Studies from Beijing Jiaotong University, Institute of Information Update Current Data on Algorithms

摘要

Investigators publish new data in the report 'Graph-preserving sparse nonnegative matrix factorizationnwith application to facial expression recognition.' "In this paper, a novel graph-preserving sparsennonnegative matrix factorization (GSNMF) algorithm is proposed for facial expression recognition. ThenGSNMF algorithm is derived from the original NMF algorithm by exploiting both sparse andngraph-preserving properties," researchers in Beijing, People's Republic of China report.