Layered Recognition Scheme for Robust Human Facial Expression Recognition using modified Hidden Markov Model
Mayur Rahul, Rashi Agrawal, Narendra Kohli UIET, CSJMU, Kanpur, India & HBTU, Kanpur, India
Abstract: Facial Expression Recognition is an application used for biometric software that can be used to recognize special expressions in a digital image by analysing and comparing different patterns. These software are popularly used for
the purpose of security and are commonly used in other applications such as credit card verification, surveillance systems,
medicines, home security, human-computer interface, etc.. Recognizing faces becomes very difficult when there is a frequent
change occurs in facial expressions. In this paper two layer extension of HMM is used to identify continuous effective facial
expressions. Partition technique is used for feature extraction. Two layered extension of HMM consists of bottom layer which
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. In HMM, Baum-Welch, Viterbi and Forward methods are used for parameter estimation for
calculating the optimal state sequence and probability of the observed sequence respectively. This proposed system consists
of three level of classification. Output of the first level is used for the training purposes for the second level and further this
level is used for the third level for testing. Six basic facial expressions are recognised i.e. anger, disgust, fear, joy, sadness and
surprise. Experimental result shows that Proposed System performs better than normal HMM and has the overall accuracy of
85% using JAFFE database.
Keywords: JAFFE, Gabor Wavelets Transform, PCA, Local Binary Patterns, Svm, Faps, Cohn-kanade Database, Markov Process, Static Modelling Layered Recognition Scheme for Robust Human Facial Expression Recognition using modified Hidden Markov Model
References:[1] Katagiri, Shigeru., Lee, Chin-Hui . (1993). A new hybrid algorithm for speech recognition based on HMM segmentation and
learning vector quantization. Speech and Audio Processing, IEEE Transactions on Volume 1(4) October. 1993 421 - 430
[2] Tsapatsoulis, N., Leonidou, M., Kollias, S. Facial expression recognition using HMM with observation dependent transition
matrix, Multimedia Signal Processing, 1998 IEEE Second Workshop on 7-9 Dec. 1998. p. 89-95
[3] Lawrance R Rabiner. A tutorial on hidden Markov models and selected applications in speech recognition, Proceedings of
the IEEE, 1 989, 77 (2) 257—286.
[4] Atlas, L., Ostendorf, M., Bernard, G. D. (2000). Hidden Markov Models for Monitoring ,Machining Tool-Wear, In: IEEE
International Conference on Acoustics, Speech, and Signal Processing, 6: 3887—3890
[5] Hatzipantelis, E., Murray, A., Penman, J. (1995). Comparing hidden Markov models with artificial neural network architectures
for condition monitoring applications, Fourth International Conference on Artificial Neural Networks, 6. 369—374.
[6] Highfield, R., Wiseman, R., Jenkins, R. (2009). How your looks betray your personality, New Scientist, February.
[7] http://www.library.northwestern.edu/spec/hogarth/physiognomics1.html
[8] Darwin, C., Darwin, F. (1904). The Expression of the Emotions in Man and Animals, 2nd edition, J. Murray, London, .
[9] Ekman, P., Friesen, W. (1978). Facial Action Coding System: A Technique for the Measurement of Facial Movement. Consulting
Psychologists Press, Palo Alto, 1978.
[10] Cohen, I., Sebe, N., Chen, L., Garg, A., Huang, T. S. (2003). Facial expression recognition from video sequences: Temporal
and static modelling. In: Computer Vision and Image Understanding, p 160–187.
[11] Lien, J. J.-J., Kanade, T., Cohn, J. F., Li, C.-C. (200). Detection, tracking, and classification of action units in facial expression.
Robotics and Autonomous Systems, 31(3) 131–146.
[12] Parda, M., Bonafonte, A. (2002). Facial animation parameters extraction and expression recognition using Hidden Markov
Models, Signal Processing: Image Communication,vol. 17, p.675–688.
[13] Aleksic, P. S., Katsaggelos, A. K. (2006). Automatic Facial Expression Recognition Using Facial Animation Parameters and
MultiStream HMMs, IEEE Trans. Information Forensics and Security, 1(1) 3-11.
[14] Shang, L., Chan, K. P. (2009). Nonparametric discriminant HMM and application to facial expression recognition, In: IEEE
conference on CVPR.
[15] Jiang, (2011). A facial expression recognition model based on HMM, In: International Conference on Electronic and
Mechanical Engineering and Information Technology.
[16] Suk, M., Prabhakran, B. (2015). Real-time facial expression recognition on smartphones, In: IEEE Winter Conference on
Applications of Computer Vision.
[17] Wu, C., Wang, S., Ji, Q. (2015). Multi-instance Hidden markov models for facial expression recognition.
[18] Sikka, K., Dhall, A., Bartlett, M. (2015). Exemplar HMM for classification of facial expressions in video, In: IEEE conference
on CVPRW.
[19] Ramkumar, G., Lagashanmugam, E. (2016). An effectual facial expression recognition using HMM, ICACCCT.
[20] Vijailakshmi, M., Senthil, T. (2014). Autmatic human facial expression recognition using HMM,IEEE 2014
[21] Jiang, Xuefang. (2011). A facial expression recognition model based on HMM, IEEE.
[22] Xiorong, Pu., Zhiku, Zhou., Heng, Tan. (2014). Partially occluded face recognition using subspace HMM, IEEE.
[23] Punith, A., Geetha, Kalaselvi. (2013). HMM based peak time facial expression recognition IJETAE, V 3 January.
[24] Rani, R., Pagaria, Mahip, M., Bartere. Facial emotion recognition in video using HMM, IJCER, 3(4).
[25] Islam, M. R., Toufiq, R., Rahman, M. F. (2014). Appearance and shape based facial system using PCA and HMM, IEEE.
[26] Singh, K. R., Zaveri, M. A., Raghuwanshi, M. M. (2014). Recognizing face under varying poses with three states HMM,
IEEE.