2021/05/18 by А. Н. Жучков, Zhuchkov, Aleksei
Computer Science · #Face and Expression Recognition #Face recognition and analysis #Advanced Image and Video Retrieval Techniques
paper · pdf · doi:10.48550/arxiv.2105.08796
This work presents an analysis of the efficiency of image augmentations for\nthe face recognition problem from limited data. We considered basic\nmanipulations, generative methods, and their combinations for augmentations.\nOur results show that augmentations, in general, can considerably improve the\nquality of face recognition systems and the combination of generative and basic\napproaches performs better than the other tested techniques.\n