Forging of age is increasing dramatically these days, especially in areas such as military, industry, crime, processing of visa, job application, etc. One of the areas of human-PC-interaction is developing an application for the automated estimation of age using face pictures. Typically, an age estimation system consists of the extraction and classification of aging features; both of which are important to improve efficiency. For the ageing feature extraction, the hybrid features extraction, which are a mixture of Active Appearance Models (AAM), Local Binary Patterns (LBP) and Gabor filter is applied. As global facial features, the shape of human faces is extracted with AAM. The local facial features are the features of the skin textures extracted with LBP and wrinkle extracted with Gabor filter. An age classification utilizing Support Vector Machine (SVM) classifies age in groups. Eight age group class is used for the age estimation. The result is represented in Cumulative Score. The higher the Cumulative Score (CS) becomes, the age estimate becomes accurate as well. Our system is implemented using Object Oriented Programming (OOP) with the help of Open Computer Vision (OpenCV) library and private dataset from Department of Computer Science, Ignatius Ajuru University of Education (IAUE). The result shows 93% accuracy on age classification and age estimation from facial images which is better than the former method.