Feature Extraction in Content based Image Retrieval

Abstract

A technique for Content Based Image Retrieval (CBIR) for the generation of image content descriptor which exploiting the advantage of low complexity Order Dither Block Truncation Coding (ODBTC). The quantizer and bitmap image are the compressed form of image obtained from the ODBTC technique in encoding step. Decoding is not performed in this method. It has two image feature such as Color Co-occurrence Feature (CCF) and Bit Pattern Feature (BPF) for indexing the image. These features are directly obtained from ODBTC encoded data stream. By comparing with the BTC image retrieval system and other earlier method the experimental result show the proposed method is superior. ODBTC is suited for image compression and it is a simple and effective descriptor to index the image in CBIR system. Content-based image retrieval is a technique which is used to extract the images on the basis of their content such as texture, color, shape and spatial layout. In order to minimize this gap many concepts was introduced. Moreover, Images can be stored and extracted based on various features and one of the prominent feature is Texture.