Development of an Emotion-Adaptive Web Interface for Enhanced User Experience

Facial expression recognition is one of the machine learning applications. It classifies a facial expression image into one of the facial expression classes based on the characteristics extracted from the image. The Transfer learning model is a pattern recognition system that extracts patterns from photographs. In our proposed study, we employed deep transfer learning to handle the scarcity of available data and designed a Convolutional Neural Network (CNN), MobileNet, AlexNet and GoogleNet models. Where, in the existing methods Machine Learning models are used that which did not got the proper accuracy and that tend to be improved. Hence the present method with other transfer learning methods as well as the wavelet transform, are obtained in order to extract features for data visualization are proposed. The proposed approach was evaluated on publicly available Facial expression dataset.

KEYWORDS: Convolutional Neural Network (CNN), Transfer Learning, Facial Expression Recognition, Wavelet Transform.