Abstract
Black rot, Black measles, Leaf blight and Mites of grape are four common grape leaf diseases that seriously affect grape yield. However, the existing research lacks a real-time detecting method for grape leaf diseases, which cannot guarantee the healthy growth of grape plants. In this article, a real-time detector for grape leaf diseases based on improved deep convolutional neural networks is proposed. This article first expands the grape leaf disease images through digital image processing technology, constructing the grape leaf disease dataset (GLDD). Based on GLDD and the Faster R-CNN detection algorithm, a deep-learning-based Faster DR-IACNN model with higher feature extraction capability is presented for detecting grape leaf diseases by introducing the Inception-v1 module, Inception-ResNet-v2 module and SE-blocks. The experimental results show that the detection model Faster DR-IACNN achieves a precision of 81.1% mAP on GLDD, and the detection speed reaches 15.01 FPS. This research indicates that the real-time detector Faster DR-IACNN based on deep learning provides a feasible solution for the diagnosis of grape leaf diseases and provides guidance for the detection of other plant diseases.
Highlights
China is a modern agricultural country with more than 2000 years of history in grape planting
The results show that when the number of anchor boxes is 5 and scales are 2, 4, 8, 16, and 32—that is, the sizes of the anchor boxes are 32 × 32, 64 × 64, 128 × 128, 256 × 256, and 512 × 512—and 90 k anchor boxes are generated in each image, the highest precision of 81.1% mean Average Precision (mAP) is obtained in the Faster DR-IACNN, which is 5.9% mAP higher than the original 3 anchor boxes
The results show that the detection model can detect multiple diseased spots of the same disease in one leaf and multiple spots of different diseases on one leaf at one time, demonstrating the strong generalization and robustness of the model
Summary
China is a modern agricultural country with more than 2000 years of history in grape planting. China has the largest grape export in the world. Grape juice, raisins, wine, and other grape products have great commercial value. Severe diseases take a great toll on yield and quality during the growing process of grapes, especially in rainy areas and periods. Timely and effective detection of grape leaf diseases is a vital means to ensure the healthy growth of grapes. The diagnosis of plant leaf diseases relies on trained experts performing visual inspection (Dutot et al, 2013), which usually leads to high cost and a large risk of error. With the rapid development of artificial intelligence, machine learning methods have been applied to plant disease detection to make it more intelligent.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
