This study presents an innovative approach to enhance facial recognition technology using contrastive convolutional neural networks (CNNs). The primary focus is on improving the accuracy and efficiency of face recognition systems under varying conditions. Key elements of this approach include meticulous data preparation and preprocessing, where images undergo normalization and diverse augmentation techniques to ensure quality inputs. The network architecture is designed to process pairs of face images, utilizing a common feature extractor and cascaded convolution layers for detailed feature representation. A specialized kernel generator further refines the process, emphasizing unique facial characteristics. The core of the training regimen is a contrastive loss function, optimized through gradient descent to enhance the network's discriminatory capabilities. Results from the study demonstrate a significant improvement in recognition accuracy, particularly highlighted by the superior performance of the proposed model in comparison to standard facial recognition algorithms. This research provides a comprehensive methodology that could revolutionize face recognition technology, offering more reliable and efficient solutions for various applications.

Facial recognition, contrastive convolution, neural networks

Agzamova M.Sh. Development of a software module implementing a proposed facial biometric authentication algorithm and evaluation of solution effectiveness. SCIENCE AND INNOVATION INTERNATIONAL SCIENTIFIC JOURNAL VOLUME 2 ISSUE 7 JULY 2023, pp. 51-57, https://doi.org/10.5281/zenodo.81507542.

Agzamova M.Sh., Irgasheva D.Y. Analysis of non-cryptographic methods for software binding to facial biometric data of user identity. International Journal of Advance Scientific Research, 3(07), 38–47. https://doi.org/10.37547/ijasr-03-07-08.

Agzamova Mohinabonu. 2023. “Emotion recognition through advanced neural architectures: a comprehensive analysis”. International Scientific and Current Research Conferences 1 (01):29-31. https://orientalpublication.com/index.php/iscrc/article/view/1194

Agzamova Mohinabonu. 2023. “Contrastive convolution in face recognition: advancements in accuracy”. Next Scientists Conferences 1 (01):3-5. https://nextscientists.com/index.php/science-conf/article/view/135.

Agzamova M.Sh., Irgasheva D.Y. A comprehensive review of the use of data mining algorithms in facial recognition systems for payment systems. Bulletin of TUIT: Management and Communication Technologies № 3(12)2023.

Chenqian Yan, Yuge Zhang, Quanlu Zhang, Yaming Yang, Xinyang Jiang, Yuqing Yang, Baoyuan Wang. Privacy-preserving Online AutoML for Domain-Specific Face Detection. URL: https://openaccess.thecvf.com/content/CVPR2022/papers/Yan_Privacy-Preserving_Online_AutoML_for_Domain-Specific_Face_Detection_CVPR_2022_paper.pdf

Yang Liu, Fei Wang, Jiankang Deng, Zhipeng Zhou, Baigui Sun, Hao Li. MogFace: Towards a Deeper Appreciation on Face Detection. URL: https://openaccess.thecvf.com/content/CVPR2022/papers/Liu_MogFace_Towards_a_Deeper_Appreciation_on_Face_Detection_CVPR_2022_paper.pdf

Roberto Pecoraro, Valerio Basile, Viviana Bono, Sara Gallo. Local Multi-Head Channel Self-Attention for Facial Expression Recognition. URL: https://arxiv.org/pdf/2111.07224v2.pdf

Kai Wang, Xiaojiang Peng, Jianfei Yang, Debin Meng, Yu Qiao. Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition. URL: https://arxiv.org/pdf/1905.04075v2.pdf

Andrey V. Savchenko. Facial expression and attributes recognition based on multi-task learning of lightweight neural networks. URL: https://ieeexplore.ieee.org/abstract/document/9582508/authors#authors

11. Minchul Kim, Anil K. Jain, Xiaoming Liu. AdaFace: Quality Adaptive Margin for Face Recognition. URL: https://arxiv.org/pdf/2204.00964.pdf