TY  - JOUR
T1  - Partition Based Feature Extraction Technique for Facial Expression
Recognition Using Multi-Stage Hidden Markov Model
AU - Rahul, Mayur AU - Kohli, Narendra AU - Agrawal, Rashi 
JO  - Journal of Engineering and Applied Sciences
VL  - 13
IS  - 9
SP  - 2651
EP  - 2658
PY  - 2018
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2018.2651.2658
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2018.2651.2658
KW  - JAFFE
KW  -Gabor wavelets transform
KW  -PCA
KW  -local binary patterns
KW  -SVM
KW  -FAPs
KW  -Cohn-Kanade database
KW  -Markov process
KW  -static modelling
AB  - Partition based feature extraction is widely used in the pattern recognition and computer vision. This
method is robust to some changes like occlusion, background, etc. In this study, partition based technique is
used for feature extraction and extension of HMM is used as a classifier. The new introduced multi-stage HMM
consists of two layers. In which bottom layer represents the atomic expression made by eyes, nose and lips.
Further upper layer represents the combination of these atomic expressions such as smile, fear, etc. Six basic
facial expressions are recognised, i.e., anger, disgust, fear, joy, sadness and surprise. Our proposed system is
able to get overall accuracy of 82% using JAFFE database.
ER  -