Performance Enhancement of Scalable Face Image Retrieval Using Multi Reference Re-Ranking

Image retrieval requires a system to find information relevant to a query which represents images containing faces of the same person appearing in the query image. In this paper, we aim to build a scalable face image retrieval system. For this purpose, we develop a new scalable face representation using Gray level co-occurrence matrix(GLCM) features at different orientation (45,60,90 degrees),gray level and moment invariant features, orientation histogram features and Law’s texture features.The extracted features are trained and classified by feed forward back propagation neural network and Support vector machine (SVM) classifier to rank the candidate images. The performance of the designed face image retrieval system will be analyzed in terms of Accuracy and retrieval rate .The performance of the proposed retrieval system will be compared with existing system. In this proposed system we aim to build a scalable face image retrieval system. For this purpose, we develop a new scalable face representation using both local and global features. In the indexing stage, we exploit special properties of faces to design new component based local features, which are subsequently quantized into visual words using a novel identity-based quantization scheme. We also use a very small Hamming signature (40 bytes) to encode the discriminative global feature for each face. In the retrieval stage, candidate images are firstly retrieved from the inverted index of visual words. We then use a new multi-reference distance to re-rank the candidate images using the Hamming signature. On a one million face database, we show that our local features and global Hamming signatures are complementary the inverted index based on gray level and moment invariant features provides candidate images with good recall, while the multi-reference re-ranking with global Hamming signature leads to good precision.