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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Fan CHEN, Kazunori KOTANI, "Facial Expression Recognition by Supervised Independent Component Analysis Using MAP Estimation" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 2, pp. 341-350, February 2008, doi: 10.1093/ietisy/e91-d.2.341.
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.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.2.341/_p
Copy
@ARTICLE{e91-d_2_341,
author={Fan CHEN, Kazunori KOTANI, },
journal={IEICE TRANSACTIONS on Information},
title={Facial Expression Recognition by Supervised Independent Component Analysis Using MAP Estimation},
year={2008},
volume={E91-D},
number={2},
pages={341-350},
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.},
keywords={},
doi={10.1093/ietisy/e91-d.2.341},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Facial Expression Recognition by Supervised Independent Component Analysis Using MAP Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 341
EP - 350
AU - Fan CHEN
AU - Kazunori KOTANI
PY - 2008
DO - 10.1093/ietisy/e91-d.2.341
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2008
AB - 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.
ER -