New local segmentation model for images with intensity inhomogeneity

Qiang Zheng; En-Qing Dong

doi:10.1117/1.OE.51.3.037006

4 April 2012 New local segmentation model for images with intensity inhomogeneity

Qiang Zheng, En-Qing Dong

Author Affiliations +

Optical Engineering, Vol. 51, Issue 3, 037006 (April 2012). https://doi.org/10.1117/1.OE.51.3.037006

Abstract

A new local segmentation model based on binary level set for images with intensity inhomogeneity is proposed. The local segmentation property is guaranteed with the gradient function of the binary level set function (LSF), and the curve evolution precision can be accurate to one-pixel width. Due to utilizing more statistical information which contains local interior, local exterior, and global interior information, the new segmentation energy is more adaptable for local segmentation in the case of intensity inhomogeneity. Since the contour is initialized as a small shape inside the desired object and inflated afterwards in local segmentation, a morphological closing operation is used to regularize the binary LSF, which not only can promote curve inflating, but also can maintain the binary property of the LSF. Experiments on medical images show that the proposed model is more effective and robust than the Chan-Vese (CV), local binary fitting (LBF), localizing region-based active contours (LR-AC), and selective binary and Gaussian filtering regularized level set method (SB-GFRLS) models in local segmentation for images with intensity inhomogeneity.

Citation Download Citation

Qiang Zheng and En-Qing Dong "New local segmentation model for images with intensity inhomogeneity," Optical Engineering 51(3), 037006 (4 April 2012). https://doi.org/10.1117/1.OE.51.3.037006

Published: 4 April 2012

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available