FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method

A light-weight low-resolution face gender classification method, called FaceHop, is proposed in this research. We have witnessed rapid progress accuracy due to the adoption of deep learning (DL) technology. Yet, DL-based systems are not suitable for resource-constrained environments with limited networking and computing. FaceHop offers an interpretable non-parametric machine solution. It has desired characteristics such as a small model size, training data amount, low complexity, input images. developed successive subspace (SSL) principle built upon foundation PixelHop++. The effectiveness method demonstrated by experiments. For gray-scale images resolution \(32 \times 32\) LFW CMU Multi-PIE datasets, achieves correct rates 94.63% 95.12% sizes 16.9K 17.6K parameters, respectively. outperforms LeNet-5 while size 75.8K parameters.