This paper introduces the framework based on the extraction of features using Gabor filters and modified hidden Markov model for classification. The three regions of interest (nose, mouth and eyes) are extracted using Gabor filters and dimensions are reduced by independent component analysis. Then these reduced dimensions are input to our two-layered HMM for training and testing. Seven facial expressions are recognized using publicly available JAFFE dataset. Experimental data shows the efficient and robust nature of our framework and shows its uniqueness on comparing it with other existing available methods.
CITATION STYLE
Rahul, M., Shukla, R., Goyal, P. K., Siddiqui, Z. A., & Yadav, V. (2021). Gabor filter and ica-based facial expression recognition using two-layered hidden markov model. In Advances in Intelligent Systems and Computing (Vol. 1086, pp. 511–518). Springer. https://doi.org/10.1007/978-981-15-1275-9_42
Mendeley helps you to discover research relevant for your work.