Transfer Learning in 2.5D Face Image for Occlusion Presence and Gender Classification
Sahil Sharma, Vijay Kumar · Advances in computational intelligence and robotics book series · 2019
Face depth image has been used for occlusion presence and gender prediction by transfer learning. This chapter discusses about the overfitting problem and how augmentation helps overcoming it. Pre-processing of the dataset includes converting a 3D object image into depth image for further processing. Five state-of-the-art 2D deep learning models (e.g., AlexNet, VGG16, DenseNet121, ResNet18, and SqueezeNet) have been discussed along with their architecture. The effect of increasing the number of epochs on the top-1 error rate has been presented in the experimental section. The result section consists of error rates in comparison of with and without augmentation on the datasets.