A person�s face provides a lot of information such as age, gender and identity. Faces play an important role in the prediction of gender. In this research, an attempt is made to classify human gender using two level decision based on Neural Networks. In this paper a feed forward propagation neural networks are constructed for human gender classification system for male and female. The performance of the system is further improved by employing second level decision using three sigma control limits applied on the output of the neural network classifier. The efficiency of the system is demonstrated through the experimental results using benchmark database images.