Saliency Detection: A Spectral Residual Approach

The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features...

Full description

Saved in:
Bibliographic Details
Published in:2007 IEEE Conference on Computer Vision and Pattern Recognition pp. 1 - 8
Main Authors: Xiaodi Hou, Liqing Zhang
Format: Conference Proceeding
Language:English
Japanese
Published: IEEE 01.06.2007
Subjects:
Computational modeling
Humans
Image analysis
Image coding
Machine vision
Object detection
Object recognition
Redundancy
Statistical distributions
Visual system
ISBN:9781424411795, 1424411793
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features, categories, or other forms of prior knowledge of the objects. By analyzing the log-spectrum of an input image, we extract the spectral residual of an image in spectral domain, and propose a fast method to construct the corresponding saliency map in spatial domain. We test this model on both natural pictures and artificial images such as psychological patterns. The result indicate fast and robust saliency detection of our method.
ISBN:9781424411795
1424411793
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2007.383267