Facial expression recognition using intelligent optical neural networks

摘要

The goal of this paper is automating facial expression analysis in facial images and image sequences using intelligent optical neural networks. Humans detect and interpret faces and facial expressions in a scene with little or no effort. Still, development of an automated system that accomplishes this task is rather difficult. A system that performs these operations accurately and in real time would form a big step in achieving a human-like interaction between man and machine. Automating facial expression analysis could bring facial expressions into man-machine interaction as a new modality and make the interaction tighter and more efficient. This paper proposes an optical neural network in detection of the facial expressions in images by extracting the gabor texture features. The Karhunen-Loeve Transform identifies the facial expression of the detected face. Results are analysed using the Cohn-Kanade facial expression database and the classification rate is proved higher compared to the approaches found in the literature.