Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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 large dependence on the initial position of the active contour, interference of local extreme points, correct segmentation of concave boundaries, etc., to reduce the overall execution time and improve the segmentation accuracy Effect

Inactive Publication Date: 2010-09-22
ZHEJIANG UNIV
View PDF0 Cites 0 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

[0107] Example 1: figure 2 Comparison of segmentation results for objects in depressed regions for various deformation models. image size

[0108] 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 ) 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)).

[0109] The weight selection of each energy item in the deformation model not only considers the unity 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 determination of the final weight is carri...

Embodiment 2

[0110] Example 2: image 3 Comparison of segmentation results for regions of interest in images for various deformation models (275 iterations). The image is 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) the distance potential energy model (α=0.05, β=0, γ=0.5, δ=0); (e) is the model using only the restraint energy generated from the inner gravity of the triangle (α=1, β=0, γ=8, δ=3); (f) is the deformation model (α=1, β=0, γ=6, δ=0; δ=3) that adopts two-stage execution strategies in the present invention .

[0111] The initial position of the active contour in this embodiment is obtained by drawing a circle. The chromaticity gradient is used to form a chromaticity profile of the region of interest in the image ("the flower region in the center of the image"). from image 3 It can be seen in , since the boundary of the region o...

Embodiment 3

[0112] Example 3: Figure 4 In order to take different image sub-blocks, the deformation model proposed in the present invention compares the segmentation results of the region of interest in the image (number of iterations: the first section is 100; the second section is 50). (Original figure is the same as embodiment 2; (a) the clustering of sub-block size=2×2; (b) the clustering of sub-block size=4×4; (c) the clustering of sub-block size=5×5 (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)).

[0113] The initial position of the active contour in this embodiment is obtained by automatic clustering. from Figure 4It can be seen that although the clustering results are different in the three cases ((a) obtains better clustering results than (b) and (c)), after the deformation model using the two-stage strategy, in the same Segmentation re...

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 invention relates to an image processing technology, 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, a large number of digital image resources are generated from various image acquisition systems every day. refers to images that exist on the World Wide Web) is not only the most pressing need of users, but also the current top priority of image understanding. In quite a few cases, users don't care about the overall meaning expressed by the image, but pay more attention to the region of interest in the image that has a specific meaning. Commonly used image segmentation methods can be roughly divided into two categories: region-based segmentation and boundary-based segmentation. Although there are many mature segmentation algorithms, they all have their own limitations and pertinence. [0003] Image segmentation base...

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 Patents(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 Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com