Automatic emotion identification is a critical part of human-machine interactions. Reflection of emotion and to develop its understanding is crucial for providing dealings between human and machine frameworks. This paper proposes an automatic system that distinguishes different emotions connected to the face. Extensive studies are carried out to explore the dealings between human sentiments and machine interactions. Thus, a robust feature extraction and optimization based emotion recognition are carried out with a high accuracy rate and fewer error probabilities. Gradient filtering and component analysis are used to extract a feature vector, and feature optimization is done using particle swarm optimization (PSO) technique. Finally, the testing process is obtained for the classification of emotions, and then performance is measured in terms of false acceptance rate, false rejection rate, and accuracy. The experimental results prove the better performance of the proposed system on different emotions present in the benchmark Japanese dataset.
Volume 11 | Issue 5
Pages: 7-14