Identification of Diseases in Sugarcane Crops Using ConvNet

Abstract

Sugarcane is an essential crop worldwide, contributing significantly to the global economy. However, various diseases threaten sugarcane production, leading to substantial yield losses. Early detection and accurate identification of these diseases are crucial for effective disease management. This paper presents the automated recognition of sugarcane diseases using a deep learning method ConvNet (CNNs). The proposed model leverages the power of deep learning to analyze images of sugarcane leaves and classify them into different disease categories. The results demonstrate the efficacy of the deep learning model in accurately identifying sugarcane diseases, paving the way for improved disease management practices. Deep learning in CNNs has achieved remarkable success across various domains, including image recognition, object detection, semantic segmentation, and more. CNN architectures like AlexNet, VGGNet, Google Net, and ResNet have demonstrated state-of-the-art performance on benchmark datasets such as Image Net, pushing the boundaries of computer vision research.