A Fuzzy Expert System for Facial Expression Recognition


  • Masoumeh Rezaei
  • Mansoureh Rezaei


Nonnegative Matrix Factorization, Fuzzy Expert System, SGERD algorithm


This paper presents a method for facial expression recognition using fuzzy expert system. The proposed expert system consists of two main steps: First, the pre-processing part, the feature extraction step provides sufficient information for the inference engine. For this reason, NMF is used to preserve the representation of the original image. Additionally, it guarantees that both of the resulting low-dimensional basis and its accompanying weights are non-negative. Second, it allows for creating rules with the SGERD algorithm and inferencing them. The second step applies a suitable set of fuzzy rules and aggregates them towards the final decision. We applied our approach to the Japanese Female Facial Expression dataset for recognizing the facial expression states. Experimental results demonstrate superiority of the proposed approach to the compared methods in terms of classification rate


How to Cite

Rezaei, M., & Rezaei, M. (2015). A Fuzzy Expert System for Facial Expression Recognition. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 7(1), 37–41. Retrieved from https://jtec.utem.edu.my/jtec/article/view/492