Abstract:
Detecting and recognizing human emotions through technology is a very active research
nowadays, in the fields of Computer Vision and Human-Computer Interaction. There are
many modern techniques through which this procedure is implemented. Some famous
techniques are Digital Image Processing, Template Matching, Machine Learning (which
further includes Neural Network and Support Vector Machines). If computers
successfully understand human emotion,
can can make systems which can reduce the gap
of Human Computer Interaction. In this project we have worked on some different color
we
models which segment and separate features of the face. The features we need to identify
are the eyes and mouth/lips region. Once the features are recognized using the color
models, these features need to be extracted. For that purpose, we have used SVM (Support
Vector Machine) with LDA (Linear Discriminant Analysis) technique to detect the eye and
lips region from the human face image and then with the help of a pre-trained SVM model
we have detected the emotion from those facial features. This research project also includes
an effective way to detect 6 different emotions, namely Happiness, Sadness, Anger,
Disgust, Surprise and Fear, using the frontal face image of a human begin as input.
