Cassava Leaf Disease Classification Using Pre-Trained EfficientN Et Model

Abstract

India relies primarily on agriculture for its subsistence, and the nation's economy is entirely dependent on agricultural products. The demand for food is rising dramatically due to the rapid rate of population growth worldwide. To meet this demand and boost production, farmers are now embracing advanced farming techniques that incorporate artificial intelligence (AI). AI is particularly utilized for crop health observation, plant disease recognition and discovery, and weather and commodity price forecasting. Crop diseases pose a significant threat to food safety, and identifying them manually, especially on larger farms, with the help of experts can be both expensive and time-consuming. To address this issue, deep-based techniques offer image-based automatic process control, inspection, and robot guidance for effective pest and disease control. This article delves into the use of deep learning methods, specifically EfficientN et, for identifying leaf diseases in cassava plants. The main focus is on categorizing leaf diseases using images from the Kaggle dataset. The model achieves impressive results, with the highest accuracy of 92.83% and the lowest loss of 0.2019, both observed at epoch 16.