Watershed segmentation with boundary curvature ratio based merging criterion

Authors:
Xiaochen He;Nelson H. C. Yung;K. P. Chow;Francis Y. L. Chin;Ronald H. Y. Chung;K. Y. K. Wong;Kenneth S. H. Tsang
Affiliations:
The University of Hong Kong, Hong Kong;The University of Hong Kong, Hong Kong;The University of Hong Kong, Hong Kong;The University of Hong Kong, Hong Kong;Verint Systems (Asia Pacific) Ltd., Asia Pacific Headquarters, Suite, Core F, Cyberport, Hong Kong;The University of Hong Kong, Hong Kong;Verint Systems (Asia Pacific) Ltd., Asia Pacific Headquarters, Suite, Core F, Cyberport, Hong Kong
Venue:
SIP '07 Proceedings of the Ninth IASTED International Conference on Signal and Image Processing
Year:
2007

Citing 5
Cited 0

Integrating Region Growing and Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Yet Another Survey on Image Segmentation: Region and Boundary Information Integration

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A novel merging criterion incorporating boundary smoothness and region homogeneity for image segmentation

PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Hybrid image segmentation using watersheds and fast region merging

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes to incorporate boundary curvature ratio, region homogeneity and boundary smoothness into a single new merging criterion to improve the over-segmentation of marker-controlled watershed segmentation algorithm. The result is a more refined segmentation result with smooth boundaries and regular shapes. To pursue a final segmentation result with higher inter-variance and lower intra-variance, an optimal number of segments could be self-determined by a proposed formula. Experimental results are presented to demonstrate the merits of this method.