Improved Potato Crop Disease Classification Using Ensembled Convolutional Neural Network

Potatoes are an essential crop cultivated in numerous regions around the globe, but they frequently get impacted by diseases that lower their production and quality. To ensure the crop reaches its maximum potential, controlling the diseases in the initial or early stages is necessary. Recent developments in deep learning algorithms have demonstrated significant improvements in predicting agricultural diseases at various stages. However, contemporary deep learning models frequently exhibit real-world performance and generalization capabilities limitations. This study proposes an ensemble convolutional neural network model that combines the three most widely used models, VGG16, MobileNetV2, and ResNet50, to increase generalizability and improve accuracy in the classification of potato crop diseases. The proposed model is trained on a large dataset containing 6644 images of potato leaves, which is constructed by merging three different publicly available datasets. These datasets are originally collected from three distinct locations around the globe (the USA, Ethiopia, and Pakistan). The model aims to achieve improvement in accuracy and maintain generalizability for classifying potato fungal diseases. The proposed ensemble architecture achieved an accuracy of 98.49%, surpassing the individual models. In this study, a web-based interface is developed for the evaluation of the model. The proposed model is tested on this web interface with the images obtained through the Google Image Search Engine. A plant pathologist supervised the selection of images and the pre-processing of the dataset. The results of the evaluation indicate that the model will perform better when deployed in real-world situations.