NEURAL NETWORK BASED IDENTIFICATION OF AN EMOTION USING ICA OF HAND GESTURES OF A HUMAN BEING

Abstract

This paper presents the identification of an emotion of a human being expressed by various Hand Gestures
with respect to that emotion. A complete database of the images of various hand gestures of an individual’s are stored in
the system then, with the use of Mathematical Imaging, step by step process is performed on it. It includes, Image
Normalization, Features Extraction by Independent Component Analysis (ICA) and finally the Classification of hand
Gesture over basic seven emotions Neutral, Happy, Sad, Fear, Anger, Surprise, and Disgust by Neural Network (NN)
using Multi-Layer Feed Forward approach with Backpropagation Algorithm.