Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment (2106.04852v2)

Published 9 Jun 2021 in cs.CV

Abstract: Face recognition has made significant progress in recent years due to deep convolutional neural networks (CNN). In many face recognition (FR) scenarios, face images are acquired from a sequence with huge intra-variations. These intra-variations, which are mainly affected by the low-quality face images, cause instability of recognition performance. Previous works have focused on ad-hoc methods to select frames from a video or use face image quality assessment (FIQA) methods, which consider only a particular or combination of several distortions. In this work, we present an efficient non-reference image quality assessment for FR that directly links image quality assessment (IQA) and FR. More specifically, we propose a new measurement to evaluate image quality without any reference. Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data. We evaluate the proposed method for different powerful FR models on two classical video-based (or template-based) benchmark: IJB-B and YTF. Extensive experiments show that, although the tinyFQnet is much smaller than the others, the proposed method outperforms state-of-the-art quality assessment methods in terms of effectiveness and efficiency.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. Design and evaluation of photometric image quality measures for effective face recognition. IET Biometrics, 3(4):314–324, 2014.
  2. Partial fc: Training 10 million identities on a single machine. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1445–1449, 2021.
  3. Faceqan: Face image quality assessment through adversarial noise exploration. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 748–754. IEEE, 2022.
  4. L. Best-Rowden and A. K. Jain. Learning face image quality from human assessments. IEEE Transactions on Information Forensics and Security, 13(12):3064–3077, 2018.
  5. Cr-fiqa: face image quality assessment by learning sample relative classifiability. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5836–5845, 2023.
  6. Face image quality assessment based on learning to rank. IEEE signal processing letters, 22(1):90–94, 2015.
  7. Lightqnet: Lightweight deep face quality assessment for risk-controlled face recognition. IEEE Signal Processing Letters, 28:1878–1882, 2021.
  8. Noise estimation in remote sensing imagery using data masking. International Journal of Remote Sensing, 24(4):689–702, 2003.
  9. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4690–4699, 2019.
  10. Retinaface: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641, 2019.
  11. Perceptual quality metrics applied to still image compression. Signal Processing, 70(3):177–200, 1998.
  12. No-reference assessment of blur and noise impacts on image quality. Signal Image & Video Processing, 2010.
  13. Image quality measures and their performance. IEEE Transactions on communications, 43(12):2959–2965, 1995.
  14. R. Ferzli and L. J. Karam. A no-reference objective image sharpness metric based on the notion of just noticeable blur (jnb). IEEE Transactions on Image Processing, 18(4):717–728, 2009.
  15. Standardization of face image sample quality. In International Conference on Biometrics, pages 242–251. Springer, 2007.
  16. Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In European conference on computer vision, pages 87–102. Springer, 2016.
  17. No-reference image sharpness assessment based on local phase coherence measurement. In 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 2434–2437, 2010.
  18. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  19. Faceqnet: quality assessment for face recognition based on deep learning. In 2019 International Conference on Biometrics (ICB), pages 1–8. IEEE, 2019.
  20. Mobilenets: Efficient convolutional neural networks for mobile vision applications. 2017.
  21. Quality assessment of facial images. In Biometric Consortium Conference, 2006 Biometrics Symposium: Special Session on Research at the, pages 1–6, 2006.
  22. Curricularface: adaptive curriculum learning loss for deep face recognition. In proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5901–5910, 2020.
  23. On evaluating pixel-level face image quality assessment. In 2022 30th European Signal Processing Conference (EUSIPCO), pages 1052–1056. IEEE, 2022.
  24. Analysis of distortion distribution for pooling in image quality prediction. IEEE Transactions on Broadcasting, 62(2):446–456, 2016.
  25. Face image assessment learned with objective and relative face image qualities for improved face recognition. In Image Processing (ICIP), 2015 IEEE International Conference on, pages 4027–4031. IEEE, 2015.
  26. Most apparent distortion: full-reference image quality assessment and the role of strategy. Journal of Electronic Imaging, 19(1), 2010.
  27. No-reference image quality assessment with deep convolutional neural networks. In 2016 IEEE International Conference on Digital Signal Processing (DSP), 2016.
  28. Liqa: Lifelong blind image quality assessment. IEEE Transactions on Multimedia, 2022.
  29. Sphereface: Deep hypersphere embedding for face recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 6738–6746, 2017.
  30. Large-margin softmax loss for convolutional neural networks. In Proceedings of The 33rd International Conference on Machine Learning, 2016.
  31. iqiyi-vid: A large dataset for multi-modal person identification. arXiv preprint arXiv:1811.07548, 2018.
  32. Iarpa janus benchmark-c: Face dataset and protocol. In 2018 International Conference on Biometrics (ICB), pages 158–165. IEEE, 2018.
  33. Magface: A universal representation for face recognition and quality assessment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14225–14234, June 2021.
  34. Blind image quality assessment: From natural scene statistics to perceptual quality. IEEE Transactions on Image Processing, 20(12):p.3350–3364, 2011.
  35. K. Nasrollahi and T. B. Moeslund. Face quality assessment system in video sequences. In European Workshop on Biometrics and Identity Management, pages 10–18. Springer, 2008.
  36. The feret evaluation methodology for face-recognition algorithms. IEEE Transactions on pattern analysis and machine intelligence, 22(10):1090–1104, 2000.
  37. Complex wavelet structural similarity: A new image similarity index. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 18(11):p.2385–2401, 2009.
  38. Face image quality evaluation for iso/iec standards 19794-5 and 29794-5. In International Conference on Biometrics, pages 229–238. Springer, 2009.
  39. Metadata-based feature aggregation network for face recognition. In ICB, pages 118–123, Feb 2018.
  40. S. Shan. No-reference visually significant blocking artifact metric for natural scene images. Signal Processing, 89(8):1647–1652, 2009.
  41. An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Trans Image Process, 14(12):2117–2128, 2006.
  42. Face biometric quality assessment via light cnn. Pattern Recognition Letters, 2017.
  43. M. Tan and Q. V. Le. Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946, 2019.
  44. Face image quality assessment for face selection in surveillance video using convolutional neural networks. In Signal and Information Processing (GlobalSIP), 2015 IEEE Global Conference on, pages 577–581. IEEE, 2015.
  45. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
  46. Iarpa janus benchmark-b face dataset. pages 592–600, 2017.
  47. Face recognition in unconstrained videos with matched background similarity. In Computer Vision and Pattern Recognition, pages 529–534, 2011.
  48. Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on, pages 74–81. IEEE, 2011.
  49. Neural aggregation network for video face recognition. In CVPR, pages 1–8. IEEE, 2017.
  50. G. Zhang and Y. Wang. Asymmetry-based quality assessment of face images. Advances in Visual Computing, pages 499–508, 2009.
  51. Kurtosis-based no-reference quality assessment of jpeg2000 images. Signal Processing Image Communication, 26(1):13–23, 2011.
  52. Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Transactions on Circuits and Systems for Video Technology, 30(1):36–47, 2020.
  53. Rrar: A novel reduced-reference iqa algorithm for facial images. In IEEE International Conference on Image Processing, 2011.
  54. Recognition oriented facial image quality assessment via deep convolutional neural network. Neurocomputing, 358:109–118, 2019.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Baoyun Peng (6 papers)
  2. Min Liu (236 papers)
  3. Zhaoning Zhang (11 papers)
  4. Kai Xu (313 papers)
  5. Dongsheng Li (240 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now