Salient Region Detection with Convex Hull Overlap

12/10/2016 ∙ by Yongqing Liang, et al. ∙ 0

In this paper, we establish a novel bottom-up cue named Convex Hull Overlap (CHO), and then propose an effective approach to detect salient regions using the combination of the CHO cue and global contrast cue. Our scheme significantly differs from other earlier work in: 1) The hierarchical segmentation model based on Normalized Graph-Cut fits the splitting and merging processes in human visual perception; 2) Previous work only focuses on color and texture cues, while our CHO cue makes up the obvious gap between the spatial region covering and the region saliency. CHO is a kind of improved and enhanced Gestalt cue, while other popular figure-ground cues such as convexity and surroundedness can be regarded as the special cases of CHO. Our experiments on a large number of public data have obtained very positive results.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.