Synthetic Image Generation Using Conditional GAN-Provided Single-Sample Face Image
Source abstract
Abstract
The performance of facial recognition systems significantly decreases when faced with a lack of training images. This issue is exacerbated when there is only one image per subject available. Probe images may contain variations such as illumination, expression, and disguise, which are difficult to recognize accurately. In this work, we present a model that generates six facial variations from a single neutral face image. Our model is based on a CGAN, designed to produce six highly realistic facial expressions from one neutral face image. To evaluate the accuracy of our approach comprehensively, we employed several pre-trained models (VGG-Face, ResNet-50, FaceNet, and DeepFace) along with a custom CNN model. Initially, these models achieved only about 76% accuracy on single-sample neutral images, highlighting the SSPP challenge. However, after fine-tuning on the synthetic expressions generated by our CGAN from these single images, their accuracy increased significantly to around 99%. Our method has proven highly effective in addressing SSPP issues, as evidenced by the significant improvement achieved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face recognition and analysis · Face and Expression Recognition · Biometric Identification and Security
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Jeju National University, Jeju 63243, Republic of Korea
Department of Computer Science, Comsats University Islamabad, Abbottabad Campus, Abbottabad 22060, Pakistan
Funding
Ministry of Education (MOE)
References (40)
Show source-provided references
1. Maintaining Privacy in Face Recognition using Federated Learning Method10.1109/ACCESS.2024.3373691 ↗
2. Saadabadi, M.S.E., Malakshan, S.R., Zafari, A., Mostofa, M., and Nasrabadi, N.M. (2023, January 2–7). A quality aware sample-to-sample comparison for face recognition. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.
3. Deep learning based single sample face recognition: A survey10.1007/s10462-022-10240-2 ↗
4. Ríos-Sánchez, B., Costa-da Silva, D., Martín-Yuste, N., and Sánchez-Ávila, C. (2019). Deep learning for facial recognition on single sample per person scenarios with varied capturing conditions. Appl. Sci., 9.10.3390/app9245474 ↗
5. Kortli, Y., Jridi, M., Al Falou, A., and Atri, M. (2020). Face recognition systems: A survey. Sensors, 20.10.3390/s20020342 ↗
6. An efficient face recognition approach combining likelihood-based sufficient dimension reduction and LDA10.1007/s11042-020-09527-9 ↗
7. A review on Generative Adversarial Networks for image generation10.1016/j.cag.2023.05.010 ↗
8. Generative adversarial networks: An overview10.1109/MSP.2017.2765202 ↗
9. Hanano, T., Seo, M., and Chen, Y.W. (2023, January 6–8). An improved cgan with self-supervised guidance encoder for generation of high-resolution facial expression images. Proceedings of the 2023 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA.10.1109/ICCE56470.2023.10043561 ↗
10. Adjabi, I., Ouahabi, A., Benzaoui, A., and Taleb-Ahmed, A. (2020). Past, present, and future of face recognition: A review. Electronics, 9.10.20944/preprints202007.0479.v1 ↗
11. A facial recognition using a combination of a novel one dimension deep CNN and LDA10.1016/j.matpr.2021.07.325 ↗
12. Masked face recognition with convolutional neural networks and local binary patterns10.1007/s10489-021-02728-1 ↗
13. Joint and collaborative representation with local adaptive convolution feature for face recognition with single sample per person10.1016/j.patcog.2016.12.028 ↗
14. Single sample face recognition via learning deep supervised autoencoders10.1109/TIFS.2015.2446438 ↗
15. A novel neural network method for face recognition with a single sample per person10.1109/ACCESS.2020.2999030 ↗
16. Neither global nor local: Regularized patch-based representation for single sample per person face recognition10.1007/s11263-014-0750-4 ↗
17. Smart attendance system based on improved facial recognition10.18196/jrc.v4i1.16808 ↗
18. Liu, F., Tang, J., Song, Y., Xiang, X., and Tang, Z. (2014, January 27–30). Local structure based sparse representation for face recognition with single sample per person. Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP), Paris, France.10.1109/ICIP.2014.7025143 ↗
19. Hong, S., Im, W., Ryu, J., and Yang, H.S. (2017, January 17–20). Sspp-dan: Deep domain adaptation network for face recognition with single sample per person. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.10.1109/ICIP.2017.8296396 ↗
20. Kumar, K.V., Teja, K.A., Bhargav, R.T., Satpute, V., Naveen, C., and Kamble, V. (2023, January 5–6). One-shot face recognition. Proceedings of the 2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS), Nagpur, India.10.1109/PCEMS58491.2023.10136112 ↗
21. Sparse Common Feature Representation for Undersampled Face Recognition10.1109/JIOT.2020.3031390 ↗
22. Iterative Dynamic Generic Learning for Face Recognition From a Contaminated Single-Sample Per Person10.1109/TNNLS.2020.2985099 ↗
23. Monogenic features based single sample face recognition by kernel sparse representation on multiple riemannian manifolds10.1016/j.neucom.2022.06.113 ↗
24. SOM-based binary coding for single sample face recognition10.1007/s12652-021-03255-0 ↗
25. 2d pose-invariant face recognition using single frontal-view face database10.1007/s11277-020-07063-1 ↗
26. A single-stage face detection and face recognition deep neural network based on feature pyramid and triplet loss10.1049/ipr2.12479 ↗
27. Neto, P.C., Sequeira, A.F., Cardoso, J.S., and Terhörst, P. (2023, January 18–22). PIC-Score: Probabilistic Interpretable Comparison Score for Optimal Matching Confidence in Single-and Multi-Biometric Face Recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPRW59228.2023.00109 ↗
28. A review on generative adversarial networks: Algorithms, theory, and applications10.1109/TKDE.2021.3130191 ↗
29. A review on Single Image Super Resolution techniques using generative adversarial network10.1016/j.ijleo.2022.169607 ↗
30. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., and Wang, Z. (2017, January 21–26). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.19 ↗
31. Conditional generative adversarial networks based on the principle of homologycontinuity for face aging10.1002/cpe.5792 ↗
32. Tran, L., Yin, X., and Liu, X. (2017, January 21–26). Disentangled representation learning gan for pose-invariant face recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.141 ↗
33. Lu, Y., Wu, S., Tai, Y.W., and Tang, C.K. (2018, January 8–14). Image generation from sketch constraint using contextual gan. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01270-0_13 ↗
34. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
35. Kwon, Y.H., and Park, M.G. (2019, January 15–20). Predicting future frames using retrospective cycle gan. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00191 ↗
36. Martinez, A., and Benavente, R. (2024, June 03). The AR Face Database: CVC Technical Report, 24. Available online: http://www.cat.uab.es/Public/Publications/1998/MaB1998/CVCReport24.pdf.
37. Parkhi, O., Vedaldi, A., and Zisserman, A. (2015, January 7–10). Deep face recognition. Proceedings of the BMVC 2015-Proceedings of the British Machine Vision Conference 2015, British Machine Vision Association, Swansea, UK.10.5244/C.29.41 ↗
38. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
39. Schroff, F., Kalenichenko, D., and Philbin, J. (2015, January 7–12). Facenet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298682 ↗
40. Taigman, Y., Yang, M., Ranzato, M., and Wolf, L. (2014, January 23–28). Deepface: Closing the gap to human-level performance in face verification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.220 ↗