Indian heritage monuments identification Using deep learning methodologies

Abstract

Abstract—India is home to a rich cultural heritage, with thousands of monuments that span several centuries and styles. Identifying and classifying these monuments is a challenging task, requiring expertise and knowledge of architecture, history, and art. In this paper, we propose a deep learning-based approach to automatically identify Indian heritage monuments from images. We use a dataset of over 10,000 images of Indian monuments and train several convolutional neural network models to classify them into 20 categories based on architectural styles, regions, and time periods. We achieve an overall accuracy of 92.3% on a held-out test set, outperforming several baseline models and human experts. We also develop a web-based interface that allows users to upload images and receive predictions from the model in real-time. Our results demonstrate the feasibility and effectiveness of using deep learning techniques for identifying Indian heritage monuments, with potential applications in tourism, education, and cultural preservation.