FacialSCDnet: A deep learning approach for the estimation of subject-to-camera distance in facial photographs
作者：
Highlights：
• Accurate estimation of subject-to-camera distance in portrait photographs.
• A novel metric is proposed, based on the effects of perspective in facial distortion.
• A new database of facial images at a distance is introduced for human identification.
• A transfer learning approach overcomes the limitations of current methods.
• Robust to expression, occlusion and pose without requiring anatomical information.
摘要
•Accurate estimation of subject-to-camera distance in portrait photographs.•A novel metric is proposed, based on the effects of perspective in facial distortion.•A new database of facial images at a distance is introduced for human identification.•A transfer learning approach overcomes the limitations of current methods.•Robust to expression, occlusion and pose without requiring anatomical information.
论文关键词：Subject-to-camera distance,Perspective distortion,Photography,Human identification,Deep learning,Transfer learning
论文评审过程：Received 28 September 2021, Revised 22 July 2022, Accepted 5 August 2022, Available online 11 August 2022, Version of Record 17 August 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118457
