利用近红外光谱技术识别不同类别的茶叶.PDF

安徽农业科学袁允燥怎则灶葬造 燥枣 粤灶澡怎蚤 粤早则蚤援 杂糟蚤援 圆园园7袁35渊14冤院4083-4084 责任编辑 王丽莉 责任校对 王淼 利用近红外光谱技术识别不同类别的茶叶 1 1 2 1 蔡健荣 吕强 张海东 陈全胜 袁 袁 袁 江苏大学生物与环境工程学院 江苏镇江 云南农业大学工程技术学院 云南昆明 袁 212013 曰2. 袁 650201冤 摘要 以龙井 碧螺春 祁红和铁观音 种中国名茶为对象 研究了采用近红外光谱结合 最近邻法 模式识别方法对茶叶进 尧 尧 4 袁 K KNN冤 行识别与分类的可行 选取 -1 波数范围内的光谱 通过标准正态变量变换 预处理后 利用 遥 6500耀5500cm 1538耀1818 nm冤 袁 SNV冤 袁 KNN 的模式识别方法建立识别模型 结果表明 主成分因子建立的 判别模型最佳 模型对训练集与预测集中样本的识别率都达到 遥 袁4 KNN 袁 100 %遥 该结论为快速准确识别茶叶提供了一种新思路遥 关键词 茶叶 近红外光谱 识别 曰 曰KNN曰 中图分类号 S123 文献标识码 A 文章编号 0517-6611 2007冤14-04083-02 Application of Near Infrared Reflectance Spectroscopy in Identification of Different Classified Tea CAI J ian rong et al School of Food Biological Engineering, Jiangsu University, Zhenji ang, Jiangsu 212013冤 Abstract With 4 kinds of famous tea of Longji ng, Biluochun, Qi and Tieguanyin as test materials, the feasibility of identification and classify of tea was studied by using near infrared reflectance spectroscopy coupled with pattern recognition based on KNN. It was found that in the spectra range between 6 500 cm-1 and 5 300 cm-1, the models of tea variety identification were built separately with KNN pattern recognition method after the pretreatment by standard normal variate transformation (SNV). Results showed that the KNN identification models were optimal when 4 principal components factors were used in building models, with the identification being all 100 % in samples of training set and