Finding faces for Gender classification using BPNN AND PCA based recognition

Abstract

Face Classification system is a computer program which will classify a face into different categories as per certain criterias. We will be training our systems to classify the images into two septum. The first would classify the images based on human or non--human characteristics. The second category of classification would be classifying the human faces as male or female face. We will implement this using Back Propagation Neural Network algorithm. This pre-classification will help in reducing the total time required to recognize an image and hence increasing the overall speed.
Face Recognition system is a computer applicaton that identifies a face of a person in a digital image by comparing the face in the image with the facial database of some trained images. This system can recognize images of a person with emotions and expressions different with those in the facial database. We will implement this using a mathematical tool called Principal Component Analysis and Mahalanobis Distance Algorithm. It can be used for security purposes at restricted places by granting access to only authorised persons. It can also be used for criminal identification.