Hybrid Features based Facial Expression Recognition using Convolutional Neural Network and Random Forest Classifier

  • Priyanka Nathawat, Dr. Vivek Chaplot

Abstract

Facial expression is one or more movements or positions of muscles under the skin of the face. These movements convey the emotional state of a person to the viewer. In the field of machine learning, several papers have been developed on facial expression recognition using various feature extraction algorithms (statistical or structural) and classifiers. These works have proven their power in terms of the recognition rate on small databases, all the same, these results remain limited in the context of processing very large amounts of data. With the emergence of the concept of deep learning and large databases, a new line of research is being developed. Our project consists of proposing a facial expression recognition approach based on deep learning and more particularly convolutional neural networks. Throughout this work one of the convolutional neural networks (CNN), Harris corner and Gabor Wavelet are made to extract the features of different images (which reflect the different expressions) and then the consequent integration of the Random Forest Classifier in order to assign a certain probability that this image expresses one emotion or another. Proposed system is evaluated under the MUG database for sequences.

Published
2021-11-23
How to Cite
Priyanka Nathawat, Dr. Vivek Chaplot. (2021). Hybrid Features based Facial Expression Recognition using Convolutional Neural Network and Random Forest Classifier. Design Engineering, 15600-15612. Retrieved from http://www.thedesignengineering.com/index.php/DE/article/view/6695
Section
Articles