Humans can accurately interpret and analyze an expressed emotion, which is a hindrance for any machine or computer. This project, under the Machine Vision, aims at designing a system that detects and successfully recognizes human emotions without any human intervention. It makes use of Eigenfaces to quantify the test and training image database into appropriate vectors. It uses principal component analysis of the images of the faces reducing the dimensionality of the training set, converting only those features that are critical for face recognition into Eigen vectors.