Tomato Leaf Disease Recognition via Optimizing Deep Learning Methods Considering Global Pixel Value Distribution

doi:10.3390/horticulturae9091034

	Tomato Leaf Disease Recognition via Optimizing Deep Learning Methods Considering Global Pixel Value Distribution
	Li, Zheng 1; Tao, Weijie 1; Liu, Jianlei 2; Zhu, Fenghua3 ; Du, Guangyue 1; Ji, Guanggang 1
发表期刊	HORTICULTURAE
	2023-09-01
卷号	9 期号:9 页码:15
通讯作者	Liu, Jianlei(llliu2023@163.com)
摘要	In image classification of tomato leaf diseases based on deep learning, models often focus on features such as edges, stems, backgrounds, and shadows of the experimental samples, while ignoring the features of the disease area, resulting in weak generalization ability. In this study, a self-attention mechanism called GD-Attention is proposed, which considers global pixel value distribution information and guide the deep learning model to give more concern on the leaf disease area. Based on data augmentation, the proposed method inputs both the image and its pixel value distribution information to the model. The GD-Attention mechanism guides the model to extract features related to pixel value distribution information, thereby increasing attention towards the disease area. The model is trained and tested on the Plant Village (PV) dataset, and by analyzing the generated attention heatmaps, it is observed that the disease area obtains greater weight. The results achieve an accuracy of 99.97% and 27 MB parameters only. Compared to classical and state-of-the-art models, our model showcases competitive performance. As a next step, we are committed to further research and application, aiming to address real-world, complex scenarios.
关键词	plant leaf disease image recognition attention mechanism smart agriculture
DOI	10.3390/horticulturae9091034
关键词[WOS]	SEGMENTATION ; SUPERPIXEL
收录类别	SCI
语种	英语
WOS研究方向	Agriculture
WOS类目	Horticulture
WOS记录号	WOS:001078991900001
出版者	MDPI
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53072
专题	多模态人工智能系统全国重点实验室
通讯作者	Liu, Jianlei
作者单位	1.Shandong Jiaotong Univ, Sch Rail Transportat, Jinan 250357, Peoples R China 2.Qufu Normal Univ, Dept Cyberspace Secur, Qufu 273165, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Li, Zheng,Tao, Weijie,Liu, Jianlei,et al. Tomato Leaf Disease Recognition via Optimizing Deep Learning Methods Considering Global Pixel Value Distribution[J]. HORTICULTURAE,2023,9(9):15.
APA	Li, Zheng,Tao, Weijie,Liu, Jianlei,Zhu, Fenghua,Du, Guangyue,&Ji, Guanggang.(2023).Tomato Leaf Disease Recognition via Optimizing Deep Learning Methods Considering Global Pixel Value Distribution.HORTICULTURAE,9(9),15.
MLA	Li, Zheng,et al."Tomato Leaf Disease Recognition via Optimizing Deep Learning Methods Considering Global Pixel Value Distribution".HORTICULTURAE 9.9(2023):15.