An Improved Technique to Compute Visual Attention Map based upon Wavelet Domain

Abstract

Visual system of human beings does not process the complete area of image rather focus upon limited area of visual image. But in which area does the visual attention focused is a topic of hot research nowadays. Research on psychological phenomenon indicates that attention is attracted to features that differ from its surroundings or the one that are unusual or unfamiliar to the human visual system. Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. Object or region based image processing can be performed more efficiently with information pertaining locations that are visually salient to human perception with the aid of a saliency map. The saliency map is a master topological map having the possible locations of objects or regions which a human perceived as important/salient. In this paper a method for computing the saliency map in wavelet transform domain has been proposed. Earlier works in this domain although calculated the saliency very efficiently but they just involve the approximation components of DWM, the detail components have not been taken care but in many applications these detailed components are of great importance to highlight the smaller but visually important components.