文章基本信息

标题：Estimating Normalized Attention of Viewers on Account of Relative Visual Saliency of Faces (NRVS)
本地全文：下载
作者：Ravi kant kumar ; Jogendra Garain ; Goutam Sanyal 等
期刊名称：International Journal of Software Engineering and Its Applications
印刷版ISSN：1738-9984
出版年度：2015
卷号：9
期号：7
页码：85-92
DOI：10.14257/ijseia.2015.9.7.09
出版社：SERSC
摘要：Humans psychological and behavioral understanding often lead to make natural decision which accurately identifies and remembers the faces which are highly appreciated or criticized by themselves in comparing to the normal viewed faces, in terms of beauty, ugliness or unique appearance. It happens due to human psychology of being biased towards the salient face in the process of face recognition and identification. This paper attempts a novel method to measure, how our attention is more restricted towards some particular faces in the crowd. This restricted attention is strongly guided by the relative visual saliency of these faces. In this paper, normalized relative visual saliency (NVRS) of the faces is evaluated using their intensity values modulated with respective spatial distance. Experiment has been carried out on test image dataset via bottom up approach. The experimental results are found to be encouraging and accuracy has also been measured exhibiting efficacy of the proposed approach.
关键词：Face Recognition; Visual Saliency; Face Identification; Visual Attention