IPSJ Online Transactions
Online ISSN : 1882-6660
ISSN-L : 1882-6660
Salient Object Detection Based on Direct Density-ratio Estimation
Masao YamanakaMasakazu MatsuguMasashi Sugiyama
Author information
JOURNALS FREE ACCESS

2013 Volume 6 Pages 96-103

Details
Abstract

Detection of salient objects in images has been an active area of research in the computer vision community. However, existing approaches tend to perform poorly in noisy environments because probability density estimation involved in the evaluation of visual saliency is not reliable. Recently, a novel machine learning approach that directly estimates the ratio of probability densities was demonstrated to be a promising alternative to density estimation. In this paper, we propose a salient object detection method based on direct density-ratio estimation, and demonstrate its usefulness in experiments.

Information related to the author
© 2013 by the Information Processing Society of Japan
Previous article Next article
feedback
Top