An assembled matrix distance metric for 2DPCA-based image recognition

Two-dimensional principal component analysis (2DPCA) is a novel image representation approach recently developed for image recognition. One characteristic of 2DPCA is that it can extract feature matrix using a straightforward image projection technique. In this paper, we propose an assembled matrix distance metric (AMD) to measure the distance between two feature matrices. To test the efficiency of the proposed distance measure, we use two image databases, the ORL face database and the PolyU palmprint database. The results of our experiments show that the assembled matrix distance metric is very effective in 2DPCA-based image recognition.