基于近红外透射光谱与机器视觉的蜜柚汁胞粒化分级检测  

Detection of Honey Pomelo in Different Granulation Levels Based on Near-Infrared Transmittance Spectroscopy Combined with Machine Vision

作　　者：孙潇鹏 刘灿灿 陆华忠[1,3] 徐赛 SUN Xiaopeng;LIU Cancan;LU Huazhong;XU Sai(College of Engineering,South China Agricultural University,Guangzhou 510642,China;College of Light Industry and Food Engineering,Guangxi University,Nanning 530004,China;Guangdong Academy of Agricultural Sciences,Guangzhou 510642,China;Public Monitoring Center for Agro-Product,Guangdong Academy of Agricultural Sciences,Guangzhou 510642,China)

机构地区：[1]华南农业大学工程学院,广东广州510642 [2]广西大学轻工与食品工程学院,广西南宁530004 [3]广东省农业科学院,广东广州510642 [4]广东省农业科学院农产品公共监测中心,广东广州510642

出　　处：《食品科学技术学报》2021年第1期37-45,共9页Journal of Food Science and Technology

基　　金：国家自然科学基金资助项目(31901404);广东省农业科学院新兴学科团队建设项目(201802XX);广东省农业科学院院长基金面上项目(201920);广东省重点领域研发计划项目(2018B020240001);广州市科创委资助项目(201904010199)。

摘　　要：汁胞粒化是一种柑橘类水果中汁液囊的生理失调现象,表现为汁液囊变硬、干燥等,对水果内部品质产生消极影响。蜜柚是一种厚皮的柑橘类水果,很难通过外部果皮及果形,鉴定果实内部的汁胞粒化程度。采用近红外透射光谱结合机器视觉技术的快速无损检测方法,对蜜柚汁胞粒化程度进行分级检测。采集600个不同生长期的蜜柚样本在900~1700 nm的光谱数据,按果实的汁胞粒化程度将其分为5级。结合化学计量学研究由汁胞粒化引起的内部品质的化学变化,而机器视觉技术可用于研究由汁胞粒化引起的外部特征的物理变化。因此,该方法相较于传统检测方法,分级模型的预测能力更好。尤其是,连续投影-K近邻算法预测模型的准确性、敏感性和特异性分别达到0.9700、0.9231和0.9874以上。结果表明:该方法可用于汁胞粒化的鉴定与评估分级,且具有巨大潜力,以期为厚皮类水果在线分选及内部品质研究提供参考和理论依据。Granulation is a physiological disorder of juice sacs in citrus fruit,which made juice sacs become hard and dry and damaged the internal quality of citrus fruit.Honey pomelo is a thick-skinned citrus fruit,and it is hard to identify the granulation levels by observing the outer peel and fruit shape.In this study,a rapid and non-destructive detection method based on near-infrared transmittance spectroscopy combined with machine vision technology was used to classify honey pomelo by the granulation levels.600 honey pomelos in different growth stages were harvested and divided into five granulation levels according to the granulation changes of samples.Spectral data of samples were recorded in the range of 900~1700 nm,which were combined with chemometrics to research the chemical changes of inner quality caused by granulation.Machine vision technology can be used to study the physical changes of external characteristics caused by granulation.Therefore,comparison of the traditional method,this method has better predictive performances in classification models.In particular,the predictive performances of accuracy,sensitivity,and specificity were respectively not less than 0.9700,0.9231,and 0.9874 in the SP A-KNN(successive projections algorithm-K nearest neighbor)predicted model.The results showed that this method could be used for classification and evaluation of granulation,and had a great potential.The method provides a reference and theoretical basis for the online sorting and inner quality detecting of thick-skinned fruits.

关 键 词：机器视觉 近红外透射光谱 蜜柚 汁胞粒化 分级模型 

分 类 号：TS255.3[轻工技术与工程—农产品加工及贮藏工程] O657.61[轻工技术与工程—食品科学与工程]