Development of a facial emotion recognition Android application for autistic patients

Abstract

Children diagnosed with an autism spectrum disorder, Asperger’s Syndrome, often have difficulties to read or understand other people’s emotions. Consequently, such children need to be taught explicitly how to read other people’s minds from nonverbal communication channels such as the facial expressions. In order to recognize the image including several objects, meaningful image regions (facial parts showing the signs of emotions) should be segmented, extracted and recognized separately for reducing the complexity of the problem. The recognition procedure consists of coarse region segmentation/extraction, to extract out various emotional features of the face. Then the extracted images have to be transformed into a format which can be compared with a set of already known emotion list in the memory. A dynamic-link matching is done to recognize the emotion of the face.

The objective of this project is to design and implement a high speed portable facial emotional recognition system on Android.