TENSOR OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS NETWORK
Abstract
This paper proposes an multilinear discriminant analysis network (MLDANet) for the recognition of multidimensional objects, knows as tensor objects. The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms. The MLDANet consists of three parts: 1) The encoder learned by MLDA from tensor data. 2) Features maps obtained from decoder. 3) The use of binary hashing and histogram for feature pooling. A learning algorithm for MLDANet is described. Evaluations on UCFll database indicate that the proposed MLDANet outperforms the PCANet, LDANet, MPCA+LDA, and MLDA in terms of classification for tensor objects.
Fichier principal
OBJECT CLASSIFICATION VIA MULTILINEAR DISCRIMINANT ANALYSIS.pdf (698.11 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)