Age and Gender Detection System using CNN
Hemleena Barik
Abstract : At the present time, the gender detection systems play a very important role in any person’s day-to-day life. Human gender detection which is a part of facial recognition has received extensive attention because of its different kind of application. because of the growth of online social networking websites and social media. However, the performance of already exist system with the physical world face pictures, images are somewhat not excellent, particularly in comparison with the result of task related to face recognition. Within this paper, I have explored that by doing learn and classification method and with the utilization of Convolution Neural Network. An approach using a convolutional neural network (CNN) is proposed for realtime gender classification based on facial images. The proposed CNN architecture exhibits a much-reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layers in the CNN is reduced to only four by fusing the convolutional and subsampling layers. Unlike in conventional CNNs, I replace the convolution operation with cross-correlation, hence reducing the computational load. The network is trained using a second-order backpropagation learning algorithm with annealed global learning rates. Performance evaluation of the proposed CNN solution is conducted on two publicly available face databases of GitHub. The neural network is able to process and classify a 32 × 32-pixel face image in less than 0.27ms, which corresponds to a very high throughput of over 3700 images per second. Training converges within less than 20 epochs. These results correspond to a superior classification performance, verifying that the proposed CNN is an effective real-time solution for gender recognition.
