Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/99710
Title: Texture aware image segmentation using graph cuts and active contours
Authors: Zhou, Hailing
Zheng, Jianmin
Wei, Lei
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2012
Source: Zhou, H., Zheng, J., & Wei, L. (2012). Texture aware image segmentation using graph cuts and active contours. Pattern recognition, 46(6), 1719-1733.
Series/Report no.: Pattern recognition
Abstract: The problem of segmenting a foreground object out from its complex background is of great interest in image processing and computer vision. Many interactive segmentation algorithms such as graph cut have been successfully developed. In this paper, we present four technical components to improve graph cut based algorithms, which are combining both color and texture information for graph cut, including structure tensors in the graph cut model, incorporating active contours into the segmentation process, and using a “softbrush” tool to impose soft constraints to refine problematic boundaries. The integration of these components provides an interactive segmentation method that overcomes the difficulties of previous segmentation algorithms in handling images containing textures or low contrast boundaries and producing a smooth and accurate segmentation boundary. Experiments on various images from the Brodatz, Berkeley and MSRC data sets are conducted and the experimental results demonstrate the high effectiveness of the proposed method to a wide range of images.
URI: https://hdl.handle.net/10356/99710
http://hdl.handle.net/10220/17541
ISSN: 0031-3203
DOI: http://dx.doi.org/10.1016/j.patcog.2012.12.005
metadata.item.grantfulltext: none
metadata.item.fulltext: No Fulltext
Appears in Collections:SCSE Journal Articles

Page view(s)

477
checked on Dec 24, 2019

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.