Building Su Viet website integrating ai for recognizing vietnamese historical figures

Abstract

This study develops the “Su Viet” website integrated with AI to recognize Vietnamese historical figures through real and synthetic images. Addressing the limited availability of authentic historical images, we employ advanced image augmentation techniques, including image mixing, diffusion, and generative models, to create diverse and realistic representations of these figures. A ResNet-50 model is then trained to accurately identify and classify historical figures based on the augmented dataset. The model achieves an accuracy of 89.74% and an F1-Score of 89.37%, demonstrating that combining AI with innovative augmentation methods significantly enhances the accuracy and robustness of historical figure recognition. The website provides interactive learning tools, promoting historical education and digital heritage preservation.