Facial Expression Recognition by Supervised Independent Component Analysis Using MAP Estimation

Abstract

Permutation ambiguity of the classical Independent Component Analysis (ICA) may cause problems in feature extraction for pattern classification. Especially when only a small subset of components is derived from data, these components may not be most distinctive for classification, because ICA is an unsupervised method. We include a selective prior for de-mixing coefficients into the classical ICA to alleviate the problem. Since the prior is constructed upon the classification information from the training data, we refer to the proposed ICA model with a selective prior as a supervised ICA (sICA). We formulated the learning rule for sICA by taking a Maximum a Posteriori (MAP) scheme and further derived a fixed point algorithm for learning the de-mixing matrix. We investigate the performance of sICA in facial expression recognition from the aspects of both correct rate of recognition and robustness even with few independent components. key words: facial expression recognition, supervised independent component analysis, fixed-point algorithm Manuscript received

Fusion Based FastICA Method: Facial Expression Recognition

“…Independent Component Analysis (ICA) has the ability to extract local facial features [7], [8]. In recent years ICA has been extensively utilized for FER [7]- [9]. As much of the information that distinguishes different facial expressions stays in the higher order statistics of the images [9], ICA is a better choice for FER than PCA.…”

“…In recent years ICA has been extensively utilized for FER [7]- [9]. As much of the information that distinguishes different facial expressions stays in the higher order statistics of the images [9], ICA is a better choice for FER than PCA. In [10], Bartlett et al implemented ICA to recognize twelve different facial expressions referred to FACS.…”

Facial Expression Recognition Based on WAPA and OEPA Fastica

“…It is also commonly used for dimension reduction. [13] and [14] employed PCA as one of the feature extractors to solve FER with the Facial Action Coding System (FACS). We previously investigated PCA on facial expression recognition [26] and [27].…”

Facial expression recognition using depth information and spatiotemporal features

“…In [5] as well as [6], PCA was used for FER with the Facial Action Coding System (FACS). Very recently, Independent Component Analysis (ICA) has been extensively utilized for FER based on local face image features [5], [10], [11]- [21]. In [14], the authors used ICA to extract local features and then classified several facial expressions.…”