优质崂山茶嫩芽识别方法的研究  

Study on Identification Method of High Quality Laoshan Tea Buds

作　　者：蔡丽萍 赵丽清[1] 龚丽农[1] 张惠莉[1] 赵强 CAI Liping;ZHAO Liqing;GONG Linong;ZHANG Huili;ZHAO Qiang(College of Mechanical and Electrical Engineering,Qingdao Agricultural University,Qingdao 266109,China)

机构地区：[1]青岛农业大学机电工程学院,山东青岛266109

出　　处：《青岛农业大学学报（自然科学版）》2018年第1期76-81,共6页Journal of Qingdao Agricultural University(Natural Science)

基　　金：山东省农机局农机技术提升项目(2017YH112);山东省重点研发计划项目(2015GNC112013)

摘　　要：优质茶的采摘,嫩叶的识别与定位是实现自动化采摘的关键所在。本文针对优质崂山茶的种植及生长特点,通过拍摄环境背景设置、两叶一针崂山茶的嫩叶识别、针尖的特征提取及定位等进行了方法研究,设置蓝光作为拍摄环境背景利用分块二值矩阵求和的方法进行针尖的识别,将求和后的分块矩阵二值化并以针尖位置为中心的9元素矩阵与两叶一针9元素矩阵进行匹配判断。试验表明该方法识别准确率可达93.83%,为实现崂山茶叶嫩芽的自动采摘提供了一种有效方法。High quality tea picking,the identification and localization of tender leaves are the key to automatic picking.Based on the characteristics of the cultivation and growth of the quality laoshan tea,this paper studied the methods of setting the environment setting,the identification of the first leaf of laoshan tea and the feature extraction and positioning of the tip.This study set blu-ray as shooting environment by using the method of block binary matrix sum to pinpoint recognition,after will sum the partitioned matrix of binarization and pinpoint location centered 9 element matrix and two leaves a needle 9 element matrix matching judgment.The experiment showed that the recognition accuracy could reach 93.83%,which provides an effective method for the automatic picking of the leaves of laoshan tea.

关 键 词：两叶一针 嫩叶识别 定位 自动采摘 

分 类 号：S24[农业科学—农业电气化与自动化]