Facial Emotion Recognition of Human Facial Expression Classification

Image Processing

Facial expression recognition has various prospective applications which have attracted the concentration of researchers in the last decade. Feature extraction is one of the most important steps in expression recognition which contributes toward fast and accurate expression recognition. Happy, surprise, normal, sad, anger facial expressions are of facial recognition. Facial expressions are most generally used for interpretation of human emotion. There is a range of different emotions in two categories: positive emotion and non-positive emotion. There are four types of generally using system: Facial detection, Facial extraction, Facial Classification and Facial recognition. Many methods have been used in the past to classify emotional facial expressions, such as Artificial Neural Networks, Bayesian Networks, Support Vector machines etc. In Existing system, facial features were extracted using higher order Zernike moments and the features were classified by an ANN based classifier. The facial expressions were classified into groups that represented either positive or non-positive emotion. The images in training section were not repeated in the testing section. It is not so much required to know the exact emotion of a person but a general explanation of the state of mind of the person is sufficient. In our proposed system, we will use PCA and geometric method for facial feature extraction and ANN classification. We will try to improve accuracy of facial expression.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.