Title: Gradient vector flow combined saliency analysis for active contours

Authors: Ruzheng Zhao; Zhiheng Zhou; Ming Dai; Jie Tang

Addresses: School of Electronic and Information Engineering, South China University of Technology, GuangZhou City, Guangdong Province 510640, China ' School of Electronic and Information Engineering, South China University of Technology, GuangZhou City, Guangdong Province 510640, China ' School of Electronic and Information Engineering, South China University of Technology, GuangZhou City, Guangdong Province 510640, China ' School of Electronic and Information Engineering, South China University of Technology, GuangZhou City, Guangdong Province 510640, China

Abstract: Image segmentation is one of the key technologies in digital image processing. Gradient vector flow (GVF) active contours model is one of important methods for image segmentation. But GVF method could not deal with complex natural images efficiently. In this paper, a new active contours algorithm is proposed. The proposed algorithm uses the advantage of saliency model in distinguishing objects and background to increasing the ability of GVF method to segment complex images. Experiment results on natural images show the better performances of proposed method compared with the tradition GVF method.

Keywords: image segmentation; edge extraction; GVF; gradient vector flow; active contours models; saliency map.

DOI: 10.1504/IJAMC.2017.085932

International Journal of Advanced Media and Communication, 2017 Vol.7 No.2, pp.81 - 92

Received: 26 May 2016
Accepted: 13 Sep 2016
Published online: 18 Aug 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article