Low-FaceNet: Face Recognition-Driven Low-Light Image Enhancement
- 21 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Abstract
Images captured in low-light conditions often induce the performance degradation of cutting-edge face recognition models. The missing and wrong face recognition inevitably makes vision-based systems operate poorly. In this paper, we propose Low-FaceNet, a novel face recognition-driven network to make low-level image enhancement (LLE) interact with high-level recognition for realizing mutual gain under a unified deep learning framework. Unlike existing methods, Low-FaceNet uniquely brightens real-world images by unsupervised contrastive learning and absorbs the wisdom of facial understanding. Low-FaceNet possesses an image enhancement network that is assembled by four key modules: a contrastive learning module, a feature extraction module, a semantic segmentation module, and a face recognition module. These modules enable Low-FaceNet to not only improve the brightness contrast and retain features but also increase the accuracy of recognizing faces in low-light conditions. Furthermore, we establish a new dataset of low-light face images called LaPa-Face. It includes detailed annotations with 11 categories of facial features and identity labels. Extensive experiments demonstrate our superiority against state-of-the-art methods of both LLE and face recognition even without ground-truth image labels. Our code and dataset are available at https://github.com/fanyihua0309/Low-FaceNet.Keywords
Funding Information
- National Natural Science Foundation of China (T2322012, 62172218, 62032011)
- Shenzhen Science and Technology Program (JCYJ20220818103401003, JCYJ20220530172403007)
- Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515010170)
This publication has 40 references indexed in Scilit:
- Beyond Brightening Low-light ImagesInternational Journal of Computer Vision, 2021
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Learning to See in the Dark2018
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- SSD: Single Shot MultiBox Detector2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- WIDER FACE: A Face Detection Benchmark2016
- FaceNet: A unified embedding for face recognition and clustering2015
- The Retinex Theory of Color VisionScientific American, 1977