In this paper we propose a methodology based on back propagation approach to estimate human age using face features. The recent technology of image processing forms the basic principles of project entitled "A Novel Approach for Face Verification and age estimation using Local Binary Pattern, elastic matching and Back propagation Neural Network' has been developed to overcome the inconveniences faced by the organizations in recognizing the exact person and to estimate the age of a human. In this research is to propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, new method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patch. The proposed method is evaluated by extensive experiments on the FG-NET dataset and MORPH dataset, and compared with two widely used facial expression recognition approaches using Local Binary Pattern. To estimate the age is automatically via facial image analysis has lots of potential real-world applications, such as human computer interaction and multimedia communication.. We found surprisingly that the added difficulty of verification produced by age gaps becomes saturated after the gap is larger than four years, for gaps of up to ten years. The face boundary can be differing from different age groups. Identify the age groups of a human based on the edges and stored in the database. Compare the input image and the existing database image.

Key words: Image processing, LBP pattern, Age estimation, Morph dataset, Discriminative approach, BPN