Comparative Analysis of VGG-16 and ResNet-50 for Occluded Ear Recognition

Hua-Chian Tey - Multimedia University, Melaka, Malaysia
Lee Ying Chong - Multimedia University, Melaka, Malaysia
Siew-Chin Chong - Multimedia University, Melaka, Malaysia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.7.4.2276

Abstract


Occluded ear recognition is a challenging task in biometric systems due to the presence of occlusions that can hinder accurate identification. There is still a research gap in enhancing the robustness of deep learning to handle severities of occlusions with different datasets. This research focuses on developing a robust occluded ear recognition system by implementing fine-tuning techniques on three popular pre-trained deep learning models, Residual Neural Network (ResNet-50), Visual Geometry Group (VGG-16), and EfficientNet. The system is evaluated on two manually occluded ear datasets, which are the AMI ear dataset and the IITD ear dataset. The experiment results showed the fine-tuned ResNet-50 model performs better than the fine-tuned VGG-16 model. The results indicate that the model's ability to accurately predict the classes or labels decreases as more data is occluded. Higher occlusion rates lead to a loss of important information, making it more challenging for the model to distinguish between different patterns and make accurate predictions. According to the findings, the amount of occlusion influenced the identification accuracy and worsened as the occlusion became larger. In the future, ear recognition systems will likely continue to improve in accuracy and be adopted by a wider range of organizations and industries. They may also be integrated with other biometric technologies and used for personalization purposes. However, ethical considerations related to the use of ear recognition systems will also need to be addressed.


Keywords


Occluded ear; fine-tune; ResNet-50; VGG-16; EfficientNet

Full Text:

PDF

References


A. Kavipriya and A. Muthukumar, "Human Age Estimation based on Ear Biometrics using KNN," in 2019 IEEE International Conference on Clean Energy and Energy Efficient Electronics Circuit for Sustainable Development (INCCES), 2019, pp. 1–5. doi: 10.1109/INCCES47820.2019.9167706.

X. Xu, Y. Liu, C. Liu, and L. Lu, "A Feature Fusion Human Ear Recognition Method Based on Channel Features and Dynamic Convolution," Symmetry (Basel), vol. 15, no. 7, 2023, doi: 10.3390/sym15071454.

V. Nazmdeh, S. Mortazavi, D. Tajeddin, H. Nazmdeh, and M. M. Asem, "Iris recognition; From classic to modern approaches," 2019 IEEE 9th Annual Computing and Communication Workshop and Conference, CCWC 2019, pp. 981–988, Mar. 2019, doi: 10.1109/CCWC.2019.8666516.

W.-H. Chuah, C. Chin, and L.-Y. Chong, "The Assistance of Eye Blink Detection for Two- Factor Authentication," Journal of Informatics and Web Engineering, vol. 2, pp. 111–121, Sep. 2023, doi: 10.33093/jiwe.2023.2.2.8.

L. F. Nakayama et al., "Retinal Scans and Data Sharing: The Privacy and Scientific Development Equilibrium," Mayo Clinic Proceedings: Digital Health, vol. 1, no. 2, pp. 67–74, 2023, doi: 10.1016/j.mcpdig.2023.02.003.

L. Markićević, P. Peer, and Ž. Emeršič, "Improving Ear Recognition with Super-resolution," in 2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP), 2023, pp. 1–5. doi: 10.1109/IWSSIP58668.2023.10180250.

M. M. Zarachoff, A. Sheikh-Akbari, and D. Monekosso, "Multi-band PCA based ear recognition technique," Multimed Tools Appl, vol. 82, no. 2, pp. 2077–2099, Jan. 2023, doi: 10.1007/S11042-022-12905-0.

J. Jeyabharathi, S. Devi, B. Krishnan, R. Samuel, M. I. Anees, and R. Jegadeesan, "Human Ear Identification System Using Shape and structural feature based on SIFT and ANN Classifier," 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), 2022, doi: 10.1109/IC3IOT53935.2022.9767893.

R. Mehta, A. Sheikh-Akbari, and K. K. Singh, "A Noble Approach to 2D Ear Recognition System using Hybrid Transfer Learning," 2023 12th Mediterranean Conference on Embedded Computing (MECO), pp. 1–5, Jun. 2023, doi: 10.1109/MECO58584.2023.10154993.

M. Sharkas, "Ear recognition with ensemble classifiers; A deep learning approach," Multimed Tools Appl, vol. 81, no. 30, pp. 43919–43945, Dec. 2022, doi: 10.1007/S11042-022-13252-W.

R. Ahila Priyadharshini, S. Arivazhagan, and M. Arun, "A deep learning approach for person identification using ear biometrics," Applied Intelligence, vol. 51, no. 4, pp. 2161–2172, 2021, doi: 10.1007/s10489-020-01995-8.

Y. Lei, J. Qian, D. Pan, and T. Xu, "Research on Small Sample Dynamic Human Ear Recognition Based on Deep Learning," Sensors, vol. 22, no. 5, 2022, doi: 10.3390/s22051718.

R. Mehta, A. Sheikh-Akbari, and K. K. Singh, "A Noble Approach to 2D Ear Recognition System using Hybrid Transfer Learning," in 2023 12th Mediterranean Conference on Embedded Computing (MECO), 2023, pp. 1–5. doi: 10.1109/MECO58584.2023.10154993.

D. Fitousi, N. Rotschild, C. Pnini, and O. Azizi, "Understanding the Impact of Face Masks on the Processing of Facial Identity, Emotion, Age, and Gender," Front Psychol, vol. 12, p. 4668, Nov. 2021, doi: 10.3389/FPSYG.2021.743793/BIBTEX.

D. Maltoni, D. Maio, A. K. Jain, and J. Feng, "Handbook of fingerprint recognition: Third edition," Handbook of Fingerprint Recognition: Third Edition, pp. 1–522, Jul. 2022, doi: 10.1007/978-3-030-83624-5.

J. Patmanee, S. Kanprachar, and K. Chamnongthai, "Effects of Preprocessing in Person Identification Using Ear Features," in 2021 25th International Computer Science and Engineering Conference (ICSEC), 2021, pp. 443–447. doi: 10.1109/ICSEC53205.2021.9684602.

K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," 2015, Accessed: Dec. 26, 2022. [Online]. Available: http://image-net.org/challenges/LSVRC/2015/

K. Simonyan and A. Zisserman, "VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION," 2015, Accessed: May 29, 2023. [Online]. Available: http://www.robots.ox.ac.uk/

M. Tan and Q. V Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proceedings of the 36th International Conference on Machine Learning, vol. 97, pp. 6105-6114, 2019, doi: 10.48550/arXiv.1905.11946.

S. Mhadgut, "Masked Face Detection and Recognition System in Real Time using YOLOv3 to combat COVID-19," 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2021, doi: 10.1109/ICCCNT51525.2021.9579525.

J. S. Talahua, J. Buele, P. Calvopina, and J. Varela-Aldas, "Facial Recognition System for People with and without Face Mask in Times of the COVID-19 Pandemic," Sustainability, vol. 13, no. 12, Jun. 2021, doi: 10.3390/SU13126900.

S. Dharanesh and A. Rattani, "Post-COVID-19 Mask-Aware Face Recognition System," 2021 IEEE International Symposium on Technologies for Homeland Security (HST), 2021, doi: 10.1109/HST53381.2021.9619841.

V. K. Kaliappan, R. Thangaraj, P. Pandiyan, K. Mohanasundaram, S. Anandamurugan, and D. Min, "Real-time face mask position recognition system using YOLO models for preventing COVID-19 disease spread in public places," Int. J. Ad Hoc Ubiquitous Comput., vol. 42, no. 2, pp. 73–82, 2023, doi: 10.1504/IJAHUC.2023.10053539.

A. Balmik, A. Kumar, and A. Nandy, "Efficient Face Recognition System for Education Sectors in COVID-19 Pandemic," 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2021, doi: 10.1109/ICCCNT51525.2021.9579523.

L. Yuningsih, G. A. Pradipta, D. P. Hostiadi, R. R. Huizen, and P. D. W. Ayu, "Ear Feature Extraction Methods - A Review," in 2022 4th International Conference on Cybernetics and Intelligent System (ICORIS), 2022, pp. 1–5. doi: 10.1109/ICORIS56080.2022.10031264.

R. D. Balangue, C. D. M. Padilla, N. B. Linsangan, J. P. T. Cruz, R. A. Juanatas, and I. C. Juanatas, "Ear Recognition for Ear Biometrics Using Integrated Image Processing Techniques via Raspberry Pi," in 2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), 2022, pp. 1–6. doi: 10.1109/HNICEM57413.2022.10109479.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks", Accessed: Sep. 03, 2023. [Online]. Available: http://code.google.com/p/cuda-convnet/

H. Alshazly, C. Linse, E. Barth, S. A. Idris, and T. Martinetz, "Towards Explainable Ear Recognition Systems Using Deep Residual Networks," IEEE Access, vol. 9, pp. 122254–122273, 2021, doi: 10.1109/ACCESS.2021.3109441.

M. Sharkas and M. Tools, "Ear recognition with ensemble classifiers; A deep learning approach," 2022, doi: 10.1007/s11042-022-13252-w.

Z. Wang, · Xiong Gao, J. Yang, Q. Yan, and Y. Zhang, "Local feature fusion and SRC-based decision fusion for ear recognition," Multimed Syst, vol. 28, pp. 1117–1134, 2022, doi: 10.1007/s00530-022-00906-w.

L. Tian and Z. Mu, "Ear recognition based on deep convolutional network," Proceedings - 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2016, pp. 437–441, Feb. 2017, doi: 10.1109/CISP-BMEI.2016.7852751.

M. Sultana, P. P. Paul, and M. Gavrilova, "A Novel Index-Based Rank Fusion Method for Occluded Ear Recognition," Proceedings - 2015 International Conference on Cyberworlds, CW 2015, pp. 337–344, Feb. 2016, doi: 10.1109/CW.2015.30.

A. Kumar and C. Wu, "Automated human identification using ear imaging," 2011, doi: 10.1016/j.patcog.2011.06.005.

S. Ramos-Cooper and G. Camara-Chavez, "Ear Recognition In The Wild with Convolutional Neural Networks," in 2021 XLVII Latin American Computing Conference (CLEI), 2021, pp. 1–10. doi: 10.1109/CLEI53233.2021.9640083.