Enhanced Bird Species Image Recognition and Classification using MobileNet and InceptionV3 Transfer learning Architectures
Abstract
The proposed study explores the application of transfer learning techniques in bird species image classification, specifically focusing on the MobileNet and InceptionV3 models. Utilizing the CUB-200-2011 dataset, the transfer learning is employed to enhance classification accuracy. The MobileNet model achieved an impressive accuracy of 74.60%, outperforming InceptionV3, which recorded an accuracy of 64.00%. The corresponding loss values were 0.8685 for MobileNet and 1.128 for InceptionV3, highlighting MobileNet's superior alignment with actual class labels. Additionally, MobileNet demonstrated a precision range of 0.45 to 0.93, while InceptionV3's precision ranged from 0.65 to 0.81. The F1-scores revealed MobileNet's performance ranged from 0.40 to 0.91, in contrast to InceptionV3’s lower F1-scores, indicating a more stable but less effective classification ability. These findings underscore the potential of MobileNet as a lightweight, efficient alternative for wildlife image classification tasks, making it particularly suitable for deployment in resource-constrained environments. The developed user interface allows for seamless interaction, enabling users to upload images and receive immediate classification results, further demonstrating the practical application of these models in conservation and biodiversity preservation efforts.
References
LeCun, Y., Bengio, Y., & Haffner, P. (2015). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324. doi:10.1109/5.726791.
LeCun, Y., & others. (2015). Deep learning. Nature, 521(7553), 436-444. doi:10.1038/nature14539.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097-1105.
Horn, G., & others. (2018). iNaturalist Species Classification Challenge. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 206-215. doi:10.1109/CVPRW.2018.00027.
Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778. doi:10.1109/CVPR.2016.90.
Szegedy, C., Vanhoucke, V., Vinyals, O., Google, T., & others. (2016). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2818-2826. doi:10.1109/CVPR.2016.308.
Howard, A. G., Sandler, M., Chen, W., Chen, L. H., & others. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
Gupta, A., & others. (2020). Evaluating MobileNet for wildlife classification. Proceedings of the International Conference on Machine Learning and Computing, 77-82. doi:10.1145/3312141.3312151.
Liu, X., & others. (2019). Fine-grained classification of bird species using InceptionV3. IEEE Access,7,77914-77923. doi:10.1109/ACCESS.2019.2
915561.
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2016). Inception-v4, Inception-ResNet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1).
Zhang, J., Chen, Y., & others. (2020). Transfer learning for wildlife image classification: A comprehensive survey. Artificial Intelligence Review, 53(5), 3701-3722. doi:10.1007/s10462-019-09769-7.
Tang, Y., & others. (2021). A comparative study of MobileNet and InceptionV3 for wildlife classification. Journal of Computer Science and Technology, 36(2), 387-398. doi:10.1007/s11390-021-2155-0.
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014). Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1717-1724. doi:10.1109/CVPR.2014.223.
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 1-48. doi:10.1186/s40537-019-0197-0.
Chen, Y., Li, M., & others. (2019). Improving wildlife image classification with data augmentation techniques. Ecological Informatics, 53, 22-30. doi:10.1016/j.ecoinf.2019.04.004.
Kim, H., & others. (2018). Ensemble learning for improved species identification. BMC Bioinformatics, 19(1), 152. doi:10.1186/s12859-018-2101-7.
Wu, J., & others. (2020). Addressing data imbalance in wildlife classification using ensemble methods. Scientific Reports, 10(1), 1-10. doi:10.1038/s41598-020-70444-1.
McCarthy, T., & others. (2021). The role of automated systems in biodiversity monitoring: A case study on poaching detection. Biodiversity and Conservation, 30(3), 703-726. doi:10.1007/s10531-021-02044-9.
M. P. & others. (2019). Leveraging deep learning for wildlife monitoring and conservation. Frontiers in Ecology and the Environment, 17(2), 86-94. doi:10.1002/fee.2025.
Noroozi, M., & others. (2020). Addressing occlusion and variable poses in wildlife image classification. Proceedings of the IEEE International Conference on Computer Vision, 932-941. doi:10.1109/ICCV.2019.00085.
C. C. & others. (2021). A survey of wildlife image classification: Challenges and opportunities. Journal of Applied Ecology, 58(2), 291-303. doi:10.1111/1365-2664.13753.
R. S., & others. (2018). Automated detection of poaching activities using deep learning models. Conservation Biology, 32(6), 1377-1388. doi:10.1111/cobi.13197.
Published
Downloads
Copyright (c) 2025 Sakthi Priya G, Vignesh Saravanan K, Dheetchana K
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
