An improved salient region detection algorithm using integrated characteristics of region

Salient region-based image retrieval is one of the hotspots in the domain of content-based image retrieval; however the metrics about region saliency is not in the uniform frame. The research on visual attention has shown that the factors including color, texture, scale and position influence on visual perception mostly. Consequently, the algorithm of salient region extraction is proposed by using four mentioned characteristics above. In the proposed algorithm, Luminance variety is used as Luminance feature of Regions; and three main colors and multi-resolution Gabor feature are respectively used for color and texture; the proportion between the region and its located image is used for scale feature of region; the distance between the centric of region and that of image is used for position feature of region. Experiment results show salient regions extracted by the proposed algorithm accord with the human perception well.