LS-SVM-based image segmentation using pixel color-texture descriptors

ISCAS OpenIR

	LS-SVM-based image segmentation using pixel color-texture descriptors
	Yang, Hong-Ying; Zhang, Xian-Jin; Wang, Xiang-Yang
	2014
发表期刊	PATTERN ANALYSIS AND APPLICATIONS
ISSN	1433-7541
卷号	17 期号:2 页码:341-359
摘要	Image segmentation remains an important, but hard-to-solve, problem since it appears to be application dependent with usually no a priori information available regarding the image structure. Moreover, the increasing demands of image analysis tasks in terms of segmentation results' quality introduce the necessity of employing multiple cues for improving image-segmentation results. In this paper, we present a least squares support vector machine (LS-SVM) based image segmentation using pixel color-texture descriptors, in which multiple cues such as edge saliency, color saliency, local maximum energy, and multiresolution texture gradient are incorporated. Firstly, the pixel-level edge saliency and color saliency are extracted based on the spatial relations between neighboring pixels in HSV color space. Secondly, the image pixel's texture features, local maximum energy and multiresolution texture gradient, are represented via nonsubsampled contourlet transform. Then, both the pixel-level edge color saliency and texture features are used as input of LS-SVM model (classifier), and the LS-SVM model (classifier) is trained by selecting the training samples with Arimoto entropy thresholding. Finally, the color image is segmented with the trained LS-SVM model (classifier). This image segmentation not only can fully take advantage of the human visual attention and local texture content of color image, but also the generalization ability of LS-SVM classifier. Experimental results show that our proposed method has very promising segmentation performance compared with the state-of-the-art segmentation approaches recently proposed in the literature.; Image segmentation remains an important, but hard-to-solve, problem since it appears to be application dependent with usually no a priori information available regarding the image structure. Moreover, the increasing demands of image analysis tasks in terms of segmentation results' quality introduce the necessity of employing multiple cues for improving image-segmentation results. In this paper, we present a least squares support vector machine (LS-SVM) based image segmentation using pixel color-texture descriptors, in which multiple cues such as edge saliency, color saliency, local maximum energy, and multiresolution texture gradient are incorporated. Firstly, the pixel-level edge saliency and color saliency are extracted based on the spatial relations between neighboring pixels in HSV color space. Secondly, the image pixel's texture features, local maximum energy and multiresolution texture gradient, are represented via nonsubsampled contourlet transform. Then, both the pixel-level edge color saliency and texture features are used as input of LS-SVM model (classifier), and the LS-SVM model (classifier) is trained by selecting the training samples with Arimoto entropy thresholding. Finally, the color image is segmented with the trained LS-SVM model (classifier). This image segmentation not only can fully take advantage of the human visual attention and local texture content of color image, but also the generalization ability of LS-SVM classifier. Experimental results show that our proposed method has very promising segmentation performance compared with the state-of-the-art segmentation approaches recently proposed in the literature.
收录类别	SCI
关键词	Image Segmentation Least Squares Support Vector Machine Human Visual Attention Local Texture Content Arimoto Entropy Thresholding
部门归属	[Yang, Hong-Ying; Zhang, Xian-Jin; Wang, Xiang-Yang] Liaoning Normal Univ, Sch Comp & Informat Technol, Dalian 116029, Peoples R China. [Wang, Xiang-Yang] Chinese Acad Sci, Inst Software, State Key Lab Informat Secur, Beijing 100190, Peoples R China.
语种	英语
WOS记录号	WOS:000334523200008
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16867
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Yang, Hong-Ying,Zhang, Xian-Jin,Wang, Xiang-Yang. LS-SVM-based image segmentation using pixel color-texture descriptors[J]. PATTERN ANALYSIS AND APPLICATIONS,2014,17(2):341-359.
APA	Yang, Hong-Ying,Zhang, Xian-Jin,&Wang, Xiang-Yang.(2014).LS-SVM-based image segmentation using pixel color-texture descriptors.PATTERN ANALYSIS AND APPLICATIONS,17(2),341-359.
MLA	Yang, Hong-Ying,et al."LS-SVM-based image segmentation using pixel color-texture descriptors".PATTERN ANALYSIS AND APPLICATIONS 17.2(2014):341-359.