A Saliency Detection Model Based on Wavelet Transform Through Fusion of Color Spaces

Visual attention is studied by detecting a salient object in an input image. Visual attention is used in various image processing applications such as image segmentation, patch rarities, pattern recognition etc. In this paper, the saliency measurement is performed by using wavelet transform.  In the proposed model we introduce a saliency measurement model based on two color spaces. One is the RGB and second is Lab. Both colour spaces gives six different channels and those channels generates different feature maps using wavelet transform. Next, the measures of saliency (local and global) are calculated and fused to indicate saliency of each patch. Local saliency is distinctiveness of a patch from its surrounding patches. Global saliency is the inverse of a patch’s probability of happening over the entire image. The final saliency map is built by normalizing and fusing local and global saliency maps of all channels from both color systems. Experimental evaluation gives the better results from the proposed model.

Key Words: Saliency Map, Wavelet Transform, local saliency, global saliency