A segmentation method for processing greenhouse vegetable foliar disease symptom images

作     者：Juncheng Ma Keming Du Feixiang Zheng Lingxian Zhang Zhongfu Sun 

作者机构：Institute of Environment and Sustainable Development in AgricultureChinese Academy of Agricultural SciencesBeijing 100081China College of Information and Electrical EngineeringChina Agricultural UniversityBeijing 100083China 

出 版 物：《Information Processing in Agriculture》 (农业信息处理（英文）)

年 卷 期：2019年第6卷第2期

页      面：216-223页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors would like to thank the financial support provided by The National Key Research and Development Program of China(2016YFD0300606 2017YFD0300402 and 2017YFD0300401) 

主　　题：Greenhouse vegetables Symptom images Decision tree Image segmentation 

摘      要：Uneven illumination and clutter background were the most challenging problems to segmentation of disease symptom *** order to achieve robust segmentation,a method for processing greenhouse vegetable foliar disease symptom images was proposed in this *** segmentation method was based on a decision tree which was constructed by a two-step coarse-to-fine ***,a coarse decision tree was built by the CART(Classification and Regression Tree)algorithm with a feature *** feature subset consisted of color features that was selected by Pearson’s Rank ***,the coarse decision tree was optimized by *** the optimized decision tree,segmentation of disease symptom images was achieved by conducting pixel-wise *** order to evaluate the robustness and accuracy of the proposed method,an experiment was performed using greenhouse cucumber downy mildew *** showed that the proposed method achieved an overall accuracy of 90.67%,indicating that the method was able to obtain robust segmentation of disease symptom images.