Unsupervised color image segmentation using a dynamic color gradient thresholding algorithm

被引：14

作者：

Balasubramanian, Guru Prashanth ^{[1
]}

Saber, Eli ^{[1
]}

Misic, Vladimir ^{[2
]}

Peskin, Eric ^{[1
]}

Shaw, Mark ^{[3
]}

机构：

[1] Rochester Inst Technol, Dept Elect Engn, Rochester, NY 14623 USA

[2] Thomas Jefferson Univ, Radiat Oncol, Philadelphia, PA 19107 USA

[3] Hewlett Packard Corp, Color & Imaging, Boise, ID 83714 USA

来源：

HUMAN VISION AND ELECTRONIC IMAGING XIII | 2008年 / 6806卷

关键词：

color image segmentation; color gradient; dynamic thresholding; agglomerative merging;

D O I：

10.1117/12.766184

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

We propose a novel algorithm for unsupervised segmentation of color images. The proposed approach utilizes a dynamic color gradient thresholding scheme that guides the region growing process. Given a color image, a weighted vector-based color gradient map is generated. Seeds are identified and a dynamic threshold is then used to perform reliable growing of regions on the weighted gradient map. Over-segmentation, if any, is addressed by a Similarity Measure-based region merging stage to produce the final segmented image. Comparative results demonstrate the effectiveness of this algorithm for color image segmentation.

引用

页数：9

共 11 条

[1]

[Anonymous], THESIS U CALIFORNIA

[2] Region-growing approach to colour segmentation using 3-D clustering and relaxation labelling [J].

Cheng, SC .

IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING, 2003, 150 (04) :270-276

[3] Mean shift: A robust approach toward feature space analysis [J].

Comaniciu, D ;

Meer, P .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619

[4] Unsupervised segmentation of color-texture regions in images and video [J].

Deng, YN ;

Manjunath, BS .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (08) :800-810

[5] DETECTING BOUNDARIES IN A VECTOR FIELD [J].

LEE, HC ;

COK, DR .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1991, 39 (05) :1181-1194

[6] Segmentation of color images using multiscale clustering and graph theoretic region synthesis [J].

Makrogiannis, S ;

Economou, G ;

Fotopoulos, S ;

Bourbakis, NG .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2005, 35 (02) :224-238

[7]

NGUYEN HT, 1998, 4 U AMST INT SENS IN

[8] THRESHOLD SELECTION METHOD FROM GRAY-LEVEL HISTOGRAMS [J].

OTSU, N .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1979, 9 (01) :62-66

[9]

Ruzon M. A., 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), P160, DOI 10.1109/CVPR.1999.784624

[10] Fusion of color and edge information for improved segmentation and edge linking [J].

Saber, E ;

Tekalp, AM ;

Bozdagi, G .

IMAGE AND VISION COMPUTING, 1997, 15 (10) :769-780

← 1 2 →