Abstract
In practice, early detection of disease is of high importance to practical value, corresponding measures can be taken at the early stage of plant disease. However, in the early stage of disease or when a rare disease occurs, there are limited training samples in practice, which makes machine learning especially deep learning models hardly work well while the stronger representative ability needs large-scale training data. To solve this problem, a fine grained-GAN based grape leaf spot identification method was proposed for local spot area image data augmentation to the generated local spot area images which were added and fed them into deep learning models for training to further strengthen the generalization ability of the classification models, which can effectively improve the accuracy and robustness of the prediction. Including 500 early-stage grape leaf spot images every category were fed into the proposed fine grained-GAN for local spot area data augmentation, 1000 local spot area sub images every category were generated in this study. The improved faster R-CNN was integrated in fine grained-GAN as local spot area detector. After that, the segmented sub-images and generated sub-images were mixed as training data input into the deep learning models, while the original segmented sub-images were used for testing. Experimental results showed that the proposed method had achieved higher identification accuracy on five state-of-art deep learning models; especially ResNet-50 had got 96.27% accuracy, which obtained significant improvements than other data augmentation methods and verified its satisfactory performance. This is of great practical significance for rare diseases or limited training samples.
Highlights
When enjoying the most luscious grape wine such as Lafite or Latour, we may not realize that the grape planting industry may have a disastrous threat by various diseases
Et al [14] proposed a plant disease identification method based on the dataset including 220,592 images with 271 categories, Experimental results showed that the proposed method had achieved a better performance than the exiting start-of-art models
We proposed a fine grained-Generative Adversarial Networks (GANs) based grape leaf spot identification model under limited training samples, which can take advantage of the strong representative ability of deep learning models and not be limited by the lack of training data
Summary
When enjoying the most luscious grape wine such as Lafite or Latour, we may not realize that the grape planting industry may have a disastrous threat by various diseases. Et al [8] proposed an unsupervised simplified fuzzy ArtMap neural network method for the detection of plant diseases These methods above had made the state-of-the-art performance in grape leaf disease identification. A total of 8,124 images were generated, experimental results showed that the proposed model can achieve 98.70% accuracy on test data based on X-ception, which demonstrated it could overcome overfitting problem and improve identification accuracy. X. Liu, et al [14] proposed a plant disease identification method based on the dataset including 220,592 images with 271 categories, Experimental results showed that the proposed method had achieved a better performance than the exiting start-of-art models. S. Militante, et al [20] proposed an improved deep learning model to capture plant leaf diseases using a large number of training data, which had achieved high identification accuracy. 2) An annotated grape leaf disease spot image dataset was built up in this work
Sign-in/Register to view highlights & summary 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.
