Early Disease Diagnosis for Rice Crop
This work addresses early disease detection for rice farmers to prevent crop damage, but it is incremental as it builds on existing techniques with localized data.
The paper tackled the problem of early disease diagnosis in rice crops by introducing a dataset with localized annotations for diseased segments and a method based on Mask RCNN to provide location and extent of infections, achieving 87.6% accuracy compared to 58.4% without localized information.
Many existing techniques provide automatic estimation of crop damage due to various diseases. However, early detection can prevent or reduce the extend of damage itself. The limited performance of existing techniques in early detection is lack of localized information. We instead propose a dataset with annotations for each diseased segment in each image. Unlike existing approaches, instead of classifying images into either healthy or diseased, we propose to provide localized classification for each segment of an images. Our method is based on Mask RCNN and provides location as well as extend of infected regions on the plant. Thus the extend of damage on the crop can be estimated. Our method has obtained overall 87.6% accuracy on the proposed dataset as compared to 58.4% obtained without incorporating localized information.