Panchadeva: Sculpture Image Classification using CNN-SVM

Main Article Content

Akshath Rao
Sindhu C
Abrar Suhail
Aayush Mehta
Saksham Dube

Keywords

CNN, SVM

Abstract

Rich culture and heritage have been a very promising factor when it has come to the land of India. India is a land which is enriched with a vast amount of architectural sculpture, rare sculptures, temples and many more. When it comes to the classification as well as recognition of these Rare Indian Sculptures, it is often a very challenging task. In the realm of image recognition, classification, and identification, entity recognition of Indian sculptures might be seen as one of the most complex and challenging challenges. This project primarily consists of a database which is manually constructed. The database consists for a total of five entities belonging to the various Indian Gods. In this project, we have considered Lord Ganesha, Lord Hanuman, Lord Krishna, Lord Shiva and lastly Lord Vishnu thus adding up to a total of five entity classes. Every image has a distinctive feature which separates and differentiates it from the rest of the images or pictures. The orientation, angles, sizes as well as the colours of all these images play a very crucial and important role in the training and processing of the machine learning model which is to be implemented. Here, the model is trained on a total of 500 images with each of 100 images belonging to one entity class. Support Vector Machine and Convolutional Neural Network, respectively, can be used to assess the efficacy and accuracy of the proposed model. Using a combination of the Deep Learning, Convolutional Neural Network (CNN) along with Sequential model with categorical cross-entropy and SoftMax functions assisted by SVM(Support Vector Machine) -the model that this project trained has enabled us to achieve an accuracy of 94%.

Abstract 94 | pdf Downloads 176

References

1. Josef NAVRATIL, Kamil P ´ ´ICHA, and Jaroslava HREBCOV ˇ A. “The importance of historical monu- ´ ments for domestic tourists: The case of South-western Bohemia (Czech
Republic)”. In: Moravian Geographical Reports 18.1 (2010), pp. 45–61.
2. Eric Tchouamou Njoya. “An analysis of the tourism and wider economic impacts of price-reducing reforms in air transport services in Egypt”. In: Research in Transportation Economics 79 (2020), p. 100795.
3. Ajay Shrestha and Ausif Mahmood. “Review of deep learning algorithms and architectures”. In: IEEE Access 7 (2019), pp. 53040–53065
4. Karl Weiss, Taghi M Khoshgoftaar, and DingDing Wang. “A survey of transfer learning”. In: Journal of Big data 3.1 (2016), p. 9.
5. Lisa Torrey and Jude Shavlik. “Transfer learning”. In: Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. IGI global, 2010, pp. 242–264. 0262 Authorized licensed use limited to: Univ of Calif Santa Barbara. Downloaded on June 15,2021 at 12:07:37 UTC from IEEE Xplore. Restrictions apply.
6. Jia Deng et al. “Imagenet: A large-scale hierarchical image database”. In: 2009 IEEE conference on computer vision and pattern recognition. Ieee. 2009, pp. 248–255.
7. Hussam Qassim, Abhishek Verma, and David Feinzimer. “Compressed residual-VGG16 CNN model for big data places image recognition”. In: 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC). IEEE. 2018, pp. 169–175
8. S. Hesham, R. Khaled, D. Yasser, S. Refaat, N. Shorim and F. H. Ismail, "Monuments Recognition using Deep Learning VS Machine Learning," 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC), NV, USA, 2021, pp. 0258-0263, doi: 10.1109/CCWC51732.2021.9376029.
9. S. Hayat, S. Kun, Z. Tengtao, Y. Yu, T. Tu and Y. Du, "A Deep Learning Framework Using Convolutional Neural Network for Multi-Class Object Recognition," 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China, 2018, pp. 194-198, doi: 10.1109/ICIVC.2018.8492777.
10. P. Shukla, B. Rautela and A. Mittal, "A Computer Vision Framework for Automatic Description of Indian Monuments," 2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Jaipur, India, 2017, pp. 116-122, doi: 10.1109/SITIS.2017.29.
11. P. Shukla, T. Gupta, A. Saini, P. Singh, and R. Balasubramanian. A deep learning frame-work for recognizing developmental disorders. In Applications of Computer Vision (WACV), 2017IEEE Winter Conference on, pages 705–714. IEEE, 2017.
12. Sindhu C and G. Vadivu, “Fine grained sentiment polarity classification using augmented knowledge sequence-attention mechanism”, in the Journal of Microprocessors and Microsystems, Vol 81, 2021. https://doi.org/10.1016/j.micpro.2020.103365
13. K. -Z. Liu, P. -J. Lee, G. -C. Xu and B. -H. Chang, "SIFT-Enhanced CNN Based Objects Recognition for Satellite Image," 2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCETaiwan), 2020, pp. 1- 2, doi: 10.1109/ICCETaiwan49838.2020.9258037.
14. Dalara, C. Sindhu and R. Vasanth, "Entity Recognition in Indian Sculpture using CLAHE and machine learning," 2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), 2022, pp. 1-12, doi: 10.1109/ICEEICT53079.2022.9768565
15. K. Umri, M. Wafa Akhyari and K. Kusrini, "Detection of Covid-19 in Chest X-ray Image using CLAHE and Convolutional Neural Network," 2020 2nd International Conference on Cybernetics and Intelligent System (ICORIS), 2020, pp. 1-5, doi: 10.1109/ICORIS50180.2020.9320806.