Classification and Identification of Ancient Indian Temple Pillars Era Using Deep Learning
Keywords:
Pillar Architecture, Transfer learning, Auto-Segmentation, Classification, Convolutional Neural Networks, Identification, Deep Learning, Pillar Time-line.Abstract
The historic Indian temples have endured for several millennia and are linked to notable dynasties in power. The pillars of style, architecture, sculpture, and techniques in this environment each display amazing marvels of their own. Currently, classification and identification of pillars time-line depend on human visual talents, even if many of the characteristics related to this activity are small and difficult to understand. Archaeologists have several complex obstacles throughout this process because there are no dependable digital methods for the scientific classification and identification of pillars time-line. Recently, a number of machine learning algorithms have been presented to automate the segmentation and recognition of pillars. Notably, the field of archaeology has benefited greatly from the application of deep learning. The current study utilizes advanced deep learning models that employ a transfer learning approach to perform classification and identification of pillars time-line. The own prepared dataset has 1030 pillar images categorized according to the time-line based on the Potika type/architecture level. These categories includes Pillar time-lines as 4th to 8th BC, 5th to 9th BC, 9th to 12th to 13th BC , 11th to 13th to 14th BC, 15th to 16th BC and 16th BC Onwards. In this current research, we use cutting-edge transfer learning deep learning models for pillar timeline classification and identification. This research employs five deep learning convolutional neural network (CNN) models, namely DenseNet121, VGG16, InceptionV3, MobileNetV2, and Xception, to diagnose and classify pillars time-line. The average pillar timeline identification efficiency was 92.00%, 90.33%, 89.17%, 87.83%, and 85.17% for all five models respectively. On the ancient temple pillar time-line dataset, DenseNet121 beat VGG16, InceptionV3, MobileNetV2, and Xception CNN models in classification accuracy and computational efficiency.
Downloads
References
Free, J. P., & Vos, H. F. (1992). Archaeology and Bible history. Zondervan.
Ceram, C. W. Gods, Graves & Scholars. Victor Gollancz & Sidgwick & Jackson, London, 1954.
Kumar, M. (2018). Pillars (Stambh)-The Supportive Elements of Hindu Temples. International journal of current research, 10(06), 70223-70228.
Mohana, H. S., & Rajithkumar, B. K. (2014, July). Era identification and recognition of Ganga and Hoysala phase Kannada stone inscriptions characters using advance recognition algorithm. In 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT) (pp. 659-665). IEEE.
Bhatt, M. S., & Patalia, T. P. (2015, November). Genetic programming evolved spatial descriptor for Indian monuments classification. In 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS) (pp. 131-136). IEEE.
Jethale, A., Nath, N. V., Arawkar, T., Bajpeyi, A., & Nirwal, D. (2018). Monument Informatica: A Tour based Guide system using Real Time Monument Recognition. Research Journal of Engineering and Technology, 9(4), 373-379.
Grishkin, V., Kovshov, A., Schigorec, S., Vlasov, D., Zhabko, A., & Iakushkin, O. (2015, October). A system for the recognition of biofouling on the surface of the monuments of cultural heritage. In 2015 International Conference" Stability and Control Processes" in Memory of VI Zubov (SCP) (pp. 630-633). IEEE.
Gurudev S. Hiremath, Narendra Kumar S, Shrinivasa Naika C. L.(2023, March).A Study on Ancient Temple Structural Elements Recognition Using Genetic Algorithm, In International Journal of Engineering and Manufacturing (IJEM), Vol.13, No.3, pp. 34-47.
Jayanthi, J., & Maheswari, P. U. (2024). Comparative study: enhancing legibility of ancient Indian script images from diverse stone background structures using 34 different pre-processing methods. Heritage Science, 12(1), 63.
Fuentes-Carbajal, J. A., Carrasco-Ochoa, J. A., Martínez-Trinidad, J. F., & Flores-López, J. A. (2023). Machine learning and image-processing-based method for the detection of archaeological structures in areas with large amounts of vegetation using satellite images. Applied Sciences, 13(11), 6663.
Hamplová, A., Lyavdansky, A., Novák, T., Svojše, O., Franc, D., & Veselý, A. (2024). Instance Segmentation of Characters Recognized in Palmyrene Aramaic Inscriptions. CMES-Computer Modeling in Engineering & Sciences, 140(3).
Gao, J., Giunchiglia, F., Zhao, T., Li, C., & Xu, H. A Cross-Scenes Ancient Character Recognition Model Based on Normalized Generator and Transformer Encoder in Computational Archaeology. Available at SSRN 4741242.
Rangkuti, A. H., Athala, V. H., Indallah, F. H., Tanuar, E., & Kerta, J. M. (2023). Optimization of Historic Buildings Recognition: CNN Model and Supported by Pre-processing Methods. JOIV: International Journal on Informatics Visualization, 7(4), 2230-2239.
Bhuvaneswari, S., & Kathiravan, K. (2024). Enhancing epigraphy: a deep learning approach to recognize and analyze Tamil ancient inscriptions. Neural Computing and Applications, 36(31), 19839-19861.
Danese, M., Gioia, D., Vitale, V., Abate, N., Amodio, A. M., Lasaponara, R., & Masini, N. (2022). Pattern recognition approach and liDAR for the analysis and mapping of archaeological looting: application to an etruscan site. Remote Sensing, 14(7), 1587.
Narang, S. R., Kumar, M., & Jindal, M. K. (2021). DeepNetDevanagari: a deep learning model for Devanagari ancient character recognition. Multimedia Tools and Applications, 80, 20671-20686.
Desai, P., Pujari, J., Ayachit, N. H., & Prasad, V. K. (2013, August). Classification of archaeological monuments for different art forms with an application to CBIR. In 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 1108-1112). IEEE.
Bhatt, M. S., & Patalia, T. P. (2015, November). Genetic programming evolved spatial descriptor for Indian monuments classification. In 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS) (pp. 131-136). IEEE.
Bhatt, M. S., & Patalia, T. P. (2017). Indian monuments classification using support vector machine. International Journal of Electrical and Computer Engineering, 7(4), 1952.
Sharma, S., Aggarwal, P., Bhattacharyya, A. N., & Indu, S. (2018). Classification of Indian monuments into architectural styles. In Computer Vision, Pattern Recognition, Image Processing, and Graphics: 6th National Conference, NCVPRIPG 2017, Mandi, India, December 16-19, 2017, Revised Selected Papers 6 (pp. 540-549). Springer Singapore.
Agarwal, A., & Saxena, V. (2010). Content Based Multimodal Retrieval for Databases of Indian Monuments. In Contemporary Computing: Third International Conference, IC3 2010, Noida, India, August 9-11, 2010. Proceedings, Part I 3 (pp. 446-455). Springer Berlin Heidelberg.
Grishkin, V. M., Shigorets, S. B., Vlasov, D. Y., Miklashevich, E. A., Zhabko, A. P., Kovshov, A. M., & Vlasov, A. D. (2016). Development of stone monuments monitoring system using computer technology. In Biogenic—Abiogenic Interactions in Natural and Anthropogenic Systems (pp. 415-421). Springer International Publishing.
Padalkar, M. G., & Joshi, M. V. (2017). Automatic Detection and Inpainting of Defaced Regions and Cracks in Heritage Monuments. Digital Hampi: Preserving Indian Cultural Heritage, 225-244.
Maaten, L. V. D., Boon, P., Lange, G., Paijmans, H., & Postma, E. (2007). Computer vision and machine learning for archaeology.
Rocca, B. (2019). Handling imbalanced datasets in machine learning. Towards data science.
https://www.kaggle.com/datasets/devguruap4u/ancient-temple-pillar-images-dataset.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
F. Chollet et al., “Keras,” GitHub, 20156. [Online]. Available: https:// github.com/keras-team/keras.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
