An efficient bi-layer content based image retrieval system

Large amount of multi-media content, generated by various image capturing devices, is shared and downloaded by millions of users across the globe, every second. High computation cost is inured in providing visually similar results to the user's query. Annotation based image retrieval is not efficient since annotations vary in terms of languages while pixel wise matching of images is not preferred since the orientation, scale, image capturing style, angle, storage pattern etc. bring huge amount of variations in the images. Content Based Image Retrieval (CBIR) system is frequently used in such cases since it computes similarity between query image and images of reference dataset efficiently. A Bi-layer Content Based Image Retrieval (BiCBIR) system has been proposed in this paper which consists of two modules: first module extracts the features of dataset images in terms of color, texture and shape. Second module consists of two layers: initially all images are compared with query image for shape and texture feature space and indexes of M most similar images to the query image are retrieved. Next, M images retrieved from previous layer are matched with query image for shape and color feature space and F images similar to the query image are returned as a output. Experimental results show that BiCBIR system outperforms the available state-of-the-art image retrieval systems.