Recognition of Facial Expressions for Images using Neural Network

Abstract

Globally terrorism continues to destroy the lives of people. To identify the terrorist amongst the other people is very difficult rather impossible. This exploratory study aims at investigating the effects of terrorism to recognize emotions. The current paper presents a view-based approach to the representation and recognition of human facial expression. In the designing of facial expression recognition (FER) system, Authors can take advantage of the resources and developed the algorithms for the system. The system divides into 3 modules, i.e. Preprocessing, Feature Extraction and Classification. The basis of the representation is a temporal template where the features are used typically based on local spatial position or displacement of specific points and regions of the face. In this paper, five different facial expressions were considered. Extracting the features, firstly logarithmic Gabor filters were applied. Then the Optimal subsets of features were selected for each expression. The classification tasks were performed using the Neural Network. Secondly, this study indicates that the YALE database contains expressers that expressed expressions.

Feature Extraction for Facial Expression Recognition based on Ensemble Learning Algorithm

“…From the facial expression information, computers can conclude the people's state of mind, so as to realize human-computer intelligent interaction [1]. In recent years, facial expression recognition technology has a variety of applications in many fields such as intelligence robot research, safety tests, computer games, educational experiments and terrorists' identification [2]. It becomes one of the hot research topics in pattern recognition.…”