Enhancing Facial Recognition Accuracy in eKYC Systems: A Comparative Evaluation of Euclidean Distance, Cosine Similarity, and SSIM Under Real-World Challenges

Ensuring robust banking security is an ongoing challenge, especially in the face of increasingly sophisticated fraud techniques. One critical aspect is the accuracy of facial recognition technology, which plays a central role in elec-tronic Know Your Customer (eKYC) processes. Inaccurate facial recognition can result in security breaches, allowing fraudsters to exploit vulnerabilities during customer registration and transactions. This issue is particularly signif-icant in Thailand?s banking industry, where reliance on eKYC frameworks is growing. Current facial recognition methods often struggle with false posi-tives, impersonation, and spoofing attacks, threatening the integrity of finan-cial systems. Hence, this paper addresses these concerns by exploring both the limitations of existing face recognition techniques and the opportunities presented by recent advancements in deep learning. The primary goal of this research is to enhance the accuracy of face recognition systems used in eKYC through the integration of advanced algorithms. By refining facial feature extraction methods and employing adaptive learning models, we aim to reinforce the verification process and significantly reduce the risk of fraud.