A Review of Image-Based Monument Identification Using Deep Learning Techniques.

Abstract

Image-based monument identification is very much demanding task due to the variability of lighting conditions, viewpoints, and occlusions. Deep learning-based methods have significantly improved in classifying and recognizing images, and they are now more frequently employed to identify monuments. The current development in deep learning-based monument recognition is given in this literature study paper. The many methods for feature extraction, categorization, and model fine-tuning are described. We also discuss the field\'s limitations and potential developments, including the need for larger, more diversified datasets and the investigation of more sophisticated deep learning methods. Overall, this work offers a thorough summary of the state-of-the-art for deep learning-based image-based monument recognition and provide sustainable growth towards identifying and understanding about ancient historical monument identification.

Introduction

he text discusses the use of deep learning, particularly convolutional neural networks (CNNs), to automate the identification of monuments from images, a task important in tourism, history, and cultural heritage. Manual monument identification is time-consuming and requires expertise, so automated deep learning-based methods can improve accuracy and efficiency.

The literature survey reviews various recent approaches using CNNs, encoder-decoder models, LSTMs, and object detection techniques like Faster R-CNN and YOLO, highlighting achievements such as high classification accuracy (up to ~98%) and improved captioning metrics. Several models are evaluated on different datasets, with future work suggested on mobile applications, larger and more diverse datasets, and enhanced semantic understanding.

Deep learning is characterized by its ability to learn hierarchical data representations automatically, handle raw inputs end-to-end, and scale with computational resources. Transfer learning and challenges such as interpretability, overfitting, and data requirements are also discussed.

Applications of deep learning extend beyond monument recognition into fields like computer vision, NLP, healthcare, finance, autonomous systems, and environmental monitoring.

Popular deep learning frameworks include TensorFlow, PyTorch, Keras, Caffe, and MXNet. The text also addresses key issues like the need for large datasets, high computational costs, interpretability challenges, vulnerability to adversarial attacks, and ethical concerns.

Performance evaluation metrics for monument identification models include accuracy, precision, recall, F1-score, confusion matrices, and ROC-AUC.

Finally, several publicly available landmark image datasets are listed, such as the Google Landmarks Dataset, UNESCO World Heritage Sites Dataset, Flickr Landmark Dataset, and others covering landmarks from cities like Aachen, Rome, and Tokyo.

Conclusion

In conclusion, the survey paper on monument identification from an image using deep learning presents a comprehensive overview of the advancements, methodologies, and challenges in this field. Through an extensive review of relevant literature, several key findings and insights have emerged. Despite the significant progress, there are still challenges and limitations in monument identification from images using deep learning. Overall, the survey article shows the potential of deep learning for identifying monuments from photos and lays the groundwork for more investigation and advancement in this fascinating area. For scholars, practitioners, and stakeholders interested in using deep learning techniques for automated monument recognition and categorization, it is an invaluable resource.

References

[1] Varsha Singh, Km Khushaboo, Vipul Kumar Singh, and Tiwary , U.S., 2023, September. Describing images using CNN and object features with attention. In 2023 International Conference on Information Technologies (InfoTech) (pp. 1-6). IEEE. [2] PreetiVoditel, AparnaGurjar, AakanshaPandey, Akrati Jain, NanditaDubey, “Image Captioning- A Deep Learning Approach using CNN and LSTM Network”, 3rd IEEE Conference on Pervasie Computing and Social Networking(ICPCSN), 2023. [3] ArunkumarGopu, PratyushNishchal, Vishesh Mittal, Kuna Srinidhi, “Image Captioning using Deep Learning Techniques”, IEEE International Conference on Contemporary Computinh and Communications(InC4), 2023. [4] YuktaNagpal ,Varun Jindal , VinayKukreja , Satvik Vats , Rishabh Sharma , “Deep Learning Multiclassification Model: Recognizing Monuments”. Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS 2023) IEEE Xplore Part Number : CFP23CB2-ART ; ISBN : 979-8-3503-2579-9, 2023. [5] Satish Kumar Satti , Goluguri N V Rajareddy , Prasad Maddula , N V VishnumurthyRavipati , “Image Caption Generation using ResNET-50 and LSTM”, IEEE Silchar Subsection Conference, 2023. [6] Chandradeep Bhatt , SumitRai , Rahul Chauhan , DeepikaDua , Mukesh Kumar , Sanjay Sharma , “Deep Fusion: A CNN-LSTM Image Caption Generator for Enhanced Visual Understanding”, 3rd International Conference on Innovative Sustainable Computational Technologies.2023. [7] Himanshu Sharma, DevanandPadha, “From Templates to Transformers: A Survey of Multimodal Image Captioning Decoders”, IEEE International Conference on Sustainable Energy and Future Electric Transportation, 2022. [8] Anoopa S, Salim A, “Comparison of Faster RCNN and YOLO V3 for Video Anomaly Localization”, IEEE International Conference on Power, Instrumentation, control and computing,2023. [9] FatmaNur ORTATAS, Emrah CETIN, “Lane Tracking with Deep Learning: Mask RCNN and Faster RCNN”, IEEE International Conference on Contemporary Computing and Communications, 2022. [10] Padmashree Desai, JagadeeshPujari, N.H.Ayachit. Classification of Archaeological Monuments for Different Art forms with an Application to CBIR, IEEE International Conference on Advances in Computing, communications and Informatics (ICACCI), IEEE, pp. no. 1108- 1112, 2013. [11] AradhyaSaini, Tanu Gupta, Rajat Kumar, Akshay Kumar Gupta,MonikaPanwar, Ankush Mittal. Image based Indian Monument Recognition using Convoluted Neural Networks, IEEE International Conference on Big Data, IoT and Data Science (BID) Vishwakarma Institute of Technology, Pune, pp.no. 138-142, Dec 20-22, 2017. https://doi.org/10.1109/BID.2017.8336587. [12] SiddhantGada, Viraj Mehta, Karan Kanchan, Chahat Jain, PurvaRaut. Monument Recognition using Deep Neural Networks. IEEE International Conference on Computational Intelligence and Computing Research 2017. [13] JaimalaJha, Sarita Singh Bhaduaria. A Novel approach for Retrieval of Historical Monuments Images using Visual Contents and Unsupervised Machine Learning. International Journal of Advanced Trends in Computer Science and Engineering Volume 9, No.3, May - June 2020. [14] Ronak Gupta, Prerana Mukherjee, BrejeshLall, Varshul Gupta. Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments. SUMAC’20, October 12, 2020, Seattle, WA, USA © 2020 Association for Computing Machinery. [15] ShahdHesham, RawanKhaled, Dalia Yasser, Samira Refaat, Nada Shorim, FatmaHelmy Ismail. Monuments Recognition using Deep Learning VS Machine Learning. IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC) | 978-1-6654-1490- 6/21/$31.00 ©2021 IEEE | DOI: 10.1109/CCWC51732.2021.9376029. [16] V. Palma. Towards Deep Learning For Architecture: A Monument Recognition Mobile App. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLII-2/W9, 2019. [17] Ravi Devesh and JaimalaJha. An Efficient Approach for Monuments Image Retrieval Using Multi-visual Descriptors. Proceeding of the Second International Conference on Microelectronics, Computing & Communication Systems Springer Nature Singapore Pte Ltd. 2019. [18] M. Trivedia, S. Agrawala, A. Kumara, S. K. Thakura, and N. Gautama. Indian Monument Recognition using Deep Learning, Article in ECS Transactions • April 2022 DOI: 10.1149/10701.15563ecst. [19] SowjanyaJindam, JaiminiKeerthanMannem, MeenaNenavath, VineelaMunigala. Heritage Identification of Monuments using Deep Learning Techniques. Indian Journal of Image Processing and Recognition (IJIPR) ISSN: 2582-8037 (Online), Volume-3 Issue-4, June 2023. [20] NehaHimesh, Shriya R, Gowthami PN, BenishRoshan. Indian Monument Recognition using CNN Algorithm. Journal of Emerging Technologies and Innovative Research (JETIR), 2019 JETIR May 2019, Volume 6, Issue 5. [21] Malay S.Bhatt, Tejas P. Patalia. Genetic Programming Evolved Spatial Descriptor for Indian Monuments Classification. IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS) 2015. [22] TanviSahay, Ankita Mehta. Architecture Classification for Indian Monuments. publication at: https://www.researchgate.net/publication/334045053

Copyright

Copyright © 2025 Praveen N, Vidya A. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.