Convolutional neural networks in face detection and recognition systems
Keywords:
convolutional neural networks, face recognition, face detection, face alignment, network architectures, computer visionAbstract
The article discusses the application of convolutional neural networks at different stages of face recognition systems: detection, alignment and recognition. The key architectures and methods used in each stage are reviewed. Multitasking CNNs that perform multiple functions simultaneously are described. Current development trends are highlighted: the application of attention mechanisms, transformers, and learning from small data.
References
Федяев, О. И. Автоматическая регистрация присутствия студентов на учебном занятии с помощью компьютерного зрения / О. И. Федяев, И. А. Коломойцева // XXI Национальная конференция по искусственному интеллекту с международным участием КИИ-2023 (Смоленск, 16-20 октября 2023 г.). Труды конференции. В 2-х томах. Т.1. – Смоленск: Принт-Экспресс, 2023. – С. 294-303.
Du L., Zhang R., Wang X. Overview of two-stage object detection algorithms //Journal of Physics: Conference Series. – IOP Publishing, 2020. – Т. 1544. – №. 1. – С. 012033.
Zhang Y. et al. A comprehensive review of one-stage networks for object detection //2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC). – IEEE, 2021. – С. 1-6.
Zhang N., Luo J., Gao W. Research on face detection technology based on MTCNN //2020 international conference on computer network, electronic and automation (ICCNEA). – IEEE, 2020. – С. 154-158.
Deng J. et al. Retinaface: Single-shot multi-level face localisation in the wild //Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. – 2020. – С. 5203-5212.
Wang X., Bo L., Fuxin L. Adaptive wing loss for robust face alignment via heatmap regression //Proceedings of the IEEE/CVF international conference on computer vision. – 2019. – С. 6971-6981.
Sam S. M. et al. Offline signature verification using deep learning convolutional neural network (CNN) architectures GoogLeNet inception-v1 and inception-v3 //Procedia Computer Science. – 2019. – Т. 161. – С. 475-483.
Zhang X. et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices //Proceedings of the IEEE conference on computer vision and pattern recognition. – 2018. – С. 6848-6856.
Alzubaidi L. et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions //Journal of big Data. – 2021. – Т. 8. – С. 1-74.
Holkar A., Walambe R., Kotecha K. Few-shot learning for face recognition in the presence of image discrepancies for limited multi-class datasets //Image and Vision Computing. – 2022. – Т. 120. – С. 104420.
