Few-Shot learning for face recognition in the presence of image discrepancies for limited multi-class datasets

作者：

Highlights：

• Implementation of the Few-Shot Learning approach to develop face recognition system for very few images for a specific class (person).

• Proposed method to images discrepancies such as different orientation, low lighting, and occlusion (due to mask) for limited datasets.

• Design of an end-to-end cascaded model for detection of any class in a testing image with any orientation, lighting condition, and occlusion

摘要

•Implementation of the Few-Shot Learning approach to develop face recognition system for very few images for a specific class (person).•Proposed method to images discrepancies such as different orientation, low lighting, and occlusion (due to mask) for limited datasets.•Design of an end-to-end cascaded model for detection of any class in a testing image with any orientation, lighting condition, and occlusion

论文关键词：Few-Shot learning,Face recognition,Occlusion,Low light,Orientation,Siamese networks

论文评审过程：Received 8 October 2021, Revised 11 January 2022, Accepted 16 February 2022, Available online 19 February 2022, Version of Record 26 February 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104420