The Effects of AI-Driven Face Restoration on Forensic Face Recognition
Source abstract
Abstract
In biometric recognition, face recognition is a mature and widely used technique that provides a fast, accurate, and reliable method for human identification. This paper aims to study the effects of face image restoration for forensic face recognition and then further analyzes the advantages and limitations of the four state-of-the-art face image restoration methods in the field of face recognition for forensic human image identification. In total, 100 face image materials from an open-source face image dataset are used for experiments. The Gaussian blur processing is applied to simulate the effect of blurred face images in actual cases of forensic human image identification. Four state-of-the-art AI-driven face restoration methods are used to restore the blurred face images. We use three mainstream face recognition systems to evaluate the recognition performance changes of the blurred face images and the restored face images. We find that although face image restoration can effectively remove facial noise and blurring effects, the restored images do not significantly improve the recognition performance of the face recognition systems. Face image restoration may change the original features in face images and introduce new made-up image features, thereby affecting the accuracy of face recognition. In current conditions, the improvement in face image restoration on the recognition performance of face recognition systems is limited, but it still has a positive role in the application of forensic human image identification.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face recognition and analysis · Biometric Identification and Security
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, China
Academy of Forensic Science, Shanghai 200063, China
Funding
Shanghai Science and Technology Commission Project · Ministry of Finance
References (48)
Show source-provided references
1. Age-invariant face recognition by multi-feature fusionand decomposition with self-attention10.1145/3472810 ↗
2. Critical features for face recognition10.1016/j.cognition.2018.09.002 ↗
3. Zeng, J., Zhu, H., Shi, S., and Qiu, X. (2018, January 14–16). Face image quality quantitative assessment for forensic identification of human images. Proceedings of the 2018 IEEE International Conference on Progress in Informatics and Computing (PIC), Suzhou, China.10.1109/PIC.2018.8706327 ↗
4. Attention-based hierarchical pyramid feature fusion structure for efficient face recognition10.1049/ipr2.12802 ↗
5. An unusual method of forensic human identification: Use of selfie photographs10.1016/j.forsciint.2016.04.028 ↗
6. Image processing effects on the deep face recognition system10.3934/mbe.2021064 ↗
7. Phillips, P.J., White, D., O’Toole, A., and Norell, K. (2017). Handbook of Biometrics for Forensic Science, Springer.
8. Valentine, T., and Davis, J.P. (2015). Forensic Facial Identification: Theory and Practice of Identification from Eyewitnesses, Composites and CCTV, Blackwell Pub.10.1002/9781118469538 ↗
9. Velusamy, S., Parihar, R., Kini, R., and Rege, A. (2020, January 13–19). FabSoften: Face beautification via dynamic skin smoothing, guided feathering, and texture restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00273 ↗
10. Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms10.1073/pnas.1721355115 ↗
11. Simulated automated facial recognition systems as decision-aids in forensic face matching tasks10.1037/xge0001310 ↗
12. Koo, J.H., Cho, S.W., Baek, N.R., and Park, K.R. (2020). Face and body-based human recognition by GAN-based blur restoration. Sensors, 20.10.3390/s20185229 ↗
13. Occlusion detection and restoration techniques for 3D face recognition: A literature review10.1007/s00138-018-0933-z ↗
14. He, M., Zhang, J., Shan, S., and Chen, X. (2022, January 18–24). Enhancing face recognition with self-supervised 3d reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00403 ↗
15. Merkle, J., Rathgeb, C., Tams, B., Lou, D.-P., Dörsch, A., and Drozdowski, P. (2022). State of the art of quality assessment of facial images. arXiv.
16. Brief review of image denoising techniques10.1186/s42492-019-0016-7 ↗
17. An experimental-based review of image enhancement and image restoration methods for underwater imaging10.1109/ACCESS.2019.2932130 ↗
18. Nonlocally centralized sparse representation for image restoration10.1109/TIP.2012.2235847 ↗
19. Zoran, D., and Weiss, Y. (2011, January 6–13). From learning models of natural image patches to whole image restoration. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain.10.1109/ICCV.2011.6126278 ↗
20. Mao, X., Shen, C., and Yang, Y.-B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Adv. Neural Inf. Process. Syst., 29.
21. Ali, A.M., Benjdira, B., Koubaa, A., El-Shafai, W., Khan, Z., and Boulila, W. (2023). Vision transformers in image restoration: A survey. Sensors, 23.10.3390/s23052385 ↗
22. Panini-Net: GAN prior based degradation-aware feature interpolation for face restoration
23. Deep sparse representation based image restoration with denoising prior10.1109/TCSVT.2022.3170689 ↗
24. State-of-art analysis of image denoising methods using convolutional neural networks10.1049/iet-ipr.2019.0157 ↗
25. Image restoration using total variation with overlapping group sparsity10.1016/j.ins.2014.10.041 ↗
26. Adaptive norm selection for regularized image restoration and super-resolution10.1109/TCYB.2015.2446755 ↗
27. Image super-resolution: The techniques, applications, and future10.1016/j.sigpro.2016.05.002 ↗
28. Image super-resolution reconstruction algorithm based on significant network connection-collaborative migration structure10.1016/j.dsp.2022.103566 ↗
29. The CNN paradigm10.1109/81.222795 ↗
30. Bhatt, D., Patel, C., Talsania, H., Patel, J., Vaghela, R., Pandya, S., Modi, K., and Ghayvat, H. (2021). CNN variants for computer vision: History, architecture, application, challenges and future scope. Electronics, 10.10.3390/electronics10202470 ↗
31. Image denoising method based on a deep convolution neural network10.1049/iet-ipr.2017.0389 ↗
32. Yin, W., Kann, K., Yu, M., and Schütze, H. (2017). Comparative study of CNN and RNN for natural language processing. arXiv.
33. Zhang, Y., Gan, Z., Fan, K., Chen, Z., Henao, R., Shen, D., and Carin, L. (2017, January 6–11). Adversarial feature matching for text generation. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia.
34. Chen, J., Chen, J., Chao, H., and Yang, M. (2018, January 18–23). Image blind denoising with generative adversarial network based noise modeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00333 ↗
35. Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., and Yang, M.-H. (2018, January 8–14). Online multi-object tracking with dual matching attention networks. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01228-1_23 ↗
36. Recent advances of generative adversarial networks in computer vision10.1109/ACCESS.2018.2886814 ↗
37. Design and development of RNN anomaly detection model for IoT networks10.1109/ACCESS.2022.3176317 ↗
38. Mikolov, T., Kombrink, S., Burget, L., Černocký, J., and Khudanpur, S. (2011, January 22–27). Extensions of recurrent neural network language model. Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic.10.1109/ICASSP.2011.5947611 ↗
39. Liang, L., Lin, L., Jin, L., Xie, D., and Li, M. (2018, January 20–24). SCUT-FBP5500: A diverse benchmark dataset for multi-paradigm facial beauty prediction. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.10.1109/ICPR.2018.8546038 ↗
40. Deep learning based face beauty prediction via dynamic robust losses and ensemble regression10.1016/j.knosys.2022.108246 ↗
41. Saeed, J.N., Abdulazeez, A.M., and Ibrahim, D.A. (2022, January 8). FIAC-Net: Facial image attractiveness classification based on light deep convolutional neural network. Proceedings of the 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA), Gunupur, India.10.1109/ICCSEA54677.2022.9936582 ↗
42. Hill, J. (2023, December 01). [Official] HitPaw Photo Enhancer—One Click AI Photo Quality Enhancer. Available online: https://www.hitpaw.com/photo-enhancer.html.
43. Labs, T. (2023, December 01). Topaz Photo AI—Maximize Image Quality with AI. Available online: https://www.topazlabs.com/topaz-photo-ai.
44. SMS-iT (2023, December 01). Image Format Converter—Image Format Conversion—Quick Image Converter Online. Available online: https://www.xunjietupian.com.
45. (2023, December 01). yangtao9009. GitHub—Yangxy/GPEN. Available online: https://github.com/yangxy/GPEN.
46. Baidu (2023, December 01). Facial Recognition Cloud Service. Available online: https://cloud.baidu.com/product/face.
47. Aliyun (2023, December 01). Human Face-Alibaba Cloud Visual Intelligence Open Platform. Available online: https://vision.aliyun.com/facebody.
48. Co, A.T. (2023, December 01). ArcSoft Vision Open Platform. Available online: https://ai.arcsoft.com.cn/product/arcface.html.