Saliency Based Adaptive Image Signature Using Binary Holistic Image Descriptor: A Survey

Finding all objects in a scene and separating them from the background is known as figure-ground separation. For a figure ground separation problem Introduce a simple image descriptor referred to as the image signature. Then show, within the theoretical framework of sparse signal mixing, that this quantity spatially approximates the foreground of an image. Thus experimentally investigate whether this approximate foreground overlaps with visually conspicuous image locations by developing a saliency algorithm based on the image signature. This saliency algorithm predicts human fixation points best among benchmark data set and does so in much shorter running time. In a related experiment, Thus demonstrate with a change blindness data set that the distance between images induced by the image signature is closer to human perceptual distance than can be achieved using other saliency algorithms, pixel-wise, or GIST descriptor methods.