Age and gender recognition with random occluded data augmentation on facial images

In this article, we propose the Random Occlusion, a data augmentation method on facial images using simple image processing techniques for age and gender recognition. Previous methods achieved promising results on constrained datasets with strict environmental settings, but the results on unconstrained datasets are still far from perfect. This article proposed a data augmentation method by altering the training images that resemble real-life photos to improve the performance of the networks by providing more varieties to the training samples. The proposed method adopted three simple occlusion techniques, Blackout, Random Brightness, and Blur, and each simulates a different kind of challenge that would be encountered in real-world applications. We verify the effectiveness of the proposed method by implementing the augmentation method on two convolution neural networks (CNNs), the modified AdienceNet and VGG16 to perform age and gender classification. The proposed augmentation method improves the age accuracy results of the modified AdienceNet and VGG16 by 1.0% and 0.8%, respectively; and gender accuracy results of the AdienceNet and VGG16 by 1.5% and 1.2%, respectively.