Abstract: In this paper, a novel kind of content feature is proposed to be extracted by independent component analysis (ICA) and used for face image retrieval. A novel content-based face image retrieval scheme is created based on this content feature—principle independent content feature (PICF). In this scheme, PICF based on higher order statistics is first extracted in the reduced space for effective representation of face images. To ensure the efficiency of computation and accuracy of retrieval, a PICF-based retrieval method that can eliminate the ambiguity in the order of independent features is used in the face image retrieval stage with the ORL database, where the images vary in illumination, expression, pose, and scale. The simulation proves the feasibility of the proposed PICF-based method and the highest  accuracy can reach 100%, and  the average precision  reaches 95.14% per thousand experiments in our simulations.

Key words: independent component analysis, principal component analysis, image retrieval, feature extraction, similarity measurement, average precision