Visual reranking approach using Pyramid structure wavelet transform for image retrieval

Rapid advances in computers and communication technology is pushing the existing information processing tools to their limits. The past few years have seen an overwhelming accumulation of media rich digital data such as images, video, and audio. The internet is an excellent example of a distributed database containing several millions of images. Image search has become a popular feature in many search engines, including Google, Yahoo!, MSN, etc., majority of which use very little, if any, image information[1]. Image Retrieval system is a powerful tool in order to manage large scale image databases. Retrieving images from large and varied collections using image content as a key is a challenging and important problem. Due to the success of text based search of Web pages and in part, to the difficulty and expense of using image based signals, most search engines return images solely based on the text of the pages from which the images are linked. No image analysis takes place to determine relevance/quality. This can yield results of inconsistent quality. So, such kind of visual search approach has proven unsatisfying as it often entirely ignores the visual content itself as a ranking signal. To address this issue, we present a new image ranking and retrieval technique known as visual reranking, defined as reordering of visual images based on their visual appearance. This approach relies on analyzing the distribution of visual similarities among the images and image ranking system that finds the multiple visual themes and their relative strengths in a large set of images. The major advantages of this approach is that, it improves the search performance by reducing the number of irrelevant images acquired as the result of image search and provides quality consistent output. Also, it performs text based search on database to get ranked images and extract features of them to obtain reranked images by visual search.