Investigating Nuisances in DCNN-Based Face Recognition

Face recognition "in the wild" has been revolutionized by the deployment of deep learning-based approaches. In fact, it has been extensively demonstrated that deep convolutional neural networks (DCNNs) are powerful enough to overcome most of the limits that affected face recognition algorithms based on hand-crafted features. These include variations in illumination, pose, expression, and occlusion, to mention some. The DCNNs discriminative power comes from the fact that low- and high-level representations are learned directly from the raw image data. As a consequence, we expect the performance of a DCNN to be influenced by the characteristics of the image/video data that are fed to the network, and their preprocessing. In this paper, we present a thorough analysis of several aspects that impact on the use of DCNN for face recognition. The evaluation has been carried out from two main perspectives: the network architecture and the similarity measures used to compare deeply learned features; and the data (source and quality) and their pre-processing (bounding box and alignment). The results obtained on the IARPA Janus Benchmark-A, MegaFace, UMDFaces, and YouTube Faces data sets indicate viable hints for designing, training, and testing DCNNs. Considering the outcomes of the experimental evaluation, we show how competitive performance with respect to the state of the art can be reached even with standard DCNN architectures and pipeline.