딥러닝 기반 저조도 향상 기술을 활용한 얼굴 인식 성능 개선
Deep Learning-Based Face Recognition through Low-Light Enhancement
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This study explores enhancing facial recognition performance in low-light environments using deep learning-based low-light enhancement techniques. Facial recognition technology is widely used in edge devices like smartphones, smart home devices, and security systems, but low-light conditions reduce accuracy due to degraded image quality and increased noise. We reviewed the latest techniques, including Zero-DCE, Zero-DCE++, and SCI (Self-Calibrated Illumination), and applied them as preprocessing steps in facial recognition on edge devices. Using the K-face dataset, experiments on the Qualcomm QRB5165 platform showed significant improvements in F1 SCORE from 0.57 to 0.833 with SCI. Processing times were 0.15ms for SCI, 0.4ms for Zero-DCE, and 0.7ms for Zero-DCE++, all much shorter than the facial recognition model MobileFaceNet’s 5ms. These results indicate that these techniques can be effectively used in resource-limited edge devices, enhancing facial recognition in low-light conditions for various applications.
Abstract
This study explores enhancing facial recognition performance in low-light environments using deep learning-based low-light enhancement techniques. Facial recognition technology is widely used in edge devices like smartphones, smart home devices, and security systems, but low-light conditions reduce accuracy due to degraded image quality and increased noise. We reviewed the latest techniques, including Zero-DCE, Zero-DCE++, and SCI (Self-Calibrated Illumination), and applied them as preprocessing steps in facial recognition on edge devices. Using the K-face dataset, experiments on the Qualcomm QRB5165 platform showed significant improvements in F1 SCORE from 0.57 to 0.833 with SCI. Processing times were 0.15ms for SCI, 0.4ms for Zero-DCE, and 0.7ms for Zero-DCE++, all much shorter than the facial recognition model MobileFaceNet’s 5ms. These results indicate that these techniques can be effectively used in resource-limited edge devices, enhancing facial recognition in low-light conditions for various applications.
참고문헌 (16)
- C. Guo, "Zero-reference Deep Curve Estimation for Low-light Image Enhancement", Proceedings of the IEEE, 2020, 1780~1789
- C. Li, "Learning to Enhance Low-light Image Via Zero-reference Deep Curve Estimation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(8), pp.4225~4238 (2021)
- L. Ma, "Toward Fast, Flexible, and Robust Low-light Image Enhancement", Proceedings of the IEEE, 2022, 5637~5646
- J. Redmon, "You Only Look Once: Unified, Real-time Object Detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
- J. Deng, "Retinaface: Single-shot Multi-level Face Localisation in the Wild", Proceedings of the IEEE, 2020, 5203~5212
- K. Zhang, "Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks", IEEE Signal Processing Letters, 23(10), pp.1499~1503 (2016)
- E. Hoffer, "Deep Metric Learning Using Triplet Network", Similarity-Based Pattern Recognition: Third International Workshop, SIMBAD 2015, pp.84~92 (2015), Springer International Publishing
- J. Deng, "Arcface: Additive Angular Margin Loss for Deep Face Recognition", Proceedings of the IEEE, 2019, 4690~4699
- Y. Zhang, "Kindling the Darkness: A Practical Low-light Image Enhancer", Proceedings of the 27th ACM International Conference on Multimedia, pp.1635~1643 (2019)
- E. H. Land, "Lightness and Retinex Theory", Journal of the Optical Society of America, 61(1), pp.1~11 (1971)
- G. P. Nam, "Large-Scale Korean Face Database Construction", Proceedings of the IEIE Conference, pp.62~63 (2017)
- Y. Guo, "MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition", Computer Vision–ECCV 2016: 14th European Conference, pp.87~102 (2016), Springer International Publishing
- S. Chen, "Mobilefacenets: Efficient cnns for Accurate Real-time Face Verification on Mobile Devices", Biometric Recognition: 13th Chinese Conference, pp.428~438 (2018), Springer International Publishing