Face recognition across pose variation and the 3S problem

Abstract

Most face recognition methods are based on linear and nonlinear subspace features extraction and classification tasks. These classification methods are used for global and local facial features for person identification. Both local and global features play different roles for recognition and classification. There are a number of face recognition methods that have been proposed up until now, and they produce good results. However, when small sample size (3S) and pose variation problems are taken into consideration, face recognition becomes more complex and does not produce good results. In this paper, 3S and pose variation problems are dealt with. First, linear discriminate analysis (LDA) is considered to minimize the singularity problem that arises when small samples of individuals are available. In the next step, the proposed framework utilizes global and local facial features and constructs a combined subspace using an enhanced LDA method that is discussed later in the sections.