图像识别技术在全国中药资源普查中的应用
投稿时间:2017-11-03  修订日期:2017-11-03  责任编辑:  点此下载全文
引用本文:
DOI:
摘要点击次数: 27
全文下载次数: 
                          
作者中文名作者英文名单位中文名单位英文名E-Mail
张小波 Zhang Xiaobo 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical, China Academy of Chinese Medical Sciences jack110007@163.com 
格小光 Ge Xiaoguang 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical, China Academy of Chinese Medical Sciences  
金艳 Jin Yan 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical, China Academy of Chinese Medical Sciences  
史婷婷 Shi Tingting 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical, China Academy of Chinese Medical Sciences  
王慧 WANG Hui 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical hwang@icmm.ac.cn 
李梦 Li Meng 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical  
景志贤 Jing Zhixian 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical  
郭兰萍 Guo Lanping 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical  
黄璐琦* Huang Luqi 中国中医科学院中药资源中心 National Resource Center for Chinese Materia Medical huangluqi01@126.com 
基金项目:] 中央本级重大增减支项目(2060302),科技基础性工作专项(2013FY114500)
中文摘要:随着计算机和图像处理技术的发展应用,图像识别技术已经应用于全国中药资源普查工作的各个阶段。其中:(1)在前期准备工作中,为建立统一的中药资源名录库,基于纸质文献资料采用文字识别技术,辅助进行与中药资源相关各类名录的数字化;为确定每个普查队外业调查的代表区域和样地,基于卫星遥感图像和植被图等基础数据,采用遥感图像分类等技术方法,辅助确定重点调查区域。(2)在外业调查过程中,为相对准确地获取中药材种植面积,基于遥感图像采用决策树模型、光谱特征、面向对象等方法,辅助进行中药材种植区域识别和面积估算。(3)在内业整理过程中,为相对准确的确定区域内中药资源种类,基于植物个体照片、标本照片和名称等采用图像识技术,辅助进行中药资源种类的统计汇总。(4)在成果转化应用中,基于药用资源个体和药材样品照片,开发中药资源种类识别APP和道地药材3D展示系统,辅助进行中药资源种类识别和药材鉴别特征展示。在中药资源普查工作中引入图像识别技术,辅助普查人员开展相关工作,不但能降低人工的工作量、提高工作效率,而且提高了普查成果的信息化水平和共享应用能力。随着中药资源普查工作的不断深入,图像识别技术方法在相关工作中还将发挥其特有的作用。
中文关键词:全国中药资源普查  图像识别技术  应用探讨
 
Application of image recognition technology in census of national traditional Chinese medicine resourcesZHANG Xiao Bo,GE Xiao guang,JIN-Yan,SHI Ting ting,WANG-Hui ,LI-Meng,
Abstract:[Abstract] With the development of computer and image processing technology, image recognition technology has been applied to the national medicine resources census work at all stages. Among them: (1) in the preparatory work, in order to establish a unified library of traditional Chinese medicine resources, using text recognition technology based on paper materials, be the assistant in the digitalization of various categories related to Chinese medicine resources; to determine the representative area and plots of the survey from each census team, based on the satellite remote sensing image and vegetation map and other basic data, using remote sensing image classification and other technical methods to assist in determining the key investigation area. (2) In the process of field investigation, to obtain the planting area of Chinese herbal medicine was accurately, we use the decision tree model, spectral feature and object-oriented method were used to assist the regional identification and area estimation of Chinese medicinal materials. (3) In the process of finishing in the industry, in order to be able to relatively accurately determine the type of Chinese medicine resources in the region, based on the individual photos of the plant, the specimens and the name of the use of image recognition techniques, to assist the statistical summary of the types of traditional Chinese medicine resources. (4) In the application of the results of transformation, based on the pharmaceutical resources and individual samples of medicinal herbs, the development of Chinese medicine resources to identify APP and authentic herbs 3D display system, assisted the identification of Chinese medicine resources and herbs identification characteristics. The introduction of image recognition technology in the census of Chinese medicine resources, assisting census personnel to carry out related work, not only can reduce the workload of the artificial, improve work efficiency, but also improve the census results of information technology and sharing application ability. With the deepening of the work of Chinese medicine resources census, image recognition technology in the relevant work will also play its unique role.
keywords:National census of Chinese medicine resources  Image recognition technology  Application discussion
查看全文   下载PDF阅读器
相关阅读
评论
zuo-jiat you-jiat