Abstract In this paper, a dimensionality reduction method applied on facial expression recognition is investigated. An unsupervised learning framework, projective complex matrix factorization (proCMF), is introduced to project high-dimensional input facial images into a lower dimension subspace. The proCMF model is related to both the conventional projective nonnegative matrix factorization (proNMF) and the cosine dissimilarity metric in the simple manner by transforming real data into the complex domain. A projective matrix is then found through solving an unconstraint complex optimization problem. The gradient descent method was utilized to optimize a complex cost function. Extensive experiments carried on the extended Cohn-Kanade and the JAFFE databases show that the proposed proCMF model provides even better performance than state-of-the-art methods for facial expression recognition.

+More

dimensionality reduction method unconstraint complex optimization problem complex cost stateoftheart methods facial expression recognition unsupervised learning framework projective complex matrix factorization procmf gradient descent method extended cohnkanade and the jaffe databases procmf model cosine dissimilarity metric

Viet-Hang Duong,Yuan-Shan Lee,Jian-Jiun Ding,Bach-Tung Pham,Manh-Quan Bui,Pham The Bao,Jia-Ching Wang,.Projective complex matrix factorization for facial expression recognition. 2018 (1),.

Viet-Hang Duong,Yuan-Shan Lee,Jian-Jiun Ding,Bach-Tung Pham,Manh-Quan Bui,Pham The Bao,Jia-Ching Wang,"Projective complex matrix factorization for facial expression recognition" 2018

Viet-Hang Duong,Yuan-Shan Lee,Jian-Jiun Ding,Bach-Tung Pham,Manh-Quan Bui,Pham The Bao,Jia-Ching Wang,"Projective complex matrix factorization for facial expression recognition"