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

Adaptive weight activity contour model construction method based on fractional order differential information and system

A technology of active contour model and fractional differentiation, which is applied in the field of image processing and can solve the problems of sensitive initial contour of image and slow calculation amount.

Active Publication Date: 2016-07-20
SHENZHEN UNIV
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0034] Although the LRCV model can handle non-homogeneous images, it only considers the local information of the image and is sensitive to the initial contour of the image.
In addition, the amount of calculation is also slow

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
  • Adaptive weight activity contour model construction method based on fractional order differential information and system
  • Adaptive weight activity contour model construction method based on fractional order differential information and system
  • Adaptive weight activity contour model construction method based on fractional order differential information and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The invention discloses a method for constructing an adaptive weight active contour model based on fractional differential information, and the specific technical scheme is as follows:

[0064] 1. Proposed model:

[0065] The proposed model mainly includes two items, a global item and a local item. The global term still introduces the data fitting term of the CV model, namely:

[0066] E. G (C,c 1 ,c 2 ) = ∫ in(C) |I-c 1 | 2 dx+∫ out(C) |I-c 2 | 2 dx,(12)

[0067] c in the above formula 1 ,c 2 is defined in equations (5) and (6).

[0068] For the local term, the following first introduces the fractional differential in the Fourier transform domain, then introduces the fractional gradient mode, and then constructs the fractional difference image, and finally constructs a new local term.

[0069] For a given univariate function f(x), its Fourier transform is defined as follows:

[0070] f ^ ( ...

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 provides an adaptive weight activity contour model construction method based on the fractional order differential information and a system. The system comprises an input module, an initiation module, a first calculation module, a second calculation module, a determination module and an output module. The system is advantaged in that fractional order differential is introduced, a new difference image is constructed, a local term is constructed by utilizing the difference image, and a new activity contour model is proposed; by utilizing the fractional order gradient mode information, one adaptive weight is proposed, so local and global terms of the model can be dynamically adjusted; by utilizing change of an inner area of an evolution curve, a new evolution stop standard is proposed, and the evolution curve can automatically stop at a correct boundary.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for constructing an adaptive weight active contour model based on fractional differential information. Background technique [0002] Image segmentation is very important for computer vision, pattern recognition, medical image processing, etc., and the active contour model (active contour model) is one of the important tools for image segmentation. The algorithm first initializes a closed curve in the image, and then moves the initial curve to the boundary of the target object by minimizing the energy functional to obtain the image segmentation result. [0003] According to the different ways of contour evolution, active contour models can be divided into boundary-based models and region-based models. Boundary-based models use boundary information to attract active contours to move toward target boundaries, while region-based models identify different...

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
CPCG06T2207/20004
Inventor 陈波张陈陈文胜潘彬彬周晓慧
Owner SHENZHEN 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