Automatic Emotion Recognition through Facial Expression Analysis in Merged Images Based on an Artificial Neural Network

摘要: This paper focuses on a system of recognizing human's emotion from detected face. The analyzed information is conveyed by the regions eye and mouth into merged new image in various facial expressions pertaining to six universal basic emotions. output obtained could be fed as an input machine capable interact with social skills, context building socially intelligent systems. methodology uses classification technique fused which composed two blocks integrated area eyes mouth, very sensitive areas changes expression that are particularly relevant for decoding emotional expressions. Finally we use feed-forward neural network trained back-propagation. Such analysis images makes it possible, obtain through combination proper data same reduce training set time while preserved rate. It shown experimental results proposed algorithm can detect good accuracy.