Complex network based salient region detection using regional color contrast and color distribution

The process of salient regions detection in the field of computer vision has increasingly become very popular topic. In recent years, lots of research works have been carried out and lots of various techniques have been developed on this topic. Detected regions plays an important role in many computer vision applications such as salient object detection, image retrieval, image retargeting - seam carving, image and video compression as an input. In the proposed frameworks, saliency maps are generated by highlighting foreground pixels/regions attracting human visual attention and suppressing background pixels/regions. In previous studies, to generate saliency maps are generally used to image's color, orientation, texture, luminance and location information. In this thesis, it has been studied on generating saliency maps by using complex network, histogram, color, location and area information in the segmented image with superpixel method. The proposed system's success and consistency are illustrated by comparing with the results of previous methods which have been gathered with a publicly available dataset.