Salient Object Detection with Segment Features Using Mean Shift Algorithm

The object recognition has attracted high attention for its diverse applications in everyday life. Due to its importance in this field, academics proposed different algorithms to recognize the desired object in the shortest possible time. This paper introduce a new fast method for saliency object detection in images. This method has four steps: regional feature extraction, segment clustering, saliency score computation and post-processing. This dataset has a diverse set of images including single, multiple and complex object images. The main aim of this paper is the detection of objects in complex images. Introduced method has better performance compared to other methods which were evaluated based on ECSSD dataset. This procedure had shown better performance in compared to RRFC, RFC, DRFI, CHC, and RC. As indicated in the presented results, F-measure of our method was better as 0.03-0.1 compared to other methods.