A direct LDA algorithm for high-dimensional data - with application to face recognition

Linear discriminant analysis (LDA) has been successfully used as a dimensionality reduction technique to many classification problems, such as speech recognition, face recognition, and multimedia information retrieval. The objective is to find a projection A that maximizes the ratio of between-class scatter S _b against within-class scatter S _w (Fisher's criterion): arg \limit _max A AS _bA ^T / AS _wA ^T .