Texture segmentation based on combination of second-order features and spatial information
Lists
Only you see this
Abstract
Texture segmentation is the process of partitioning an image into regions with different textures containing similar group of pixels. Most of segmentation algorithms can be regarded as consisting of two successive processes: feature extraction and feature-based segmentation. In this paper, a new texture segmentation method based on the combination of secondorder features and spatial information is proposed. Our method has been compared with the Only Second-order Features(OSF) based algorithm and the Krishnapuram and Freg's (KF) algorithm by segmenting images from the Brodatz album and a real-life scenery image dataset. The results show that the proposed approach reduces the inaccurate small regions and keeps the edge of contiguous target regions more smooth. In addition, the parameters of filter bank are selected elaborately according to human psychophysics research, thus our algorithm is so intuitive and physiological relevant that it reserves opportunities for further approaches.
BibTeX
@inproceedings{zheng2009texture,
author = {Qingqing Zheng and Nong Sang and Yuehuan Wang and Biao Wang},
title = {{Texture segmentation based on combination of second-order features and spatial information}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {2009},
doi = {10.1117/12.832506},
}Loading related content...