Abstract
Anthracnose, brown spot, mites, black rot, downy mildew, and leaf blight are six common grape leaf pests and diseases, which cause severe economic losses to the grape industry. Timely diagnosis and accurate identification of grape leaf diseases are decisive for controlling the spread of disease and ensuring the healthy development of the grape industry. This paper proposes a novel recognition approach that is based on improved convolutional neural networks for the diagnoses of grape leaf diseases. First, based on 4,023 images collected in the field and 3,646 images collected from public data sets, a data set of 107,366 grape leaf images is generated via image enhancement techniques. Afterward, Inception structure is applied for strengthening the performance of multi-dimensional feature extraction. In addition, a dense connectivity strategy is introduced to encourage feature reuse and strengthen feature propagation. Ultimately, a novel CNN-based model, namely, DICNN, is built and trained from scratch. It realizes an overall accuracy of 97.22% under the hold-out test set. Compared to GoogLeNet and ResNet-34, the recognition accuracy increases by 2.97% and 2.55%, respectively. The experimental results demonstrate that the proposed model can efficiently recognize grape leaf diseases. Meanwhile, this study explores a new approach for the rapid and accurate diagnosis of plant diseases that establishes a theoretical foundation for the application of deep learning in the field of agricultural information.
Highlights
The grape industry is one of the major fruit industries in China, and the total output of grapes reached 13.083 million tons in 2017
The TensorFlow and Keras deep learning frameworks were used to implement the dense Inception convolutional neural network (DICNN) model, which is convenient for the development of comparative experiments due to its Python interfaces (Bahrampour et al, 2015; Abadi et al, 2016a; Abadi et al, 2016b; Tang, 2016)
An accuracy of 94.89% was realized by DenseNet, which is due to its compelling advantages of strengthening feature propagation and encouraging feature reuse
Summary
The grape industry is one of the major fruit industries in China, and the total output of grapes reached 13.083 million tons in 2017. In (Mohanty et al, 2016; Zhang and Wang, 2016; Lu J. et al, 2017; Lu Y. et al, 2017; Khan et al, 2018; Liu et al, 2018; Geetharamani and Pandian, 2019; Ji et al, 2019; Jiang et al, 2019; Liang et al, 2019; Oppenheim et al, 2019; Pu et al, 2019; Ramcharan et al, 2019; Wagh et al, 2019; Zhang et al, 2019a; Zhang et al, 2019b; ), CNNs are extensively studied and applied to the diagnosis of plant diseases According to these studies, CNNs can learn advanced robust features of diseases directly from original images rather than selecting or extracting features manually, which outperform the traditional feature extraction approaches. An innovative recognition approach for grape leaf diseases based on CNNs is presented. This approach aims at overcoming two main challenges: First, CNN models require a large amount of data for training.
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.
