Evaluation of Face Recognition Methods in Unconstrained Environments

Face recognition is one of the most challenging applications of image analysis and pattern recognition. Face recognition methods perform well on the images that are collected with careful cooperation of the subjects. Whereas, the challenges of change in illumination, expression, pose make this problem harder. Age changes the facial texture and shape while occluded images left partial facial features for processing, thus making the problem of face recognition much harder. This paper presents an overview and a general classification of face recognition methods along with their pros and cons. We present a comparison across different methods and conclude by discussing possible future directions.