Ordered Dither Block Truncation Coding For Content Based Image Retrieval Using Relevance Feedback

Abstract

: Now a days, content based image retrieval (CBIR) plays an important role in the image retrieval systems. Ordered dither block truncation coding (ODBTC) is applied in proposed system for CBIR which have relevance feedback mechanism. In this system features of an image are extracted using ODBTC for the generation of image content descriptor. ODBTC offers a simple and effective way to index images in CBIR system. ODBTC compresses an image block into minimum quantizer, maximum quantizer and bitmap image. The proposed image retrieval system generates Color co-occurrence feature (CCF) and bit pattern feature (BPF) from the maximum quantizer, minimum quantizer and bitmap image respectively .To be more profitable, relevance feedback technique is applied into CBIR so that more precise results can be obtained by taking users feedback into account. The method proposed here is superior to the block truncation coding and earlier methods.