5 August 2010 Unsupervised salient object segmentation from color images
Author Affiliations +
Proceedings Volume 7744, Visual Communications and Image Processing 2010; 77441Q (2010); doi: 10.1117/12.863360
Event: Visual Communications and Image Processing 2010, 2010, Huangshan, China
Abstract
This paper proposes an efficient approach for unsupervised segmentation of salient objects from color images. A set of Gaussian models are first estimated based on a pre-segmentation result of the input image, and then for each pixel, a set of normalized color likelihood measures to each Gaussian model are calculated. The color saliency and spatial saliency of Gaussian models are exploited to generate the pixel-wise saliency map. By thresholding the saliency map, the pixels are classified into object seed pixels, background seed pixels and uncertain pixels to obtain the trimap. For each pixel, the probability belonging to salient object/background is evaluated using kernel density estimation, and the geodesic distances to salient object and background are calculated based on the object likelihood map. By comparing the two geodesic distances, uncertain pixels are finally classified into salient object or background. Experimental results demonstrate the better segmentation performance of the proposed approach.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhi Liu, Lu Wang, Liquan Shen, Zhaoyang Zhang, "Unsupervised salient object segmentation from color images", Proc. SPIE 7744, Visual Communications and Image Processing 2010, 77441Q (5 August 2010); doi: 10.1117/12.863360; https://doi.org/10.1117/12.863360
PROCEEDINGS
10 PAGES


SHARE
KEYWORDS
Image segmentation

RGB color model

Visualization

Color image processing

Distance measurement

Image processing

Image retrieval

RELATED CONTENT


Back to Top