Missing Person Identification

Abstract

At present the Computer automated Face recognition systems are used for personal identification, but the Age variations of an individual poses a serious problem for it. Designing an appropriate feature representation and an effective matching framework for age invariant face recognition remains an open problem. To classify person age using faces author using combination of two CNN where one CNN will extract face features which can help in identify changes in face over time and second CNN helps in predicting/ classifying age. Face aging causes intra-subject variations (such as geometric changes during childhood & adolescence, wrinkles and saggy skin in old age) which negatively affects the accuracy of face recognition systems. Therefore, this paper proposes a unified, multi-task framework to jointly handle these two tasks, termed MTLFace, which can learn age-invariant identity-related representation while achieving pleasing face synthesis. Specifically, we first decompose the mixed face features into two uncorrelated components—identity- and age-related features—through an attention mechanism, and then decorrelate these two components using multi-task training and continuous domain adaption. d. This system will decrease the crimes and ensure the security in our society.