An object recognition algorithm with structure-guided saliency detection and SVM classifier

Computer Vision is a field which deals with extracting, analyzing, processing and understanding the images. One of the major application of computer vision is Object Recognition. In this paper, an algorithm is proposed where, object recognition requires two tasks: (i) Object Detection and (ii) Object Classification. The former task, extracts constructive information from the image and detects the objects. Computational modeling of human visual system enables various applications and one of which include object detection. Therefore, saliency detection provides an effective method for object detection. The final task of the object recognition is object classification. Histogram of Gradient features are extracted from the saliency active region and given to a conventional SVM classifier. The accuracy of the proposed work has been experimentally evaluated in the ETH-80 dataset.