Method for partitioning interested areas in WEB image

A region of interest and image technology, applied in the field of image processing, can solve the problems of local extreme point interference, large dependence on the initial position of the active contour, and correct segmentation of the concave boundary, so as to improve the segmentation accuracy and reduce the overall execution time. Effect

Inactive Publication Date: 2009-06-03
ZHEJIANG UNIV
View PDF0 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The object of the present invention is to provide a method for segmenting the region of interest in a WEB image, which uses the color, texture and shape characteristics of the region of interest in the WEB image, and makes up for the inability of the traditional deformation model to correctly segment the concave boundary and the limitation of the active contour. The initial position dependence is large, and it is easy to be disturbed by local extreme points; at the same time, it also improves the insufficiency of the gray-scale segmentation method for color image segmentation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for partitioning interested areas in WEB image
  • Method for partitioning interested areas in WEB image
  • Method for partitioning interested areas in WEB image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0108] Example 1: figure 2 Compare the segmentation results of objects in the recessed area for various deformation models. Image size

[0109] It is 64×64. ((a) Traditional deformation model (α=1, β=0.2, γ=10, δ=0) (200 iterations); (b) Balloon force model (α=1, β=0.2, γ=10, δ =0.05) (200 iterations); (c) distance potential energy model (α=0.05, β=0, γ=0.5, δ=0) (200 iterations); (d) GVF model (α=0.05, β= 0, γ=1, δ=0.5) (200 iterations); (e) the improved model in the present invention (α=1, β=0.2, γ=10, δ=4) (180 iterations); (f ) The two-stage execution strategy of the improved model in the present invention (α=1, β=0.2, γ=10, δ=0; δ=4) (140 iterations)).

[0110] The weight selection of each energy item in the deformation model not only considers the unification between different models, but also tries to ensure that each model can obtain a better boundary segmentation effect within the specified number of iterations, so the final weight determination is implemented It is cont...

Embodiment 2

[0111] Example 2: image 3 Compare the segmentation results of the region of interest in the image for various deformation models (275 iterations). The image comes from the Corel image library, and the image size is 100×100. ((a) Original image; (b) Traditional deformation model (α=1, β=0, γ=6, δ=0); (c) Balloon force model (α=0.6, β=0, γ=2, δ=0.15); (d) Distance potential energy model (α=0.05, β=0, γ=0.5, δ=0); (e) is a model that uses only the restraint energy generated from the inner gravitational force of a triangle (α=1, β=0, γ=8, δ=3); (f) is the deformation model adopting two-stage execution strategy in the present invention (α=1, β=0, γ=6, δ=0; δ=3)) .

[0112] In this embodiment, the initial position of the active contour is obtained by drawing a circle. The chromaticity gradient is used to form the chromaticity contour of the region of interest in the image (the "flower area in the center of the image"). From image 3 It can be seen that since the boundary of the region ...

Embodiment 3

[0113] Example 3: Figure 4 In order to compare the segmentation results of the region of interest in the image by the deformation model proposed in the present invention when different image sub-blocks are taken (the number of iterations: the first segment is 100; the second segment is 50). (The original image is the same as in Example 2; (a) sub-block size = 2×2 cluster; (b) sub-block size = 4×4 cluster; (c) sub-block size=5×5 cluster ; (D) is the segmentation result corresponding to (a); (e) is the segmentation result corresponding to (b)); (f) is the segmentation result corresponding to (c); (α=1, β=0, γ=6, δ=0; δ=3)).

[0114] In this embodiment, the initial position of the active contour is obtained by automatic clustering. From Figure 4 It can be seen that although the clustering results are not the same in the three cases ((a) obtains better clustering results than (b) and (c)), after using the deformation model of the two-stage strategy, the same The segmentation results ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for portioning interested areas in WEB image, comprising the steps as follows: a novel deformation model is established so as to solve the problems of sunken areas and pseudo-boundary and improve the convergence precision of active contour; secondly, a clustering method in a colorful space Lab on the basis of image sub-block, color and vein characteristic is provided so as to realize the coarse partition to the interested areas and automatic gaining of initial position of the active contour, to accelerate the execution speed of the deformation model, and to avoid the interference of noise and isolated edges at the same time; finally, the method provides two execution strategies of the deformation model, which effectively partitions the complex and irregular areas in WEB images and leads the deformation model to have more flexibility and practicability. The method sufficiently combines the advantages of deformation model based on the boundary and the clustering based on the areas, effectively improves the partition precision of the interested areas in images and reduces the whole partition execution time.

Description

Technical field [0001] The present invention relates to image processing technology, and in particular to a method for segmenting a region of interest in a WEB image. Background technique [0002] With the vigorous development of the Internet and social informatization, massive digital image resources are generated from various image acquisition systems every day. How to effectively use these WEB images (WEB is the abbreviation of World Wide Web, also known as the World Wide Web; WEB images It refers to images that exist on the World Wide Web) is not only the most urgent need of users, but also the primary task of current image understanding. In quite a few cases, users do not care about the overall meaning expressed by the image, but pay more attention to the region of interest with specific meaning in the image. Commonly used image segmentation methods can be roughly divided into two categories: region-based segmentation and boundary-based segmentation. Although there are many ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00
Inventor 姚敏朱蓉柳一鸣
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap