Mood detection system via using various dimension reduction techniques

Natural facial expressions commonly occur in social interactions between people, and are useful for providing an emotional context for the interaction , and for communicating social intentions. This project depicts an idea regarding detecting an unknown human face from input imagery and recognize his/her current mood. The objective of this research work is that psychological state giving information about some disorders helpful with diagnosis of depression , mania or schizophrenia. The elimination of errors due to reflections in the image has not been implemented but the algorithms used in this project are computationally efficient to resolve errors. Endeavours are also put in this project to enhance the recognition rate of mood detection by adopting unique methodology.In this research work we have accepted seven different moods to be recognized are: Joy, Fear, Contempt, Sad, Disgust, Angry and Astonished. Principal Component Analysis (PCA) is implemented with Fisher face Algorithm to recognize different moods. The main part of this project is to recognize emotional facial moods given in one of the database data with high accuracy.