Machine vision quality assessment for robust face detection

作者：

Highlights：

• Quality assessment from the point of view of face detection algorithms requires a new definition.

• We define machine vision quality for face detection as a weighted combination of precision and recall.

• We use machine vision quality for image enhancement to improve face detection performance.

• Experiments reveal the benefit of using machine vision quality when compared to perceptual quality.

摘要

•Quality assessment from the point of view of face detection algorithms requires a new definition.•We define machine vision quality for face detection as a weighted combination of precision and recall.•We use machine vision quality for image enhancement to improve face detection performance.•Experiments reveal the benefit of using machine vision quality when compared to perceptual quality.

论文关键词：

论文评审过程：Received 10 July 2018, Revised 13 October 2018, Accepted 18 December 2018, Available online 29 December 2018, Version of Record 9 January 2019.

论文官网地址：https://doi.org/10.1016/j.image.2018.12.012