A New Approach of Facial Expression Recognition for Ambient Assisted Living

Abstract

Ambient Assisted Living and Ambient Intelligence have seen their impact greatly grows, especially these last decades. It is mainly due to the increase of the ageing population and people with cognitive diseases. Several technologies were developed to make the use of assistive technology more acceptable and comfortable for the elderly in order to reduce or even replace the human assistance. However, there are many challenges and issues, especially in the interaction between the elderly and assistive systems. To make the system interact as human beings, emotions were used. In this paper, we present a new approach to recognize emotions based on facial expressions represented by images. It is based on a new method for feature selection based on distances. We also suggest the use of the well-known K-Nearest Neighbor classifier with optimized parameters. This approach is found effective when tested using two different datasets of images.