Optimizasyon Algoritmaları ile MagFace Yüz Tanıma Modelinden Özellik Seçimi

Yıl 2023, Cilt: 35 Sayı: 2, 561 - 567, 01.09.2023

Mehmet Fatih Ozdemır , Davut Hanbay

https://doi.org/10.35234/fumbd.1233505

Öz

Son yıllarda gelişen donanımlarla birlikte literatürde yapay zeka alanında birçok çalışma yapılmaktadır. Bu gelişmeler arasında yüz tanıma algoritmaları önemli bir yere sahiptir. Yüz tanıma algoritmaları arasında ise en başarılı olanları genellikle derin öğrenme yaklaşımlarıdır. SphereFace, CosFace, ArcFace, MagFace gibi modeller literatürde yer alan önemli derin öğrenme modelleridir. Derin öğrenme modelleri başarılarının aksine genellikle hesaplama açısından maliyetlidir. Bu nedenle, bu modeller için hesaplama yükünü azaltacak gelişmiş yöntemlere ihtiyaç duyulmaktadır. Bunun için en geçerli yöntemlerden biri gömülü yüz öznitelikleri arasından en değerli olanı seçmektir. Böylece maliyet düşürülebilir hatta başarı değerleri daha da arttırılabilir. Bu çalışmada PSO, GA, SCA, DE optimizasyon algoritmaları kullanılarak MagFace 512 gömülü özelliklerinin en değerlileri elde edilmeye çalışılmıştır. Sonuç olarak LFW, CFP, AGEDB veri setlerinde seçilen değerli 193, 252, 280 öznitelikleri sırasıyla 99.83, 98.57, 98.65 doğruluk değerlerine ulaşılmıştır.

Anahtar Kelimeler

Yüz Tanıma, Öznitelik Seçimi, Optimizasyon

Feature Selection From MagFace Face Recognition Model With Optimization Algorithms

Öz

In recent years, many studies have been carried out in the field of artificial intelligence in the literature with the development of equipment. Face recognition algorithms have an important place among these developments. Among the face recognition algorithms, the most successful ones are usually deep learning approaches. Models such as SphereFace, CosFace, ArcFace, and MagFace are important deep learning models in the literature. Despite their success, deep learning models are often computationally costly. Therefore, advanced methods are needed to reduce the computational load for these models. One of the most valid methods for this is to choose the most valuable one among embedding features for face recognition. Thus, cost can be reduced, and accuracy values can be increased even more. In this study, the most valuable of the 512 embedded features in the MagFace model was tried to be obtained by using PSO, GA, SCA, and DE optimization algorithms. As a result, accuracy values of 99.83%, 98.57%, and 98.65% were reached for 193, 252, and 280 features selected in the LFW, CFP, and AGEDB datasets, respectively.

Anahtar Kelimeler

Face Recognition, Feature Selection, Optimization

Kaynakça

• Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, and Le Song. Sphereface:Deep hypersphere embedding for face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 212–220, 2017.
• Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. Cosface: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5265–5274, 2018.
• Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4690–4699, 2019.
• Qiang Meng, Shichao Zhao, Zhida Huang, and Feng Zhou. Magface: A universal representation for face recognition and quality assessment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14225–14234, 2021.
• Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. Learning face representation from scratch. arXiv preprint arXiv:1411.7923, 2014.
• Gary B Huang, Marwan Mattar, Tamara Berg, and Eric Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. In Workshop on faces in’Real-Life’Images: detection, alignment, and recognition, 2008.
• Lior Wolf, Tal Hassner, and Itay Maoz. Face recognition in unconstrained videos with matched background similarity. In CVPR 2011, pages 529–534. IEEE, 2011.
• Ira Kemelmacher-Shlizerman, Steven M Seitz, Daniel Miller, and Evan Brossard. The megaface benchmark: 1 million faces for recognition at scale. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4873–4882, 2016.
• James Kennedy and Russell Eberhart. Particle swarm optimization. In Proceedings of ICNN’95-international conference on neural networks, volume 4, pages 1942–1948. IEEE, 1995.
• John H Holland. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press, 1992.
• Seyedali Mirjalili. SCA: A Sine Cosine Algorithm for solving optimization problems. Knowledge-Based Systems, 96:120– 133, March 2016.
• Rainer Storn and Kenneth Price. Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization, 11(4):341–359, 1997.
• Grega Vrbancˇicˇ, Lucija Brezocˇnik, Uroš Mlakar, Dušan Fister, and Iztok Fister Jr. NiaPy: Python microframework for building nature-inspired algorithms. Journal of Open Source Software, 3, 2018.
• Soumyadip Sengupta, Jun-Cheng Chen, Carlos Castillo, Vishal M. Patel, Rama Chellappa, and David W. Jacobs. Frontal to profile face verification in the wild. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1–9, 2016.
• Stylianos Moschoglou, Athanasios Papaioannou, Christos Sagonas, Jiankang Deng, Irene Kotsia, and Stefanos Zafeiriou. Agedb: The first manually collected, in-the-wild age database. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 1997–2005, 2017.