PCA-based dictionary building for accurate facial expression recognition via sparse representation

• Published in: Journal of visual communication and image representation Vol. 25; no. 5; pp. 1082 - 1092
• Main Authors: Mohammadi, M.R., Fatemizadeh, E., Mahoor, M.H.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.07.2014; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Basic emotions; Classification; Computer science; control theory; systems; Data processing. List processing. Character string processing; Detection, estimation, filtering, equalization, prediction; Dictionaries; Dictionary building; Dictionary learning; Difference image; Exact sciences and technology; Face recognition; Facial; Facial expression recognition; Generalization power; Information, signal and communications theory; Memory organisation. Data processing; Object recognition; Pattern recognition. Digital image processing. Computational geometry; Principal Component Analysis; Representations; Signal and communications theory; Signal, noise; Software; Sparse representation; Telecommunications and information theory; Visual; Facial expression recognition; Dictionary building; Basic emotions; Difference image; Sparse representation; Generalization power; Principal Component Analysis; Dictionary learning; Computer vision; Dictionaries; Expressed emotion; Image recognition; Image processing; Face recognition; Emotion emotionality; Pattern recognition; Object recognition; Modeling; Facies; Facial expression; Principal component analysis; Image classification
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2014.03.006

•We propose a new dictionary building algorithm based on Principal Component Analysis.•The new DB algorithm is used for facial expression recognition.•The PCA-based dictionary is less dependent to identity and more reliable.•The state-of-the-art sparse solvers including BP, MP and SL0 are compared.•The generalization power of the proposed algorithm across datasets is studied. Sparse representation is a new approach that has received significant attention for image classification and recognition. This paper presents a PCA-based dictionary building for sparse representation and classification of universal facial expressions. In our method, expressive facials images of each subject are subtracted from a neutral facial image of the same subject. Then the PCA is applied to these difference images to model the variations within each class of facial expressions. The learned principal components are used as the atoms of the dictionary. In the classification step, a given test image is sparsely represented as a linear combination of the principal components of six basic facial expressions. Our extensive experiments on several publicly available face datasets (CK+, MMI, and Bosphorus datasets) show that our framework outperforms the recognition rate of the state-of-the-art techniques by about 6%. This approach is promising and can further be applied to visual object recognition.