COMPARATIVE ANALYSIS OF CUSTOMIZED CNN AND TEACHABLE MACHINE IN PLANT LEAVES IMAGES

Parth R. Dave; Viral B. Pansiniya; Bhaveshkumar P. Patel; Bhoomi H. Trivedi; Yogesh B. Patel

doi:10.29121/shodhkosh.v5.i2.2024.5192

Authors

Parth R. Dave Assistant Professor, Computer Engineering Department, L. D. College of Engineering- Ahmedabad, Gujarat
Viral B. Pansiniya Assistant Professor, Computer Engineering Department, Government Engineering College – Patan, Gujarat
Bhaveshkumar P. Patel Assistant Professor, Computer Engineering Department, Government Engineering College – Patan, Gujarat
Bhoomi H. Trivedi Assistant Professor, Computer Engineering Department, L. D. College of Engineering- Ahmedabad, Gujarat
Yogesh B. Patel Assistant Professor, Computer Engineering Department, Government Engineering College – Patan, Gujarat, India

DOI:

https://doi.org/10.29121/shodhkosh.v5.i2.2024.5192

Keywords:

Plant Species Classification, Customized Cnn, Teachable Machine, Deep Learning, Image Recognition, Leaves Dataset

Abstract [English]

Accurate identification of plant species is critical for biodiversity monitoring, ecological studies, and agricultural management. Traditional manual identification methods are time-consuming and prone to human error, necessitating automated solutions. This research presents a comparative analysis between a customized Convolutional Neural Network (CNN) model and Google's Teachable Machine for plant species classification using the Leaves Image Dataset. The customized CNN is designed with multiple convolutional layers and optimized hyper parameters, while the Teachable Machine offers a no-code AI solution. Experimental results demonstrate that the customized CNN outperforms the Teachable Machine in terms of accuracy, precision, recall, and F1-score. The study highlights the strengths and limitations of both approaches, providing insights for deploying species classification models in real-world scenarios.

References

H. Rehana, M. Ibrahim, and M. H. Ali, "Plant Disease Detection using Region-Based Convolutional Neural Network," arXiv preprint arXiv:2303.09063, 2023.

A. Bagga et al., "Image‐based detection and classification of plant diseases using deep learning: State‐of‐the‐art review," Urban Agriculture & Regional Food Systems, 2023. DOI: https://doi.org/10.1002/uar2.20053

B. S. Hamed, M. M. Hussein, and A. M. Mousa, "Plant Disease Detection Using Deep Learning," International Journal of Intelligent Systems and Applications, vol. 15, no. 6, pp. 38–50, 2023. DOI: https://doi.org/10.5815/ijisa.2023.06.04

P. S. Thakur et al., "Explainable vision transformer enabled convolutional neural network for plant disease identification: PlantXViT," arXiv preprint arXiv:2207.07919, 2022. DOI: https://doi.org/10.1016/j.ecoinf.2023.102245

A. Yasin and R. Fatima, "On the Image-Based Detection of Tomato and Corn Leaves Diseases: An in-depth comparative experiments," arXiv preprint arXiv:2312.08659, 2023.

H. M. Hussain, "Plant Leaf Image Dataset," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/hmohamedhussain/leaves-image-dataset

Chakraborty, K. K., Mukherjee, R., Chakroborty, C., & Bora, K. (2022). Automated recognition of optical image-based potato leaf blight diseases using deep learning. Physiological and Molecular Plant Pathology, 117, 101781. DOI: https://doi.org/10.1016/j.pmpp.2021.101781

J. A. Campos-Leal, A. Yee Rendón, and I. F. Vega-Lopez, "Simplifying VGG-16 for plant species identification," IEEE Latin America Transactions, vol. 20, no. 11, pp. 2330–2338, 2022. DOI: https://doi.org/10.1109/TLA.2022.9904757

Debnath, A., Hasan, M. M., Raihan, M., Samrat, N., Alsulami, M. M., Masud, M., & Bairagi, A. K. (2023). A smartphone-based detection system for tomato leaf disease using EfficientNetV2B2 and its explainability with artificial intelligence (AI). Sensors, 23(21), 8685. DOI: https://doi.org/10.3390/s23218685

Shoaib, M., Shah, B., EI-Sappagh, S., Ali, A., Ullah, A., Alenezi, F., Gechev, T., Hussain, T., & Ali, F.(2023). An advanced deep learning models-based plant disease detection: A review of recent research. Frontiers in Plant Science, 14, 1158933. DOI: https://doi.org/10.3389/fpls.2023.1158933

Omer, S. M., Ghafoor, K. Z., & Askar, S. K (2023). Plant disease diagnosing based on deep learning techniques: A survey and research challenges. ARO-The Scientific Journal of Koya University, 11(1), 38–47. DOI: https://doi.org/10.14500/aro.11080

Tian, K., Zeng, J., & Song, T. (2022). Tomato leaf diseases recognition based on deep convolutional neural networks. Journal of Agricultural Engineering, 54(1), 1432. DOI: https://doi.org/10.4081/jae.2022.1432

Hosny, K. M., El-Hady, W. M., Samy, F. M., Vrochidou, E., & Papakostas, G. A. (2023). Multi-class classification of plant leaf diseases using feature fusion of deep convolutional neural network and local binary pattern. IEEE Access, 11, 62307–62317. DOI: https://doi.org/10.1109/ACCESS.2023.3286730

Tavakoli, H., Alirezazadeh, P., & Hedayatipour, A. (2021). Leaf image-based classification of some common bean cultivars using discriminative convolutional neural networks. Computers and Electronics in Agriculture, 181, 105935. DOI: https://doi.org/10.1016/j.compag.2020.105935

Liu, K.-H., Yang, M.-H., Huang, S.-T., & Lin, C. (2022). Plant species classification based on hyperspectral imaging via a lightweight convolutional neural network model. Frontiers in Plant Science, 13, 855660. DOI: https://doi.org/10.3389/fpls.2022.855660

Loddo, A., Loddo, M., & Di Ruberto, C. (2021). A novel deep learning-based approach for seed image classification and retrieval. Computers and Electronics in Agriculture, 187, 106269. DOI: https://doi.org/10.1016/j.compag.2021.106269

Batchuluun, G., Nam, S.-H., & Park, K.-R. (2022). Deep learning-based plant-image classification using a small training dataset. Mathematics, 10(17), 3091. DOI: https://doi.org/10.3390/math10173091

Saleem, M. H., Potgieter, J., & Arif, K. M.(2020). Plant disease classification: A comparative evaluation of convolutional neural networks and deep learning optimizers. Plants, 9(10), 1319. DOI: https://doi.org/10.3390/plants9101319

V. Nair and G. E. Hinton, "Rectified Linear Units Improve Restricted Boltzmann Machines," in Proc. 27th Int. Conf. Mach. Learn. (ICML), 2010, pp. 807–814.