Abstract: This paper mainly introduces the application of linear transformation matrix in pattern recognition,face recognition based on Principal Component Analysis (PCA) and Two-dimensional Principal Component Analysis (2DPCA).and the source and algorithm in matrix theory.A kind of innovative method of analyzing is put forward,namely PCA+2DPCA,which is to get the engenvector through 2DPCA and achieve the optimal compress through PCA,and thus reduce the number of dimensions.

Key words: linear transformation, face recognition, PCA；2DPCA；PCA+2DPCA