Identifying the Age Using Face Image Using DWT, LBP, SVM and k-NN

Abstract

                                             ABSTRACT

The research related to identifying the age using face images has become progressively more important, due to the fact it has a multiplicity of potentially helpful applications. In this paper we survey the complete age synthesis or age estimation from face images techniques. Automatic facial age identifying is one of the main issues in pattern recognition which shows the age of human according to her/his facial expressions. Basically, age detection/estimation is a process of identifying the actual (or approximate) age of human. An identifying the age system is usually composed of aging feature extraction and feature classification; both of which are important in order to get better the performance. Facial features are measured one of the important personal behavior. This can be used in numerous applications, like face recognition and age estimation. The importance of these applications lies in numerous areas, like defense applications, law enforcement applications, and attendance systems. Identifying the age is classification of a face image with exact actual age or age group. In this paper, we are going to plan a system to identify the age using face images which is based on Discrete Wavelet Transform (DWT) and Local Binary Pattern (LBP) for feature extraction and Support Vector Machine (SVM) and k-NN (k-nearest neighbor) for classifier. Our planned approach has been developed, tested and trained using the database FG-NET.

Keywords: DWT, LBP, SVM, k-NN, Feature extraction, Classification