出处:
链接: https://sci-hub.st/https://www.sciencedirect.com/science/article/pii/S016816992030795X
DOI:10.1016/j.compag.2020.105824
引用格式:Jiang Feng,Lu Yang,Chen Yu,Cai Di,Li Gongfa. Image recognition of four rice leaf diseases based on deep learning and support vector machine[J]. Computers and Electronics in Agriculture,2020,179. (Computers and Electronics in Agriculture,SCIE,2区)
datasets:
1、taken in rural farmland(8911 images, 2274 images of healthy rice, 6637 images of disease(:were clipped by manual clipping))
performance index:
1、convergence speed
2、accuracy
shape eigenvalues
1、area
2、the number of lesions
3、area to number ratio(the ratio of the number of lesion)
color space:
1、RGB
2、HSI
3、YCbCr
摘要:
提出问题、需求:在农情信息领域中,辨别和预测叶片病害一直是研究热点;
DL+SVM的优势:相结合使用,可有效解决问题同时提高识别精度;
提出的方法:CNNs提取图像特征,SVM对特定疾病进行分类与预测,利用