Abstract
Effective classification of plant diseases is crucial for increasing agricultural productivity and ensuring global food se-curity. Deep learning, in particular convolutional neural networks (CNN s), has proven to be a revolutionary approach for plant disease classification using image data. This review examines prominent deep learning works that have been successfully applied to plant disease classification. The strengths of these works are highlighted, particularly their ability to accurately identify specific visual markers of disease, enabling precise differentiation in a wide range of plants. By utilizing extensive agricultural datasets, the deep models consistently achieve high accuracy and outperform traditional manual methods in terms of speed and reliability. However, challenges such as the variability of datasets, environmental influences on image quality and the computational cost of training and deploying CNN models are also addressed. This review highlights the potential of deep learning-based plant disease classification as a scalable and efficient solution for precision agriculture, enabling early detection and intervention to mitigate crop losses and improve agricultural sustainability.
Israa Tartoussi
PhD Student
My research focuses on Deep Learning Image-Based Plant Disease Classification.
Fadi Dornaika
Ikerbasque Research Professor
Ikerbasque Research Professor with expertise in computer vision, machine learning, and pattern recognition.
Pendar Alirezazadeh
Postdoctoral Research Fellow
Postdoctoral researcher specializing in Edge AI, deep learning quantization, and efficient neural network models for embedded systems.