Abstract: In the provided field instruction, deep learning is described as mimicking the brain using artificial neurons to automatically extract layered patterns from diverse data, such as images and text, for tasks like disease recognition and language translation. The challenges include data availability and quality, particularly in collecting extensive and high-quality images of potato leaves with varying diseases and growth stages. Model generalizability is highlighted as a concern, with a focus on convolutional neural networks (CNNs), such as VGG16 and ResNet, for image recognition. The proposed system suggests leveraging transfer learning by utilizing pre-trained models for potato disease classification and employing data augmentation to artificially expand datasets. Emphasizing the increase in quantity and diversity of training data is recommended to enhance the model's ability to generalize to unseen data and improve robustness in various scenarios.
Keywords: Potato, Leaf, Disease, Prediction, Deep learning, CNN, Agriculture, Crop health, Image classification
Cite:
Vishal V, Harishkumar R, B.A Banupriya, G.Thiagarajan, "A Deep Learning Approach for Accurate Potato Leaf Disease Prediction", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 2, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13234.
|
DOI:
10.17148/IJARCCE.2024.13234
