tar-2007-105.pdf (4.26 MB)
Download file

A smart agricultural application: Automated Detection of Diseases in Vine Leaves Using Hybrid Deep Learning

Download (4.26 MB)
journal contribution
posted on 07.10.2021, 12:05 by A Alkan, M Abdullah, H Abdulah, M Assaf, Huiyu Zhou
This paper reports a study which utilizes deep learning for automated detection of the symptoms of diseases on vine leaves. Vine fruits or grapes are very important and have existed in Syria and surrounding areas (e.g. Turkey) for many years. Quality of vine fruits is also very important in grape production as it is consumed in these areas every day. The aim of this study is to improve disease-detection accuracy in vine leaves and to develop a system to help Syrian and Turkish farmers and agricultural engineers to maintain the quality of grape production. In this study, over 1000 images of vine leaves have been collected from vine yards in Syria and the internet. These images are processed using MATLAB 2018B, Deep Learning Toolbox including Convolutional Neural Networks (CNNs) with AlexNet, GoogleNet and ResNet 18. A standard transfer learning (TL) algorithm is also used with CNNs, whereas a multiclass support vector machine (SVM) is used with AlexNet, whilst GPU and CUDA are used for accelerating the process of the disease detection for vine leaves. A software system has been created that enables the automatic and efficient detection of nine types of leaf diseases and the identification of healthy leaves. Experimental studies showed that the total detection accuracy of this system reaches 92.5%, 87.4% and 85.0%, 85.1% when AlexNet + TL, ResNet 18 + TL, GoogleNet + TL and AlexNet+SVM are used respectively. This smart agricultural application can provide early identification of the symptoms of grape diseases on leaves and thus help maintain the quality of vine fruits.



Turkish Journal of Agriculture and Forestry,(2021), 45

Author affiliation

School of Informatics


VoR (Version of Record)

Published in

Turkish Journal of Agriculture and Forestry









Acceptance date


Copyright date


Available date