Abstract

This study presents a very new and innovative approach to classify the elephants using a deep learning framework [2] which is built on transfer learning and data augmentation techniques. By using the features of MobileNetV2 as the base model, followed by different layers, the model achieved a high accuracy in classifying between images of elephants and other objects. This paper explains in detail about the end-to-end process, including dataset preparation, pre-processing, model architecture, and evaluation metrics. The results indicated the effectiveness of the proposed model in obtaining a high classification accuracy with a robust generalization across the training and validation datasets.

References

• M. H. Salem, Y. Li, and Z. Liu. ”Transfer Learning on EfficientNet for Maritime Visible Image Classification,” 2022 7th International Conference on Signal and Image Processing (ICSIP), Suzhou, China, 2022, pp. 514-520, doi: 10.1109/ICSIP55141.2022.9887050.
• Alzubaidi, L., Zhang, J., Humaidi, A.J. et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, 53 (2021).
• Shorten, C., Khoshgoftaar, T.M. A survey on Image Data Augmentation for Deep Learning. J Big Data 6, 60 (2019).
• Tammina, Srikanth. (2019). Transfer learning using VGG-16 with Deep Convolutional Neural Network for Classifying Images. International Journal of Scientific and Research Publications (IJSRP). 9. p9420. 10.29322/IJSRP.9.10. 2019.p9420.
• Tan, M. and Le, Q., 2021, July. Efficientnetv2: Smaller models and faster training. In International conference on machine learning (pp. 10096-10106). PMLR.
• Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), pp.84-90.
• Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks, doi: 10.48550/arXiv.1801.04381.
• Mothukuri Sujith, Shailendra Singh Kathait, Piyush Dhuliya Valiance Analytics Private Limited. Artificial Intelligence for Human-Animal Conflict Mitigation: Image Classification and Human Tracking in Tadoba Andhari Tiger Reserve. ”International Conference on Human-Elephant Conflict Management”
• Shailendra Singh Kathait, Vaibhav Singh, Ashish Kumar (2024) Valiance Analytics Private Limited. Individual Tiger Identification using Transfer Learning. International Journal of Computer Applications (0975 – 8887) Volume 186 – No.11, March 2024
• Kartikya Gupta, Vaibhav Sharma, Shailendra Singh Kathait (2024) Valiance Analytics Private Limited. Smart Screening: Non-Invasive Detection of Severe Neonatal Jaundice using Computer Vision and Deep Learning. International Journal of Computer Applications (0975 – 8887) Volume 186 – No.35, August 2024
• Shailendra Singh Kathait, Ashish Kumar, Piyush Dhuliya, Ikshu Chauhan (2024) Valiance Analytics Private Limited. Deep Learning-based Model for Wildlife Species Classification. International Journal of Computer Applications (0975 – 8887) Volume 186 – No.1, January 2024
• Keiron O’Shea and Ryan Nash. An introduction to convolutional neural networks, 2015.
• Karen Simonyan, Andrew Zisserman (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. doi: arXiv.1409.1556