Leaf Disease Detection using Deep Learning

• Afifa Rubani

  Author

Plant diseases pose a significant threat to agricultural productivity and global food security, especially in developing countries where timely diagnosis remains a challenge. This study presents a deep learning-based approach for automated plant leaf disease detection using Convolutional Neural Networks (CNN). The proposed model is trained on subsets of the PlantVillage dataset, focusing on potato and tomato crops, covering diseases such as Early Blight, Late Blight, Bacterial Spot, and Septoria Leaf Spot. The methodology involves image preprocessing, data augmentation, and CNN-based feature extraction to enhance classification performance. Experimental results demonstrate that the proposed model achieves high accuracy of 97.2% for potato diseases and 94.8% for tomato diseases, outperforming traditional machine learning methods. Comparative analysis with existing research highlights the efficiency and scalability of the proposed approach. The study concludes that CNN-based models provide a reliable and robust solution for plant disease detection, with strong potential for real-time agricultural applications.

[1] Strange, R. N., & Scott, P. R. (2005). Plant disease: a threat to global food security.

[2] Kethineni, K., & Pradeepini, G. (2023). Identification of Leaf Disease Using Machine Learning Algorithm for Improving the Agricultural System.

[3] Chowdhury, M. E. H., et al. (2021). Automatic and Reliable Leaf Disease Detection Using Deep Learning Techniques.

[4] Sharma, A., Bijral, R. K., Manhas, J., & Sharma, V. (2022). Mango Leaf Diseases Detection using Deep Learning.

[5] Agarwal, M., et al. (2020). ToLeD: Tomato leaf disease detection using convolution neural network.

[6] Durmus, H., et al. (2017). Disease detection on the leaves of the tomato plants by using deep learning.

[7] Saleem, R., et al. (2021). Mango leaf disease recognition and classification using novel segmentation and vein pattern technique.

[8] Amara, J., Bouaziz, B., & Algergawy, A. (2017). A deep learning-based approach for banana leaf diseases classification.

[9] Balakrishnan, S., Ramesh, T., & Kumar, P. (2023). EfficientNet-based deep learning model for tomato leaf disease classification.

[10] Wang, L., & Liu, H. (2024). Hybrid CNN-transformer models for agricultural image analysis.

[11] Zhang, L., & Li, H. (2024). Mobile-optimized deep learning for in-field plant disease diagnosis.

[12] Chen, Y., Wang, D., & Liu, Z. (2022). GAN-based data augmentation for improving tomato disease classification.

[13] Singh, R., Wang, H., & Gupta, S. (2023). Domain adaptation for plant disease detection in field conditions.

[14] Roberts, M., & Chen, K. (2023). Addressing class similarity challenges in plant disease classification.

[15] Zhou, H., Martinez, J., & Wilson, K. (2024). Hyperspectral imaging for early detection of plant diseases: Challenges and opportunities.

[16] Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science.

[17] Ferentinos, K. P. (2018). Deep learning models for plant disease detection. Computers and Electronics in Agriculture.

[18] Too, E. C., et al. (2019). Transfer learning for plant disease detection. Computers and Electronics in Agriculture.

[19] Hughes, D. P., & Salathé, M. (2015). Open access repository of plant disease images.

[20] Brahimi, M., Boukhalfa, K., & Moussaoui, A. (2017). Deep learning for tomato disease classification.

[21] Sladojevic, S., et al. (2016). Deep neural networks for plant disease recognition. Computational Intelligence and Neuroscience.

[22] Barbedo, J. G. A. (2018). Impact of dataset size in plant disease detection.

[23] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey.

[24] Li, Y., et al. (2020). CNN-based plant disease classification.

[25] Picon, A., et al. (2019). Deep learning for crop disease detection in real conditions.

[26] Zhang, S., et al. (2018). Cucumber disease recognition using CNN.

[27] Lu, J., et al. (2017). Rice disease detection using deep CNN.

[28] Fuentes, A., et al. (2017). Real-time detection of tomato diseases.

[29] Sun, Y., et al. (2017). Deep learning for crop pest identification.

[30] Arsenovic, M., et al. (2019). Deep learning for plant disease classification.

[31] Tm, P., et al. (2018). Tomato plant disease classification using CNN.

[32] Rangarajan, A. K., et al. (2018). Tomato disease classification using deep learning.

[33] Pawara, P., et al. (2018). Transfer learning for plant disease detection.

[34] Cruz, A. C., et al. (2017). Automatic detection of plant diseases.

[35] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature.

[36] Krizhevsky, A., et al. (2012). ImageNet classification with deep CNNs.

[37] Simonyan, K., & Zisserman, A. (2014). Very deep CNN (VGGNet).

[38] He, K., et al. (2016). Deep residual learning (ResNet).

[39] Tan, M., & Le, Q. (2019). EfficientNet: Rethinking CNN scaling.

[40] Dosovitskiy, A., et al. (2021). Vision transformers.

[41] Shorten, C., & Khoshgoftaar, T. (2019). Image data augmentation review.

[42] Goodfellow, I., et al. (2014). Generative adversarial networks (GANs).

[43] Kingma, D. P., & Ba, J. (2014). Adam optimizer.

[44] Bishop, C. M. (2006). Pattern recognition and machine learning.

[45] Hastie, T., et al. (2009). The elements of statistical learning.

[46] FAO. (2020). The state of food and agriculture.

[47] World Bank. (2021). Agriculture and food security report.

[48] ICAR. (2022). Agricultural statistics of India.

[49] Ministry of Agriculture, India. (2023). Crop disease reports.

[50] Food and Agriculture Organization. (2022). Digital agriculture trends.

• PDF