Image-Based Face Detection and Recognition

Abstract

Face recognition from image or video is a popular topic in biometrics research. Many public places\nusually have surveillance cameras for video capture and these cameras have their significant value for\nsecurity purpose. It is widely acknowledgedthatthefacerecognitionhaveplayedanimportant role in\nsurveillance system as it doesn’t need the object’s cooperation. The actual advantages of face based\nidentification over other biometrics are uniqueness and acceptance. As human face is a dynamic object\nhaving high degree of variability in its appearance, that makes face detection a difficult problem in\ncomputer vision. In this field, accuracy and speed of identification is a mainissue.\nThe goal of this paper is to evaluate various face detection and recognition methods, provide complete\nsolution for image based face detection and recognition with higher accuracy, better response rate as\nan initial step for video surveillance. Solution is proposed based on performed tests on various face rich\ndatabases in terms of subjects, pose, emotions, race andlight.