A New Approach for Gender Classification

Gender of the person can affect the human behavior and social interactions greatly. In this paper, we present a novel texture descriptor Local Directional Pattern (LDP) to represent facial image for gender classification. The proposed method operates on a neighborhood of a pixel and forms a feature vector. All the extracted feature vectors are copied into a matrix which represents the coded image. The experimental results are carried on Google Images and can also be applied on FERET and FG-NET face database. Experimental results show that the proposed method on the images collected from Google Images achieved around 95% accuracy.