arrow
Return

Bayesian salient object detection based on saliency driven clustering

delete2014-03-01
delete11
PRE
AI
L
Lei Zhou
K
Keren Fu
Y
Yijun Li
Y
Yu Qiao
X
Xiangjian He
杨
杨洁 (Jie Yang) *
DOI:10.1016/j.image.2014.01.001delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Salient object detection is essential for applications, such as image classification, object recognition and image retrieval. In this paper, we design a new approach to detect salient objects from an image by describing what does salient objects and backgrounds look like using statistic of the image. First, we introduce a saliency driven clustering method to reveal distinct visual patterns of images by generating image clusters. The Gaussian Mixture Model (GMM) is applied to represent the statistic of each cluster, which is used to compute the color spatial distribution. Second, three kinds of regional saliency measures, i.e, regional color contrast saliency, regional boundary prior saliency and regional color spatial distribution, are computed and combined. Then, a region selection strategy integrating color contrast prior, boundary prior and visual patterns information of images is presented. The pixels of an image are divided into either potential salient region or background region adaptively based on the combined regional saliency measures. Finally, a Bayesian framework is employed to compute the saliency value for each pixel taking the regional saliency values as priority. Our approach has been extensively evaluated on two popular image databases. Experimental results show that our approach can achieve considerable performance improvement in terms of commonly adopted performance measures in salient object detection. (C) 2014 Elsevier B.V. All rights reserved.
Keywords:
Saliency object detection
Saliency driven clustering
Regional saliency computation
Bayesian model

Journal

S
Signal Processing and Image Communication
IF:
2.7
Papers:
2.8K
Citations:
4.2K

Organization

S
shanghai jiao tong university
Scholars:
15.7W
Papers: 11.7W
Citations: 159
U
university of technology sydney
Scholars:
1.6W
Papers: 2.0W
Citations: 25
Cited Papers

Cited Papers

EFFECT OF ANDROGENS ON STRUCTURE AND RATE OF CROWING IN THE JAPANESE QUAIL (COTURNIX JAPONICA)
err2000-01-01
err0
PREAI
errLaura Beani; Federica Briganti; Giuseppe Campanella; Concetta Lupo; Francesco Dessi-Fulgheri
errShare
errSave
Modeling attention to salient proto-objects
err2006-11-01
err1.0K
PREAI
errWalther, Dirk; Koch, Christof
errShare
errSave
Collagen degradation products measured in serum can separate ovarian and breast cancer patients from healthy controls: A preliminary study
err2015-11-24
err0
errOAAI
errC.L. Bager; N. Willumsen; D.J. Leeming; V. Smith; M.A. Karsdal; D. Dornan; A.C. Bay-Jensen
errShare
errSave
The role of context in object recognition
err2007-12-01
err751
PREAI
errOliva, Aude; Torralba, Antonio
errShare
errSave
O(N) implementation of the fast marching algorithm
err2006-03-01
err177
errOAAI
errYatziv, L; Bartesaghi, A; Sapiro, G
errShare
errSave
researcher View more