The quantification of tea appearance quality using Hyper-spectral imaging

• Published in: Jiangxi nongye daxue xuebao = Acta agriculturae universitatis jiangxiensis Vol. 35; no. 2
• Main Authors: Wu Ruimei, Jiangxi Agricultural University, Nanchang (China), College of Engineering, Wu Yanhong, Jiangxi Agricultural University, Nanchang (China), College of Engineering, Ai Shirong, Jiangxi Agricultural University, Nanchang (China), College of Software
• Format: Journal Article
• Language: Chinese
• Published: 01.04.2013
• Subjects: http://www.fao.org/aos/agrovoc#c_4881; http://www.fao.org/aos/agrovoc#c_5993; http://www.fao.org/aos/agrovoc#c_7634; MODELE; MODELOS; PLANTE; PLANTS; TE; TEA; THE
• ISSN: 1000-2286

为弥补感官审评方法评定茶叶品质存在的不足，提出采用高光谱图像来量化分析茶叶的外形感官品质。以碧螺春名优绿茶为对象，采集其高光谱图像，利用主成分分析法从原始高光谱图像中优选出3个波长（768.74，827.54，886.83nm）下的特征图像。分别提取每个特征图像的颜色特征和纹理特征，3个特征图像共提取90个特征变量。利用BP神经网络方法建立特征变量与外形感官评分之间的相关模型，模型对预测集样本的相关系数为0.859，预测均方根误差为3.611。在预测集中，对模型的预测值与实际评分值进行t检验时，预测值与实际值无显著差异，说明所建模型是准确可靠的。 Hyper-spectral imaging technique was used for the quantitative evaluation of tea quality so as to make up the deficiency of sensory evaluation method for evaluating green tea quality. “Biluochun”, a famous green tea was used as the test object. Hyper-spectral image