Rice Disease Detection and Classification Using Mask R-CNN and DenseNet

Rice is an essential crop in the world food supply. As the consumption of rice grows, its production has fallen due to diseases. These diseases are able to spread quickly, leading to outbreaks that cause major yield loss. It is important to identify the disease quickly before it spreads out. However, most rice disease classification model is that the training uses datasets containing images with a single leaves. This is unrealistic as it is cumbersome to take a picture of each leaves one by one. This paper proposes the use of segmentation using Mask R-CNN, this will allowed the model to focus on identifying key features of three types of rice disease, namely rice blast, brown spot, and leaf blight. DenseNet classification model is trained using the cropped dataset and uncropped dataset. The result shows an increased in F1 score, which is counted as the frequency of a model making correct predictions. The F1 score when using cropped dataset compared to uncropped dataset increased by 8,22%, from 77,91% to 86,13%. This proves the idea of image segmentation using Mask-RCNN is able to improve the accuracy and performance of image classification models.