Super-resolution for biometrics: A comprehensive survey

作者：

Highlights：

• Discuss the significance of super-resolution in the context of biometrics and how it is different from the general super-resolution.

• Present a background knowledge in general super-resolution approaches.

• Provide a comprehensive review of existing super-resolution approaches for biometric modalities, including face (2D and 3D), iris, gait and latent prints (fingerprint and palmprint) and other emerging modalities.

• Highlight and discuss current challenges and recommendations for future research in Super-resolution for biometrics.

摘要

•Discuss the significance of super-resolution in the context of biometrics and how it is different from the general super-resolution.•Present a background knowledge in general super-resolution approaches.•Provide a comprehensive review of existing super-resolution approaches for biometric modalities, including face (2D and 3D), iris, gait and latent prints (fingerprint and palmprint) and other emerging modalities.•Highlight and discuss current challenges and recommendations for future research in Super-resolution for biometrics.

论文关键词：Super-resolution,Biometrics,Face recognition,Iris recognition,Gait recognition,Fingerprint recognition,Non-ideal biometrics,Human identification at a distance,Deep learning

论文评审过程：Received 20 April 2017, Revised 18 December 2017, Accepted 7 January 2018, Available online 11 January 2018, Version of Record 30 January 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.01.002