MNTV3-ECOC: A Deep Learning Framework for Apple Leaf Disease Detection and Classification using Transfer Learning

Abstract

Apple fruit has major significance in the global agricultural economy due to the nutritional value that it provides and its economic benefits. In addition, there are many threats to UK apple production from various diseases, including foliar disease. There are several different methods being developed to diagnose plant disease. To overcome these limitations, this paper proposes an automated system for the identification and classification of diseased regions on apple fruit leaves using the MNTV3-ECOC architecture. The first step in the process is to apply Bilateral Filtering to remove noise from the images while preserving leaf vein edges, and (CLAHE) was used to enhance contrast. Then, a SegNet model was utilized to automatically identify the region(s) affected by disease, and after that, a pre-trained version of the MobileNetV3 model was utilized to extract relevant features. Finally, an Error Correcting Output Codes (ECOC) model was used to classify the type of the disease. An experiment was conducted to test the ability of the proposed model using a publicly available dataset consisting of 13,124 images of apple fruit leaves, each classified into one of four disease types. The proposed model achieved a classification accuracy of 97.80% along with a precision of 97.38%, a sensitivity of 97.25%, a specificity of 97.60%, and an F-score of 97.50%. Thus, based on these findings there is a large potential to combine image analysis with deep learning-based feature extraction and intelligent classification algorithms to achieve an earlier disease diagnosis of apple production.