首页 | 简介 | 作者 | 编者 | 读者 | Ei(光盘版)收录本刊数据 | 网络预印版 | 点击排行前100篇 | English
陈全胜,赵杰文,蔡健荣,Vittayapadung Saritporn.基于近红外光谱和机器视觉的多信息融合技术评判茶叶品质[J].农业工程学报,2008,24(3):.DOI:
基于近红外光谱和机器视觉的多信息融合技术评判茶叶品质
投稿时间:2007-06-08  修订日期:2007-10-30
中文关键词:  近红外光谱  机器视觉  多信息融合  茶叶  检测
基金项目:江苏省自然基金重点资助项目(BK2006707-1); 国家863计划资助项目(2006AA10Z263)
作者单位
陈全胜 江苏大学食品与生物工程学院镇江 212013 
赵杰文 江苏大学食品与生物工程学院镇江 212013 
蔡健荣 江苏大学食品与生物工程学院镇江 212013 
Vittayapadung Saritporn 江苏大学食品与生物工程学院镇江 212013 
摘要点击次数: 6093
全文下载次数: 2611
中文摘要:首次提出利用近红外光谱和机器视觉的多传感信息融合技术评判茶叶品质。试验以4个等级的炒青绿茶为试验对象,对获取的图像特征信息和光谱特征信息,通过主成分分析提取相应的主成分得分向量构成模式识别的输入。利用BP神经网络方法建立茶叶综合品质评判模型。在模型的建立过程中,对各个信息的主成分因子数进行了优化。从试验的结果看,在图像信息主成分因子数等于6,光谱信息主成分因子数等于3时,建立的模型最佳,模型训练时的回判率为99%,预测时的识别率为89%。研究结果表明基于近红外光谱和机器视觉技术的多传感信息融合技术评判茶叶综合品质的方法是可行的,评判结果的准确性和稳定性都较单个信息模型有所提高。
Chen Quansheng,Zhao Jiewen,Cai Jianrong,Vittayapadung Saritporn.nspection of tea quality by using multi-sensor information fusion based on NIR spectroscopy and machine vision[J].Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE),2008,24(3):.DOI:
nspection of tea quality by using multi-sensor information fusion based on NIR spectroscopy and machine vision
Author NameAffiliation
Chen Quansheng School of Food and Biological Engineering,Jiangsu University,Zhenjiang 212013,China 
Zhao Jiewen School of Food and Biological Engineering,Jiangsu University,Zhenjiang 212013,China 
Cai Jianrong School of Food and Biological Engineering,Jiangsu University,Zhenjiang 212013,China 
Vittayapadung Saritporn School of Food and Biological Engineering,Jiangsu University,Zhenjiang 212013,China 
Key words:near infrared spectroscopy  machine vision  multi-sensor information fusion  tea  inspection
Abstract:This study first offered a new idea that tea comprehensive quality was discriminated with multi-sensor information fusion from near infrared spectroscopy and machine vision. In this experiment, four grades of roasted green tea were used as experimental targets. Principal component analysis (PCA) was implemented on these feature variables from image information and spectral information, and principal components (PCs) vectors were extracted as the inputs of pattern recognition. The discriminating model was built by BP neural network. The principal component factors from two-sensor information were optimized in building model. Experimental results showed that the optimal model was obtained under PCs=6 for image information and PCs=3 for spectral information. The discriminating rate equaled to 99% in training set, and 89% in prediction set. The overall results showed that it was feasible to discriminate tea comprehensive quality with two-sensor information fusion. The correct rate and robustness of the discriminating model from two-sensor information fusion were better than those of the model from the single-sensor information.
查看全文   下载PDF阅读器

京ICP备06025802号-3

主办单位:中国农业工程学会 单位地址:北京朝阳区麦子店街41号

服务热线:010-59197076、59197077 传真: 邮编:100125 Email:tcsae@tcsae.org
本系统由北京勤云科技发展有限公司设计

京公网安备 11010502031390号