Facial Expression Recognition using Support Vector Machine (SVM) and Convolutional Neural Network (CNN)

Abstract

Facial expression is an important mode of non-verbal conversation among people. It is really a speedy growing and an evergreen research field in the region of computer vision, artificial intelligence and automation. Facial expressions can be recognized by training images. There are some limitations such as noise in the presently available emotion recognition techniques. This paper proposes a facial expression recognition method based on Support Vector Machine (SVM). It also adopts Convolutional Neural Network (CNN) for image training. SVM follows a technique called kernel trick to transform the data. SVM performs better than other existing techniques, and there by improves the overall performance of facial expression recognition.