A novel classification measure based on matrix volume according to the high dimensional geometry theory is proposed for face recognition. Many two dimensional PCA (2DPCA)-based face recognition methods almost pay much attention to the feature extraction, and the classification measure is little investigated. The typical classification measure used in 2DPCA is the sum of the Euclidean distance between two feature vectors in feature matrix, called traditional Distance Measure (DM). However, this proposed method is to compute the matrix volume. To test its performance,experiments are done based on ORL and AR face databases. The experimental results show the Matrix Volume Measure (MVM) is more efficient than the DM in 2DPCA-based face recognition.