With the advances in the computer vision in the past few years, analysis of human facial expressions has gained attention. Facial expression analysis is now an active field of research for over two decades now. However, still there are a lot of questions unanswered. This project will explore and devise algorithms and techniques for facial expression analysis in practical environments. Methods will also be developed for inferring the emotion of a group of people. The central hypothesis of the project is that close to real-world data can be extracted from movies and facial expression analysis on movies is a stepping stone for moving to analysis in the real-world. The data extracted from movies carries with it rich meta-data information which will be useful for exploring the role of context in emotion recognition in the wild. For the analysis of groups of people various attributes effect the perception of mood. Study will be conducted and thorough literature survey will be performed on what are these contextual attributes. A system which can classify the mood of a group of people in videos will be developed and will be used to solve the problem of efficient image browsing and retrieval based on emotion.