Abstract
Automatically recognizing human faces with partial occlu- sions is one of the most challenging problems in face analysis commu- nity. This paper presents a novel string-based face recognition approach to address the partial occlusion problem in face recognition. In this ap- proach, a new face representation, Stringface, is constructed to integrate the relational organization of intermediate-level features (line segments) into a high-level global structure (string). The matching of two faces is done by matching two Stringfaces through a string -to-string match- ing scheme, which is able to efficiently find the most discriminative lo- cal parts (substrings) for recognition without making any assumption on the distributions of the deformed facial regions. The proposed ap- proach is compared against the state-of-the-art algorithms using both the AR database and FRGC (Face Recognition Grand Challenge) ver2.0 database. Very encouraging experimental results demonstrate, for the first time, the feasibility and effectiveness of a high-level syntactic method in face recognition, showing a new strategy for face representation and recognition.