Class Based Image Search with Hash Codes

Abstract

With the proliferation of images on the internet, there is a strong need to develop an efficient image search system. In this paper proposes an efficient image retrieval system using hash codes..Hash codes reduce the memory computation during the search. With the hash codes image matching can be efficiently measured. The hashing method import high level image features in to hamming space performing search based on hamming distance. In this paper proposes mainly two tasks  such as offline processing and online processing .In the offline processing bitwise weight of the hash codes for the predefined classes are generated. In online processing computing query adaptive weight. Then the images can be ranked by weighted hamming distance at a finer grained hash code level.