Face recognition in low-quality images using adaptive sparse representations

作者：

Highlights：

• New method based on sparse representations for face recognition in low-quality images.

• Release of AR-LQ, a dataset with blurred images (AR-blur) and low-resolution images (AR-LR) acquired using a realistic method with a DLSR camera.

• Experiments on blurred images.

• Experiments on low-resolution images.

• Discussion of the results in greater detail.

摘要

•New method based on sparse representations for face recognition in low-quality images.•Release of AR-LQ, a dataset with blurred images (AR-blur) and low-resolution images (AR-LR) acquired using a realistic method with a DLSR camera.•Experiments on blurred images.•Experiments on low-resolution images.•Discussion of the results in greater detail.

论文关键词：Face recognition,Sparse representations,Deep learning,Superresolution,Low-quality images,Low-resolution

论文评审过程：Received 3 November 2017, Revised 20 October 2018, Accepted 27 February 2019, Available online 4 April 2019, Version of Record 15 April 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.02.012