Deep diagnosis: A real-time apple leaf disease detection system based on deep learning

• A suitable size expert-annotated apple leaf disease dataset has been prepared. • Presented a two-stage apple disease detection system based on Xception and Faster-RCNN. • Used a transfer learning method to initialize model by weight parameters learned on large-scale datasets. • Achieved an overall 88% of classification accuracy and our best detection model achieved mAP of 42%. • Promising results indicate that this system can be very helpful for farmers and Apple growers. Diseases and pests are one of the major reasons for low productivity of apples which in turn results in huge economic loss to the apple industry every year. Early detection of apple diseases can help in controlling the spread of infections and ensure better productivity. However, early diagnosis and identification of diseases is challenging due to many factors like, presence of multiple symptoms on same leaf, non-homogeneous background, differences in leaf colour due to age of infected cells, varying disease spot sizes etc. In this study, we first constructed an expert-annotated apple disease dataset of suitable size consisting around 9000 high quality RGB images covering all the main foliar diseases and symptoms. Next, we propose a deep learning based apple disease detection system which can efficiently and accurately identify the symptoms. The proposed system works in two stages, first stage is a tailor-made light weight classification model which classifies the input images into diseased, healthy or damaged categories and the second stage (detection stage) processing starts only if any disease is detected in first stage. Detection stage performs the actual detection and localization of each symptom from diseased leaf images. The proposed approach obtained encouraging results, reaching around 88% of classification accuracy and our best detection model achieved mAP of 42%. The preliminary results of this study look promising even on small or tiny spots. The qualitative results validate that the proposed system is effective in detecting various types of apple diseases and can be used as a practical tool by farmers and apple growers to aid them in diagnosis, quantification and follow-up of infections. Furthermore, in future, the work can be extended to other fruits and vegetables as well.