Welcome to the InfoSci Platform
Reference Hub1
An Efficient and Robust Technique for Facial Expression Recognition Using Modified Hidden Markov Model

An Efficient and Robust Technique for Facial Expression Recognition Using Modified Hidden Markov Model

Mayur Rahul, Pushpa Mamoria, Narendra Kohli, Rashi Agrawal
Copyright: © 2018 |Volume: 9 |Issue: 3 |Pages: 11
ISSN: 1942-3594|EISSN: 1942-3608|EISBN13: 9781522544166|DOI: 10.4018/IJAEC.2018070102
Cite Article Cite Article

MLA

Rahul, Mayur, et al. "An Efficient and Robust Technique for Facial Expression Recognition Using Modified Hidden Markov Model." IJAEC vol.9, no.3 2018: pp.12-22. http://doi.org/10.4018/IJAEC.2018070102

APA

Rahul, M., Mamoria, P., Kohli, N., & Agrawal, R. (2018). An Efficient and Robust Technique for Facial Expression Recognition Using Modified Hidden Markov Model. International Journal of Applied Evolutionary Computation (IJAEC), 9(3), 12-22. http://doi.org/10.4018/IJAEC.2018070102

Chicago

Rahul, Mayur, et al. "An Efficient and Robust Technique for Facial Expression Recognition Using Modified Hidden Markov Model," International Journal of Applied Evolutionary Computation (IJAEC) 9, no.3: 12-22. http://doi.org/10.4018/IJAEC.2018070102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

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 article, a 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, the upper layer represents the combination of these atomic expressions such as smile, fear, etc. Six basic facial expressions are recognized, i.e. anger, disgust, fear, joy, sadness and surprise. Experimental results show that the proposed system performs better than normal HMM and has an overall accuracy of 85% using the JAFFE database.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.