Title :
Using moment invariants and HMM in facial expression recognition
Author :
Zhu, Y. ; De Silva, L.c. ; Ko, C.C.
Author_Institution :
Dept. of Electr. Eng., Nat. Univ. of Singapore, Singapore
Abstract :
Moment invariants are invariant under shifting, scaling and rotation. They are widely used in pattern recognition because of their discrimination power and robustness. The HMM method is natural and highly reliable way of recognition. In this paper we propose a method for using moment invariants as features and HMM as the recognition method in facial expression recognition. Sequences of four universal expressions, i.e., anger, disgust, happiness and surprise, are recognised. We attain accuracy as high as 93.75%
Keywords :
face recognition; feature extraction; hidden Markov models; image sequences; HMM; discrimination power; facial expression recognition; features; moment invariants; pattern recognition; robustness; sequences; Communications technology; Face recognition; Facial features; Facial muscles; Hidden Markov models; Image recognition; Image sequences; Pattern recognition; Robustness; Skin;
Conference_Titel :
Image Analysis and Interpretation, 2000. Proceedings. 4th IEEE Southwest Symposium
Conference_Location :
Austin, TX
Print_ISBN :
0-7695-0595-3
DOI :
10.1109/IAI.2000.839621
