Automatic Facial Expression Recognition System Using Shape-Information-Matrix (SIM): An Expression Specific Approach

Automatic Facial Expression Recognition System Using Shape-Information-Matrix (SIM): An Expression Specific Approach

Avishek Nandi, Paramartha Dutta, Md Nasir
Copyright: © 2020 |Volume: 9 |Issue: 4 |Pages: 18
ISSN: 1947-928X|EISSN: 1947-9298|EISBN13: 9781799806684|DOI: 10.4018/IJNCR.2020100103
Cite Article Cite Article

MLA

Nandi, Avishek, et al. "Automatic Facial Expression Recognition System Using Shape-Information-Matrix (SIM): An Expression Specific Approach." IJNCR vol.9, no.4 2020: pp.34-51. http://doi.org/10.4018/IJNCR.2020100103

APA

Nandi, A., Dutta, P., & Nasir, M. (2020). Automatic Facial Expression Recognition System Using Shape-Information-Matrix (SIM): An Expression Specific Approach. International Journal of Natural Computing Research (IJNCR), 9(4), 34-51. http://doi.org/10.4018/IJNCR.2020100103

Chicago

Nandi, Avishek, Paramartha Dutta, and Md Nasir. "Automatic Facial Expression Recognition System Using Shape-Information-Matrix (SIM): An Expression Specific Approach," International Journal of Natural Computing Research (IJNCR) 9, no.4: 34-51. http://doi.org/10.4018/IJNCR.2020100103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Automatic recognition of facial expressions and modeling of human expressions are very essential in the field of affective computing. The authors have introduced a novel geometric and texture-based method to extract the shapio-geometric features from an image computed by landmarking the geometric locations of facial components using the active appearance model (AAM). Expression-specific analysis of facial landmark points is carried out to select a set of landmark points for each expression to identify features for each specific expression. The shape information matrix (SIM) is constructed the set salient landmark points assign to an expression. Finally, the histogram-oriented gradients (HoG) of SIM are computed which is used for classification with multi-layer perceptron (MLP). The proposed method is tested and validated on four well-known benchmark databases, which are CK+, JAFFE, MMI, and MUG. The proposed system achieved 98.5%, 97.6%, 96.4%, and 97.0% accuracy in CK+, JAFFE, MMI, and MUG database, respectively.

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.