期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2013
卷号：2
期号：5
页码：1635
出版社：S&S Publications
摘要：In this paper a method is presented to identify co-attention objects from an image pair. This method providesan effective way to predict human fixations within multi-images, and robustly highlight co-salient regions. This methodgenerates the SISM by computing three visual saliency maps within each image. For the MISM computation, a comultilayergraph is introduced using a spatial pyramid representation for the image pair. Two types of descriptors (i.e.,color and texture visual descriptors) are extracted for each region node, which are then used to compute the similaritybetween a node-pair. Finally, a fast single-pair SimRank algorithm is employed to measure the similarity based on thenormalized SimRank score.
