GACV: Geodesic-aided C-V method

被引：48

作者：

Chen, Li ^{[1
]}

Zhou, Yue ^{[1
]}

Wang, Yonggang ^{[1
]}

Yang, Jie ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai 200240, Peoples R China

来源：

PATTERN RECOGNITION | 2006年 / 39卷 / 07期

关键词：

image processing; image segmentation; deformable model; active contour; C-V method; geodesic active contours;

D O I：

10.1016/j.patcog.2006.01.017

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel algorithm for image segmentation is proposed. The proposed method incorporates geodesic curves and C-V method to raise active contours' performance on image segmentation. Moreover, we extend our method to color images. By practical experiments, it is verified that our model obtains better results than original methods, especially with respect to images within holes, complex background, weak edges, and noise. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1391 / 1395

页数：5

共 5 条

[1]

CHAN FT, 2001, IEEE T IMAGE PROCESS, V2, P266

[2] Active contours without edges for vector-valued images [J].

Chan, TE ;

Sandberg, BY ;

Vese, LA .

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2000, 11 (02) :130-141

[3]

GUILLERMO S, 1997, COMPUT VISION IMAGE, V68, P247

[4]

MALLADI R, 1995, IEEE T PATTERN ANAL, V1

[5] A multiphase level set framework for image segmentation using the Mumford and Shah model [J].

Vese, LA ;

Chan, TF .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2002, 50 (03) :271-293

← 1 →