Occlusion Verification in Face Detection and Age Estimation Using Local Binary Pattern and Dtod Classifier Using Morph Dataset

The purpose of this research work is focused on occlusion conditions in the face like wearing sunglasses and scarf in the eyes and mouth positions of the facial image. The proposed work has three stages. The first stage was based on Decision Tree Induction C5.0 algorithm to classify the occluded part and non occluded part in the facial image. The Second stage was face verification using Local Binary Pattern method. The third stage carried out the estimation of human age using Back Propagation Neural Network. The results of the proposed work having high accuracy of identification of face using decision tree and local binary pattern method using non occluded part of the facial image as the feature. Also the age can be identified using Back Propagation Neural Network algorithm using winkles as a feature and the gender can be classified using the Posteriori and Priori probability values. Compared to the existing work the occluded part was efficiently classified using Decision Tree method and the age can be classified into minimum age intervals like 0-2, 3-5, 69 instead of 0-9 in the existing work.