Title :
Unsupervised image segmentation using local homogeneity analysis
Author :
Jing, Feng ; Li, Mingjing ; Zhang, Hong-Jiang ; Zhang, Bo
Abstract :
In this paper, a novel method is presented for unsupervised image segmentation based on local homogeneity analysis. First, a criterion for homogeneity of a certain pattern is proposed. Applying the criterion to local windows in the original image results in the "H-image". The high and low values of the H-image correspond to possible region boundaries and region interiors respectively. Then, a region growing method is used to segment the image based on the H-image. Finally, visually similar regions are merged together to avoid over-segmentation. Experimental results on real images show the effectiveness and robustness of the method.
Keywords :
image segmentation; image texture; merging; pattern classification; H-image; automatic image segmentation; image local windows; image merging; image texture; local homogeneity analysis; pattern homogeneity criterion; region boundaries; region growing method; region interiors; unsupervised image segmentation; visually similar region merging; Asia; Computer vision; Content based retrieval; Image analysis; Image retrieval; Image segmentation; Intelligent systems; Object recognition; Quantization; Robustness;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1206008
