To Improve Content Based Face Retrieval By Creating Semantic Code Words

Abstract

The importance and the complete amount of human face photos make manipulations e.g., search and mining of large-scale human face images a really vital research problem and allow many real world applications. We aim to make use of automatically detected human attributes that contain semantic prompts of the face photos to improve content based face retrieval by constructing semantic code words for efficient large-scale face retrieval. By leveraging human attributes in a scalable and systematic framework we propose two orthogonal methods named attribute-enhanced sparse coding and attribute embedded inverted indexing to perk up the face retrieval in the offline and online stages. We examine the efficiency of different attributes and vital factors necessary for face retrieval. The purpose in this paper is to deal with one of the imperative and challenging problems large-scale content-based face image retrieval. Given a uncertainty face image content-based face image retrieval seeks to find similar face images from a large image database. It is and facilitates equipment for many applications including automatic face annotation crime investigation etc.