Gender classification

Abstract

Gender recognition has been playing a very important role in various applications such as human computer interaction, surveillance and security. In this context, this project aims to investigate a gender classification system and propose new models for a better performance. We have evaluated different learning algorithm; the SVM – RBF with a 5% outlier fraction outperformed other classifiers. We have examined the effectiveness of different feature selection methods. We have proposed two classification methods that focus on training subsets of images among the training images. Method 1 combines the outcome of different classifiers based on different image subsets, while method 2 is based on clustering the training data and building a classifier for each cluster. Experimental results showed that both methods might increase the classification accuracy. The first method performed better than the second one. In addition, results have shown that method 1 can reach 100% accuracy.