A New Facial Image Deviation Estimation and Image Selection Algorithm (Fide-Isa) for Facial Image Recognition Systems: The Mathematical Models

Hassan Opotu Siyaka, Olumide Owolabi, Bisallah I. H.

Abstract


Deep learning models have been successful and shown to perform better in terms of accuracy and efficiency for facial recognition applications. However, they require a huge amount of data samples that were well annotated to be successful. Their data requirements have led to some complications which include increased processing demands of the systems where such systems were to be deployed. Reducing the training sample sizes of deep learning models is still an open problem. This paper proposes the reduction of the number of samples required by the convolutional neural network used in training a facial recognition system using a new Facial Image Deviation Estimation and Image Selection Algorithm (FIDE-ISA). The algorithm was used to select appropriate facial image training samples incrementally based on their facial deviation. This will reduce the need for a huge dataset in training deep learning models. The experiment was implemented using MATLAB R2020a in a system with a 2.6 GHz processing speed. Preliminary results indicated a 100% accuracy for models trained with 54 images (at least 3 images per individual) and above.


Full Text:

PDF

References


Alhayani, B. S. A., & Rane, M. (2014) face recognition system by image processing. International Journal of Electronics and Communication Engineering & Technology (IJECET), ISSN 0976 – 6464(Print), ISSN 0976 – 6472(Online), 5, (5), pp. 80-90 © IAEME

Almabdy, S., & Elrefaei, L. (2019). Deep convolutional neural network-based approaches for face recognition. Applied Sciences (Switzerland), 9(20). https://doi.org/10.3390/app9204397

Alqadi, Z., Khrisat, M., Dwairi, M., & Khawatreh, S. (2020). Building Face Recognition System (FRS ). 9(June), 15–24.

Arafah, M., Achmad, A., Indrabayu, & Areni, I. S. (2020). Face Identification System Using Convolutional Neural Network for Low Resolution Image. 2020 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2020 - Proceedings, 55–60. https://doi.org/10.1109/Comnetsat50391.2020.9328967

Coskun, M., Ucar, A., Yildirim, O., & Demir, Y. (2017). Face recognition based on convolutional neural network. Proceedings of the International Conference on Modern Electrical and Energy Systems, MEES 2017, 2018-Janua(January 2018), 376–379. https://doi.org/10.1109/MEES.2017.8248937

Filippidou, F. P., & Papakostas, G. A. (2020). Single Sample Face Recognition Using Convolutional Neural Networks for Automated Attendance Systems. 4th International Conference on Intelligent Computing in Data Sciences, ICDS 2020. https://doi.org/10.1109/ICDS50568.2020.9268759

Ling, H., Wu, J., Huang, J., Chen, J., & Li, P. (2020). Attention-based convolutional neural network for deep face recognition. Multimedia Tools and Applications, 79(9–10), 5595–5616. https://doi.org/10.1007/s11042-019-08422-2

Marsot, M., Mei, J., Shan, X., Ye, L., Feng, P., Yan, X., Li, C., & Zhao, Y. (2020). An adaptive pig face recognition approach using Convolutional Neural Networks. Computers and Electronics in Agriculture, 173. https://doi.org/10.1016/j.compag.2020.105386

Nagpal, S., Singh, M., Singh, R., & Vatsa, M. (2019). Deep learning for face recognition: Pride or prejudiced? ArXiv, July.

Ogbuju, E., Adetayo, A. P., & Obilikwu, P. (2020). A Face Recognition System for Attendance Record in a Nigerian University. Journal of Scientific Research and Development, 19(June), 38–45.

Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015). Deep Face Recognition. Section 3, 41.1-41.12. https://doi.org/10.5244/c.29.41

Pei, Z., Xu, H., Zhang, Y., Guo, M., & Yee-Hong, Y. (2019). Face recognition via deep learning using data augmentation based on orthogonal experiments. Electronics (Switzerland), 8(10), 1–16. https://doi.org/10.3390/electronics8101088

Peng, X., Ratha, N., & Pankanti, S. (2016). Learning face recognition from limited training data using deep neural networks. Proceedings - International Conference on Pattern Recognition, 0, 1442–1447. https://doi.org/10.1109/ICPR.2016.7899840

Siyaka, O. H., Owolabi, O. & Hashim, B. I. (2021) A Novel Facial Image Deviation Estimation and Image Selection Algorithm (Fide-Isa) for Training Data Reduction in Facial Recognition System. Journal of Science Technology and Education, ATBU Bauchi. 9 (2), June 2021. ISSN: 2277-0011; Journal homepage: www.atbuftejoste.com

Swapna, M., Sharma, Y. K., & Prasad, B. M. G. (2020). A Survey on Face Recognition Using Convolutional Neural Network. Advances in Intelligent Systems and Computing, 1079, 649–661. https://doi.org/10.1007/978-981-15-1097-7_54

Tao, K., He, Y., & Chen, C. (2019). Design of Face Recognition System Based on Convolutional Neural Network. Proceedings - 2019 Chinese Automation Congress, CAC 2019, 5403–5406. https://doi.org/10.1109/CAC48633.2019.8996236

Tuncer, T., Dogan, S., Abdar, M. & Paweł Pławiak, P. (2020). A novel facial image recognition method based on perceptual hash using quintet triple binary pattern. Multimedia Tools and Applications (2020) 79:29573–29593

Vinay, A., Gupta, A., Bharadwaj, A., Srinivasan, A., Murthy, K. & Natarajan, S. (2018) Deep Learning on Binary Patterns for Face Recognition. International Conference on Computational Intelligence and Data Science (ICCIDS 2018). Procedia Computer Science 132 (2018) 76–83. http://dx.doi.org/10.1016/j.procs.2018.05.164. Retrieved June 14, 2021.


Refbacks

  • There are currently no refbacks.