Depression is a common mental illness, which is affected by most people of the world. Most of people who are suffering from depression need treatment. By careful examination of Emotions, the early detection of depression is possible. This review presents an in-depth study of the various papers on depression analysis from emotions of facial images of patients. There are various methods used for facial recognition, feature extraction and classification of depression. There are various datasets used AVEC, Clinical Depression dataset from BlackDog Institute and others are used. 5 facial recognition and 5 feature extraction methods are studied. We found that the literature has primarily focused on viola jones method for face detection methods (54%) and deep learning methods for feature extraction (45%). Discussion on limitations of the methods conceived over the past year as well as future perspectives on various methods to improve performance are also provided.

Keywords : Depression Detection, Viola Jones Face Detection, Deep Learning.