山西农业大学学报（自然科学版）2018，Vol.38Issue(5)：57-63,7.DOI:10.13842/j.cnki.issn1671-8151.201712011
基于机器视觉葡萄叶片还原糖含量的检测系统
Machine vision application on detecting reducing sugar content of grape leaves
摘要
Abstract
[Objective]In order to solve the problems of low efficiency and high cost of conventional method for reducing sugar test,present study proposed a detection system with machine vision.[Methods]A grape leaf reducing sugar de-tection system was developed using LabVIEW and MATLAB software platform.The reducing sugar content of grape leaves measured by spectral chemistry experiment method was used as control data.The combined parameters and fea-tures of first and second color moments,and gray level co -occurrence matrix were used to extract the grape leaf color and texture features,and the SVM classification model based on radial basis function kernel was constructed by using the feature vector as input vector,and was used to analyze 480 collected grape leaves.[Results]Results showed that the accuracy rate of the system was reached to 88.125%,and the color and texture characteristics were highly correla-ted with reducing sugar content.[Conclusion]The results were accurate,time -consuming and stable compared to traditional methods,and provided an effective analysis tactic for the determination of sugar content in grape leaves, which indicated important significance for improving the real -time testing efficiency of field crops.关键词
葡萄叶片/颜色矩/灰度共生矩阵/支持向量机/MATLAB/还原糖Key words
Grape leaves/Color moment/Gary symbiotic matrix/Support vector machine/MATLAB/Reducing sugar分类
信息技术与安全科学引用本文复制引用
贾尚云,高晓阳,李红岭,邵世禄,杨梅,武季玲..基于机器视觉葡萄叶片还原糖含量的检测系统[J].山西农业大学学报（自然科学版）,2018,38(5):57-63,7.基金项目
国家自然科学基金项目(61164001) （61164001）
