Semantic Hashing Technique for Retrieving Web Facial Images

Semantic Hashing Technique Algorithm to filter the documents given to TF-IDF, higher accuracy can achieve than applying TF-IDF to the entire document set. It Reduces the comparison time by removing Indexing technique and makes the system become more faster. Framework of search-based face annotation (SBFA) is evaluated by mining weakly labelled facial images that are freely available on the World Wide Web (WWW). One challenging problem for search-based face annotation scheme is how to effectively perform annotation by exploiting the list of most similar facial images and their weak labels that are often noisy and incomplete. To tackle this problem, An effective unsupervised label refinement (ULR) approach for refining the labels of web facial images using machine learning techniques is used. By formulating the learning problem as a convex optimization and develop effective optimization algorithms to solve the large-scale learning task efficiently. Clustering-based approximation algorithm is proposed to speed up scheme further, which can improve the scalability considerably. An extensive set of empirical studies on a large-scale web facial image test bed are conducted, in which encouraging results showed that the proposed ULR algorithms can significantly boost the performance of the promising SBFA scheme