Multilinear Tensor Supervised Neighborhood Embedding Analysis for View-Based Object Recognition

Abstract

In this paper, we propose a multilinear (N-Dimensional) Tensor Supervised Neighborhood Embedding (called ND-TSNE) for discriminant feature representation, which is used for view-based object recognition. ND-TSNE use a general N ^th order tensor discriminant and neighborhood-embedding analysis approach for object representation. The benefits of ND-TSNE include: (1) a natural way of representing data without losing structure information, i.e., the information about the relative positions of pixels or regions; (2) a reduction in the small sample size problem which occurs in conventional supervised learning because the number of training samples is much less than the dimensionality of the feature space; (3) a neighborhood structure preserving in tensor feature space for object recognition and a good convergence property in training procedure. With Tensor-subspace features, the random forests as a multi-way classifier is used for object recognition, which is much easier for training and testing compared with multi-way SVM. We demonstrate the performance advantages of our proposed approach over existing techniques using experiments on the COIL-100 and the ETH-80 datasets.