A (en) * | 2013-08-23 | 2013-11-27 | 华北电力大学 | Image segmentation method based on two-channel texture segmentation active contour model |
CN104504720A (en) * | 2015-01-07 | 2015-04-08 | 四川大学 | New prostate ultrasonoscopy segmentation technique |
CN104732551A (en) * | 2015-04-08 | 2015-06-24 | 西安电子科技大学 | Level set image segmentation method based on superpixel and graph-cup optimizing |
-
2016
- 2016-03-18 CN CN201610159202.XA patent/CN105894496A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101447076A (en) * | 2008-12-02 | 2009-06-03 | 浙江大学 | Method for partitioning interested areas in WEB image |
CN101673345A (en) * | 2009-07-01 | 2010-03-17 | 北京交通大学 | Method for extracting target closed contour based on shape prior |
CN103413332A (en) * | 2013-08-23 | 2013-11-27 | 华北电力大学 | Image segmentation method based on two-channel texture segmentation active contour model |
CN104504720A (en) * | 2015-01-07 | 2015-04-08 | 四川大学 | New prostate ultrasonoscopy segmentation technique |
CN104732551A (en) * | 2015-04-08 | 2015-06-24 | 西安电子科技大学 | Level set image segmentation method based on superpixel and graph-cup optimizing |
Non-Patent Citations (3)
Title |
---|
VICENT CASELLES ET AL: "Geodesic Active Contours", 《INTERNATIONAL JOURNAL OF COMPUTER VISION》 * |
朱蓉: "基于语义的Web图像分类研究", 《中国博士学位论文全文数据库信息科技辑》 * |
赵在新 等: "结合半局部信息与结构张量的无监督纹理图像分割", 《中国图像图形学报》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107480593A (en) * | 2017-07-12 | 2017-12-15 | 广东交通职业技术学院 | Beltrami flows and the hyperspectral image classification method of recursive filtering |
CN107480593B (en) * | 2017-07-12 | 2020-07-03 | 广东交通职业技术学院 | Hyperspectral image classification method of Beltrami flow and recursive filtering |
CN110264482A (en) * | 2019-05-10 | 2019-09-20 | 河南科技大学 | Active contour dividing method based on middle intelligence set transformation matrix factorisation |
CN110264482B (en) * | 2019-05-10 | 2022-09-09 | 河南科技大学 | Active contour segmentation method based on transformation matrix factorization of noose set |
CN112967202A (en) * | 2021-03-12 | 2021-06-15 | 华北水利水电大学 | Denoising method for encrypted image with privacy protection by hyperbolic partial differential equation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109872397B (en) | Three-dimensional reconstruction method of airplane parts based on multi-view stereo vision | |
WO2017219391A1 (en) | Face recognition system based on three-dimensional data | |
CN107862667B (en) | Urban shadow detection and removal method based on high-resolution remote sensing image | |
CN110363719B (en) | Cell layered image processing method and system | |
CN109902585B (en) | Finger three-mode fusion recognition method based on graph model | |
CN110738676A (en) | GrabCT automatic segmentation algorithm combined with RGBD data | |
CN104850847B (en) | Image optimization system and method with automatic thin face function | |
WO2015092904A1 (en) | Image-processing apparatus, image-processing method, and image-processing program | |
CN108596975A (en) | A kind of Stereo Matching Algorithm for weak texture region | |
CN110544300B (en) | Method for automatically generating three-dimensional model based on two-dimensional hand-drawn image characteristics | |
CN111507921B (en) | Tunnel point cloud denoising method based on low-rank recovery | |
CN103971122B (en) | Three-dimensional face based on depth image describes method | |
CN110490301B (en) | Line feature description method based on convolutional neural network | |
Yang et al. | Automatic segmentation of human brain sulci | |
CN110751680A (en) | Image processing method with fast alignment algorithm | |
CN104809457A (en) | Three-dimensional face identification method and system based on regionalization implicit function features | |
CN103955945A (en) | Self-adaption color image segmentation method based on binocular parallax and movable outline | |
CN102663762B (en) | The dividing method of symmetrical organ in medical image | |
CN105894496A (en) | Semi-local-texture-feature-based two-stage image segmentation method | |
CN106373126B (en) | Image significance detection method based on fusion class geodesic curve and boundary comparison | |
CN112164145A (en) | Method for rapidly extracting indoor three-dimensional line segment structure based on point cloud data | |
CN105741264A (en) | Two-phase image segmentation method based on semi-local texture features | |
JP6132485B2 (en) | Image processing apparatus, operation method of image processing apparatus, and image processing program | |
CN111275610B (en) | Face aging image processing method and system | |
Bhadauria et al. | Building extraction from satellite images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160824 |