A novel approach to the extraction of multiple salient objects in an image

This paper describes a novel approach for extraction of multiple objects from a given image of a natural scene. In the proposed approach, multiple objects are extracted by the application of saliency detection on the image. We use two distinct approaches for object extraction. One approach uses superpixels on the saliency map. Then the intensity of saliency map in each superpixel is used to compute distance between the centres of superpixels. These act as constraints to extract the objects from the image. The other approach is the application of Active Contour model on the saliency map and estimating a bounding box on the intermediate binary image result extracts the objects in the image. The approach is unique in its way of extracting objects from a scene containing multiple objects as it does not use extensive image search like the existing algorithms and therefore leads to a fast and simple extraction.