Image Classification Based on New Matrix Distance
Xinbin Zhao · Journal of Information and Computational Science · 2015
Image classiflcation problem has been the highlight in the fleld of machine learning. Most of the traditional learning algorithms are based on the vector space model, but in computer vision research, gray images are naturally represented by matrices. However, learning machine based on matrix often sufiers from the problem that the Traditional Euclidean Distance (TED) for images without preserving the natural matrix structure. In this paper, we present a novel Linear Support Matrix Machine (LSMM) based on New Matrix Distance (NMD), which integrates the merits of Classical Support Vector Machine (C-SVM) and the NMD of matrix data. Difierent with the TED, which is constrained by orthogonality assumption, NMD measures the distance between matrix points by considering the spatial relationships of pixels of matrix. Therefore, NMD is robust to small perturbation of images. Using some benchmark face recognition databases, we demonstrate a consistent performance improvement of LSMM embedded with the NMD over their original versions.