A Comparison of Transfer Learning Models for Face Recognition

Abstract

Face recognition (FR) is a method that uses face feature analysis and comparison to identify or verify individuals. Siamese neural networks (SNNs) are an effective method for FR, providing high accuracy and versatility, especially in situations where data is restricted. Unlike standard neural networks, SNNs learn to distinguish between pairs of inputs rather than individual inputs. However, detecting and recognizing faces in unconstrained environments poses a significant challenge due to various factors such as head pose, illumination, and facial expression variations. The aim of this paper is to design and develop an efficient approach based on SNNs and Transfer Learning methods. For this purpose LFW dataset and transfer learning architectures like VGG-16, EfficientNet, RestNet50 and ConvNext have been utilised. Performance of the architectures were measured using 5-Fold cross validation. According to results, EfficientNet, RestNet50 and ConvNext produced 78% accuracy, 95% and 93 % accuracy respectively. SNN with VGG-16 exhibited a low loss and produced the best accuracy in face recognition with 96%.

Keywords

• Face recognition
• Siamese neural network
• VGG-16
• ConvNext
• EfficientNet
• RestNet50

References

1. S. G. Bhandari, S. Rodrigues, P. C. Thejas, and B. S. Nausheeda, “ANALYSIS OF FRUSING LBPH ALGORITHM: A REVIEW,” Redshine Arch., vol. 2, 2023.
2. I. Adjabi, A. Ouahabi, A. Benzaoui, and A. Taleb-Ahmed, “Past, present, and future of face recognition: A review,” Electronics, vol. 9, no. 8, p. 1188, 2020.
3. T. Gerig et al., “Morphable face models-an open framework,” in 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), 2018, pp. 75–82.
4. Y.-S. Lim, S.-H. Lee, S.-J. Cheong, and Y.-H. Park, “A long-distance 3D FRarchitecture utilizing MEMS-based region-scanning LiDAR,” in MOEMS and Miniaturized Systems XXII, 2023, vol. 12434, pp. 87–91.
5. S. Koley, H. Roy, S. Dhar, and D. Bhattacharjee, “Illumination invariant FRusing fused cross lattice pattern of phase congruency (FCLPPC),” Inf. Sci. (Ny)., vol. 584, pp. 633–648, 2022.
6. aAmal A. Moustafa, A. Elnakib, and N. F. F. Areed, “Age-invariant FRbased on deep features analysis,” Signal, Image Video Process., vol. 14, pp. 1027–1034, 2020.
7. Y. Wen, K. Zhang, Z. Li, and Y. Qiao, “A discriminative feature learning approach for deep face recognition,” in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII 14, 2016, pp. 499–515.
8. Z. Chen, X. Feng, and S. Zhang, “Emotion detection and FRof drivers in autonomous vehicles in IoT platform,” Image Vis. Comput., vol. 128, p. 104569, 2022.

9. T. Sabharwal and R. Gupta, “Deep facial recognition after medical alterations,” Multimed. Tools Appl., vol. 81, no. 18, pp. 25675–25706, 2022.
10. Torrey, L., & Shavlik, J. (2010). Transfer learning. In Handbook of research on machine learning applications and trends: algorithms, methods, and techniques (pp. 242-264). IGI global.
11. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
12. D. Chicco, “Siamese neural networks: An overview,” Artif. neural networks, pp. 73–94, 2021.
13. N. Serrano and A. Bellogín, “Siamese neural networks in recommendation,” Neural Comput. Appl., pp. 1–13, 2023.
14. Z. S. Naser, H. N. Khalid, A. S. Ahmed, M. S. Taha, and M. M. Hashim, “Artificial Neural Network-Based Fingerprint Classification and Recognition.,” Rev. d’Intelligence Artif., vol. 37, no. 1, 2023.
15. U. Ruby and V. Yendapalli, “Binary cross entropy with deep learning technique for image classification,” Int. J. Adv. Trends Comput. Sci. Eng, vol. 9, no. 10, 2020.
16. M. Heidari and K. Fouladi-Ghaleh, “Using Siamese networks with transfer learning for FRon small-samples datasets,” in 2020 International Conference on Machine Vision and Image Processing (MVIP), 2020, pp. 1–4.
17. S. Tammina, “Transfer learning using vgg-16 with deep convolutional neural network for classifying images,” Int. J. Sci. Res. Publ., vol. 9, no. 10, pp. 143–150, 2019.
18. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv Prepr. arXiv1409.1556, 2014.
19. McDermott, J. (2021). Hands-On Transfer Learning with Keras and the vgg16 Model.
20. Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
21. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
22. Liu, Z., Mao, H., Wu, C. Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022). A convnet for the 2020s. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11976-11986).
23. A. Jalal and U. Tariq, “The LFW-gender dataset,” in Computer Vision–ACCV 2016 Workshops: ACCV 2016 International Workshops, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part III 13, 2017, pp. 531–540.
24. G. B. Huang, M. Mattar, T. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database forstudying FRin unconstrained environments,” 2008.
25. K. Sohn, H. Lee, and X. Yan, “Learning structured output representation using deep conditional generative models,” Adv. Neural Inf. Process. Syst., vol. 28, 2015.
26. Stone, M. (1974). Cross‐validatory choice and assessment of statistical predictions. Journal of the royal statistical society: Series B (Methodological), 36(2), 111-133.
27. X. Li, Y. Xiang, and S. Li, “Combining convolutional and vision transformer structures for sheep face recognition,” Comput. Electron. Agric., vol. 205, p. 107651, 2023.
28. P. Grother, M. Ngan, and K. Hanaoka, FRvendor test (fvrt): Part 3, demographic effects. National Institute of Standards and Technology Gaithersburg, MD, 2019.
29. J. J. Howard, E. J. Laird, R. E. Rubin, Y. B. Sirotin, J. L. Tipton, and A. R. Vemury, “Evaluating proposed fairness models for FRalgorithms,” in International Conference on Pattern Recognition, 2022, pp. 431–447.
30. M. Zulfiqar, F. Syed, M. J. Khan, and K. Khurshid, “Deep FRfor biometric authentication,” in 2019 international conference on electrical, communication, and computer engineering (ICECCE), 2019, pp. 1–6.
31. S.-C. Chong, A. B. J. Teoh, and T.-S. Ong, “Unconstrained face verification with a dual-layer block-based metric learning,” Multimed. Tools Appl., vol. 76, pp. 1703–1719, 2017.
32. C. Xiong, L. Liu, X. Zhao, S. Yan, and T.-K. Kim, “Convolutional fusion network for face verification in the wild,” IEEE Trans. Circuits Syst. Video Technol., vol. 26, no. 3, pp. 517–528, 2015.
33. A. Majumdar, R. Singh, and M. Vatsa, “Face verification via class sparsity based supervised encoding,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1273–1280, 2016.
34. J. Zhang, X. Jin, Y. Liu, A. K. Sangaiah, and J. Wang, “Small Sample FRAlgorithm Based on Novel Siamese Network.,” J. Inf. Process. Syst., vol. 14, no. 6, 2018.
35. B. Ameur, M. Belahcene, S. Masmoudi, and A. Ben Hamida, “Weighted PCA-EFMNet: A deep learning network for Face Verification in the Wild,” in 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018, pp. 1–6.
36. H. Wang et al., “Cosface: Large margin cosine loss for deep face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 5265–5274.