2.5D Face Recognition System using EfficientNet with Various Optimizers

Min-Er Teo - Multimedia University, Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia
Lee-Ying Chong - Multimedia University, Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia
Siew-Chin Chong - Multimedia University, Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia
Pey-Yun Goh - Multimedia University, Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.4.3030

Abstract


Face recognition has emerged as the most common biometric technique for checking a person's authenticity in various applications. The depth characteristic that exists in 2.5D data, also known as depth image, is utilized by the 2.5D facial recognition algorithm to supply additional details, strengthening the system's precision and durability. A deep learning approach-based 2.5D facial recognition system is proposed in this research. The accuracy of 2.5D face recognition could be enhanced by integrating depth data with deep learning approaches. Besides, optimizers in the deep learning approach act as a function for adjusting the properties, like learning rates and weights in the neural network, which can minimize the overall loss of the system and further enhance performance. In this paper, several experiments have been conducted in two versions of EfficientNet architectures, such as EfficientNetB1 and EfficientNetB4, using different optimizers, including Adam, Nadam, Adamax, RMSProp, etc. Various optimizers are compared to find the most suitable optimizer for the system. The Face Recognition Grand Challenge version 2 (FRGC v2.0) database was utilized in this research. This research aims to increase the 2.5D face recognition system’s effectiveness and efficiency by implementing deep learning approaches. Based on the experimental result, a deep learning algorithm enhances the system's accuracy rate. It also proves that the EffifientNetB4, using Adam optimizer, gained the highest accuracy rate at 97.93%.


Keywords


2.5D face recognition; depth image, deep learning; EfficientNet; optimizers

Full Text:

PDF

References


A. J. Shepley, "Deep Learning For Face Recognition: A Critical Analysis," arXiv, 2019. [Online]. Available: https://arxiv.org/abs/1907.12739.

L. Y. Chong, T. S. Ong, and A. B. J. Teoh, “Feature fusions for 2.5D face recognition in Random Maxout Extreme Learning Machine,” Applied Soft Computing, vol. 75, pp. 358–372, Feb. 2019, doi:10.1016/j.asoc.2018.11.024.

I. N. Alam, I. H. Kartowisastro, and P. Wicaksono, “Transfer Learning Technique with EfficientNet for Facial Expression Recognition System,” Revue d’Intelligence Artificielle, vol. 36, no. 4, pp. 543–552, Aug. 2022, doi: 10.18280/ria.360405.

M. Tan and Q. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proceedings of the 36th International Conference on Machine Learning, vol. 97, K. Chaudhuri and R. Salakhutdinov, Eds., PMLR, Jun. 2019, pp. 6105–6114. [Online]. Available: https://proceedings.mlr.press/v97/tan19a.html.

G. Ayush, “A Comprehensive Guide on Optimizers in Deep Learning.” Analytics Vidhya, Jan. 23, 2024. [Online]. Available: https://www.analyticsvidhya.com/blog/2021/10/a-comprehensive-guide-on-deep-learning-optimizers/

S. Soltanpour and Q. J. Wu, “Multimodal 2D–3D face recognition using local descriptors: pyramidal shape map and structural context,” IET Biometrics, vol. 6, no. 1, pp. 27–35, Sep. 2016, doi: 10.1049/iet-bmt.2015.0120.

B. Guo and F. Da, “Expression-Invariant 3D Face Recognition Based on Local Descriptors,” Journal of Computer-Aided Design & Computer Graphics, vol. 31, no. 7, p. 1086, 2019, doi:10.3724/sp.j.1089.2019.17433.

S. Soltanpour and Q. M. J. Wu, “Weighted Extreme Sparse Classifier and Local Derivative Pattern for 3D Face Recognition,” IEEE Transactions on Image Processing, vol. 28, no. 6, pp. 3020–3033, Jun. 2019, doi: 10.1109/tip.2019.2893524.

L. Shi, X. Wang, and Y. Shen, “Research on 3D face recognition method based on LBP and SVM,” Optik, vol. 220, p. 165157, Oct. 2020, doi: 10.1016/j.ijleo.2020.165157.

H. Boukamcha, M. Hallek, F. Smach, and M. Atri, “Automatic landmark detection and 3D Face data extraction,” Journal of Computational Science, vol. 21, pp. 340–348, Jul. 2017, doi:10.1016/j.jocs.2016.11.015.

Y. Yu, F. Da, and Y. Guo, “Sparse ICP With Resampling and Denoising for 3D Face Verification,” IEEE Transactions on Information Forensics and Security, vol. 14, no. 7, pp. 1917–1927, Jul. 2019, doi: 10.1109/tifs.2018.2889255.

M. Peter, J.-L. Minoi, and I. H. M. Hipiny, “3D Face Recognition using Kernel-based PCA Approach,” Computational Science and Technology, pp. 77–86, Aug. 2018, doi: 10.1007/978-981-13-2622-6_8.

B. Nassih, A. Amine, M. Ngadi, Y. Azdoud, D. Naji, and N. Hmina, “An efficient three-dimensional face recognition system based random forest and geodesic curves,” Computational Geometry, vol. 97, p. 101758, Aug. 2021, doi: 10.1016/j.comgeo.2021.101758.

W.-H. Chuah, S.-C. Chong, and L.-Y. Chong, “The Assistance of Eye Blink Detection for Two- Factor Authentication,” Journal of Informatics and Web Engineering, vol. 2, no. 2, pp. 111–121, Sep. 2023, doi: 10.33093/jiwe.2023.2.2.8.

K. Xu, X. Wang, Z. Hu, and Z. Zhang, “3D Face Recognition Based on Twin Neural Network Combining Deep Map and Texture,” 2019 IEEE 19th International Conference on Communication Technology (ICCT), Oct. 2019, doi: 10.1109/icct46805.2019.8947113.

J. Xu, W. Tian, G. Lv, S. Liu, and Y. Fan, “2.5D Facial Personality Prediction Based on Deep Learning,” Journal of Advanced Transportation, vol. 2021, pp. 1–12, Jun. 2021, doi:10.1155/2021/5581984.

M. E. Atik and Z. Duran, “Deep Learning-Based 3D Face Recognition Using Derived Features from Point Cloud,” Innovations in Smart Cities Applications, Volume 4, pp. 797–808, 2021, doi: 10.1007/978-3-030-66840-2_60.

W. Hariri and M. Zaabi, “Deep Residual Feature Quantization for 3D Face Recognition,” Nov. 2021, doi: 10.21203/rs.3.rs-1103780/v1.

Y. Yan, C. Han, J. Qin, H. Chen, and T. Guo, “Facial depth descend: A generation paradigm for facial depth map,” Neurocomputing, vol. 466, pp. 298–310, Nov. 2021, doi: 10.1016/j.neucom.2021.09.010.

K. Dutta, D. Bhattacharjee, M. Nasipuri, and O. Krejcar, “3D Face Recognition Using a Fusion of PCA and ICA Convolution Descriptors,” Neural Processing Letters, vol. 54, no. 4, pp. 3507–3527, Feb. 2022, doi: 10.1007/s11063-022-10761-5.

J.-R. Lee, K.-W. Ng, and Y.-J. Yoong, “Face and Facial Expressions Recognition System for Blind People Using ResNet50 Architecture and CNN,” Journal of Informatics and Web Engineering, vol. 2, no. 2, pp. 284–298, Sep. 2023, doi: 10.33093/jiwe.2023.2.2.20.

G. Mu, D. Huang, G. Hu, J. Sun, and Y. Wang, “Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces,” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5766–5775, Jun. 2019, doi:10.1109/cvpr.2019.00592..

S. Zulqarnain Gilani and A. Mian, “Learning from Millions of 3D Scans for Large-Scale 3D Face Recognition,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, doi: 10.1109/cvpr.2018.00203.

S. D. P.R. and B. R., “A two-phase approach for expression invariant 3D face recognition using fine-tuned VGG-16 and 3D-SIFT descriptors,” Multimedia Tools and Applications, vol. 82, no. 15, pp. 23873–23890, Feb. 2023, doi: 10.1007/s11042-023-14407-z.

R. Xu et al., “Depth Map Denoising Network and Lightweight Fusion Network for Enhanced 3D Face Recognition,” Pattern Recognition, vol. 145, p. 109936, Jan. 2024, doi: 10.1016/j.patcog.2023.109936.

S. Sharma and V. Kumar, “3D landmark‐based face restoration for recognition using variational autoencoder and triplet loss,” IET Biometrics, vol. 10, no. 1, pp. 87–98, Dec. 2020, doi:10.1049/bme2.12005.

V. Agarwal, “Complete Architectural Details of all EfficientNet Models.” [Online]. Available: https://towardsdatascience.com/complete-architectural-details-of-all-efficientnet-models-5fd5b736142

A. F. Agarap, "Deep Learning using Rectified Linear Units (ReLU)," arXiv preprint, arXiv:1803.08375, 2019. [Online]. Available: https://arxiv.org/abs/1803.08375.

M. Wang, S. Lu, D. Zhu, J. Lin, and Z. Wang, “A High-Speed and Low-Complexity Architecture for Softmax Function in Deep Learning,” 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), pp. 223–226, Oct. 2018, doi:10.1109/apccas.2018.8605654.

M.-E. Teo, L.-Y. Chong, and S.-C. Chong, “Fusion-Based 2.5D Face Recognition System,” Journal of Telecommunications and the Digital Economy, vol. 12, no. 1, pp. 19–38, Mar. 2024, doi:10.18080/jtde.v12n1.770.

H. Hu, S. A. A. Shah, M. Bennamoun, and M. Molton, “2D and 3D face recognition using convolutional neural network,” TENCON 2017 - 2017 IEEE Region 10 Conference, pp. 133–132, Nov. 2017, doi:10.1109/tencon.2017.8227850.

W. Zhang and L. Chen, “CrossEncoder: Towards 3D-Free Depth Face Recovery and Fusion Scheme for Heterogeneous Face Recognition,” Representations, Analysis and Recognition of Shape and Motion from Imaging Data, pp. 93–109, 2019, doi: 10.1007/978-3-030-19816-9_8.

Y. Cai, Y. Lei, M. Yang, Z. You, and S. Shan, “A fast and robust 3D face recognition approach based on deeply learned face representation,” Neurocomputing, vol. 363, pp. 375–397, Oct. 2019, doi: 10.1016/j.neucom.2019.07.047.

W. Niu, Y. Zhao, Z. Yu, Y. Liu, and Y. Gong, “Research on a face recognition algorithm based on 3D face data and 2D face image matching,” Journal of Visual Communication and Image Representation, vol. 91, p. 103757, Mar. 2023, doi:10.1016/j.jvcir.2023.103757.

Y. Yu, F. Da, and Z. Zhang, “Few-data guided learning upon end-to-end point cloud network for 3D face recognition,” Multimedia Tools and Applications, vol. 81, no. 9, pp. 12795–12814, Feb. 2022, doi:10.1007/s11042-022-12211-9.