Sesame Plant Disease Classification Using Deep Convolution Neural Networks

Monitoring sesame plant health and detecting disease early are essential to reducing disease spread and facilitate effective management practices. In this research, we developed an image classification model to detect bacterial blight-infected, phyllody-infected, and healthy sesame crops. Since images were necessary to carry out this study, we collected 2300 images at the Gondar and Humera Agriculture Research Centers and directly from the field in Metema. Since the collected images were limited, to increase the number of images in the dataset, we used image augmentation with different variations. In the image preprocessing step, we used a median filter for noise filtering, and contrast stretching techniques were used for image contrast and brightness enhancement. SegNet semantic segmentation, which is deep convolution neural network-based architecture, was used to segment the leaf part of the image from the background. In the feature extraction and classification steps, a deep convolutional neural network was used. Finally, we evaluated the proposed model and compared it with two recent deep convolution neural network models, namely, Xception and InceptionV3. The proposed model for the classification of sesame diseases achieved better accuracy, with 96.67% testing accuracy, 97.78% validation accuracy, and 98% training accuracy.