Detecting Sugarcane Diseases through Adaptive Deep Learning Models of Convolutional Neural Network

Sugarcane disease causes a threat in the sugarcane industry that leads to massive demolition of infected crops, decreases cultivation and financial loss of farmers. Early detection of the diseases using machine learning technology can avoid such loss and disaster. Subsequently, deep learning is an interesting technology to solve this problem through machine learning. CNN has proven to be a popular technique in recognizing and detecting plant diseases through deep learning. This paper aims to integrate various CNN architectures of deep learning models to achieve the highest accuracy rate in detecting and recognizing sugarcane diseases. The models were trained using 14,725 images of a healthy sugarcane leaves and infested sugarcane diseases and achieves a maximum 95.40% accuracy rate during training. Three architectures of CNN; StridedNet, LeNet, and VGGNet were used in the conduct of this study. VGGNet model tops the other two models achieving an accuracy rate of 95.40%, LeNet model achieves the rate of 93.65%, while StridedNet model achieves 90.10% accuracy rate during training. The three models trained serve its purpose by classifying images of a healthy sugarcane leaves and diseased infested sugarcane leaves based on the leaf features. This paper also bids a successful result for the researchers who are in the development of recognition system for sugarcane diseases.