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

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

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

Jia-Ching Wang, et al."Projective complex matrix factorization for facial expression recognition" 2018

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