Visual Search Based on Contour Salient

Online shopping is becoming more and more popular for a number of reasons; prices are often lower online, you don´t have to queue up in busy shops and you can buy almost any product imaginable with just a few clicks of your mouse. But the general problems of shopping Web site is that, most of the existing online shops list products based on keywords. As the inherent limitation, keyword browsing makes it difficult to find the exact products that human being desire. In this paper, we propose a visual search algorithm based on contour salient. The proposed approach extracts the object edge using Canny edge detector, and then chooses the salient point from the contour based on the points´ contour flexibility. We perform Fourier transformation to these salient points and a shape normalization procedure to generate the descriptor representing the shape feature. Finally, SVM and dynamic time warping method are used to train the database images and compute the distance between query image and test image. Experimental result shows our method is effective to search the similar product images with query.