[1]尚静,张艳,孟庆龙.光谱技术结合化学计量学识别苹果品种[J].北方园艺,2019,43(16):66-71.[doi:10.11937/bfyy.20183895]
　SHANG Jing,ZHANG Yan,MENG Qinglong.Identification of Apple Varieties Based on Spectroscopy Technology Combined With Chemometrics[J].Northern Horticulture,2019,43(16):66-71.[doi:10.11937/bfyy.20183895]

点击复制

光谱技术结合化学计量学识别苹果品种

《北方园艺》[ISSN:1001-0009/CN:23-1247/S] 卷: 43卷期数: 2019年16 页码: 66-71 栏目: 出版日期: 2019-08-30

Title:: Identification of Apple Varieties Based on Spectroscopy Technology Combined With Chemometrics

作者:: 尚静1; 2; 张艳2; 孟庆龙1; 2; （1.贵阳学院食品与制药工程学院，贵州贵阳 550005；2.贵阳学院农产品无损检测工程研究中心，贵州贵阳 550005）

Author(s):: SHANG Jing1; 2; ZHANG Yan2; MENG Qinglong1; 2; (1.Food and Pharmaceutical Engineering Institute，Guiyang University，Guiyang，Guizhou 550005；2.The Research Center of Nondestructive Testing for Agricultural Products，Guiyang University，Guiyang，Guizhou 550005)

关键词:: 紫外/可见光谱; 化学计量学; 主成分分析; 无损识别

Keywords:: ultravioletradiation/visible spectroscopy; chemometrics; principal component analysis; nondestructive identification

DOI:: 10.11937/bfyy.20183895

文献标志码:: A

摘要:: 以“冰糖心”“嘎啦”和“山东富士”苹果为试材，采用紫外/可见光谱技术结合化学计量学，分别建立了判别3种苹果品种的K最近邻（KNN）识别模型和偏最小二乘判别分析（PLS-DA）识别模型，分析了不同的光谱预处理方法（二阶微分（SD）、标准正态变换（SNV）和多元散射校正（MSC））对各模型识别效果的影响，并采用主成分分析方法对预处理后的光谱数据进行降维，以提取能反映苹果品种的特征光谱。结果表明：采用主成分分析法选择了累计贡献率超过99%的前6个主成分作为样本集特征光谱数据，很好地实现了光谱数据的降维；二阶微分预处理方法对光谱的预处理效果最好。综上所述，建立的识别模型均能基本满足实际要求，且SD+KNN模型的建模效果最好，MSC+KNN模型的预测性能最好，SD+PLS-DA模型的总识别效果最好。

Abstract:: The recognition models of three different apple varieties (‘Candy’‘Gala’ and ‘Fuji’ apple) were established based on UV/VIS spectroscopy technology combined with K nearest neighbor (KNN) and partial least-square discriminant analysis (PLS-DA)，respectively.Then the influence of the different spectrum pretreatment methods (second derivation (SD)，standard normal variation (SNV) and multi-scatter calibration (MSC)) on the recognition models was analyzed.Finally，the characteristic spectrum of apples were extracted by the principal component analysis.The results showed that the first six principal components with the cumulative contribution rate above 99% were selected as the characteristic spectral data in the sample set by the principal component analysis，and the dimensionality reduction of the spectral data was well achieved.The effect of second derivation preprocessing for the spectrum data was the best.In conclusion，the recognition models all had an acceptable accuracy，especially SD+KNN model had optimal recognition performance for modeling set and MSC+KNN model had optimal recognition performance for prediction set.And SD+PLS-DA model had optimal total recognition performance.

参考文献/References:

[1]PAN L Q,ZHANG Q,ZHANG W,et al.Detection of cold injury in peaches by hyperspectral reflectance imaging and artificial neural network[J].Food Chemistry,2016,192:134-141.[2]CEN H Y,LU R F,ZHU Q B,et al.Nondestructive detection of chilling injury in cucumber fruit using hyperspectral imaging with feature selection and supervised classification[J].Postharvest Biology & Technology,2016,111:352-361.[3]GUO W C,ZHAO F,DONG J L.Nondestructive measurement of soluble solids content of kiwifruits using near-infrared hyperspectral imaging[J].Food Analytical Methods,2016(9):38-47.[4]ERKINBAEV C,HENDERSON K,PALIWAL J.Discrimination of gluten-free oats from contaminants using near infrared hyperspectral imaging technique[J].Food Control,2017,80:197-203.[5]MO C,KIM G,KIM M S,et al.Fluorescence hyperspectral imaging technique for foreign substance detection on fresh-cut lettuce[J].Journal of the Science of Food & Agriculture,2017,97(12):3985-3993.[6]王思玲,蔡骋,马惠玲,等.基于高光谱成像的苹果水心病无损检测[J].北方园艺,2015(8):124-130.[7]郭志明,赵春江,黄文倩,等.苹果糖度高光谱图像可视化预测的光强度校正方法[J].农业机械学报,2015,46(7):227-232.[8]PU H B,LIU D,WANG L,et al.Soluble solids content and pH prediction and maturity discrimination of lychee fruits using visible and near infrared hyperspectral imaging[J].Food Analytical Methods,2016(9):235-244.[9]FAN S X,ZHANG B H,LI J B,et al.Prediction of soluble solids content of apple using the combination of spectra and textural features of hyperspectral reflectance imaging data[J].Postharvest Biology & Technology,2016,121:51-61.[10]陈帅帅,张鹏,李江阔,等.寒富苹果可溶性固形物可见/近红外光谱无损检测模型的优化[J].保鲜与加工,2018,18(2):86-93.[11]SUN Y,WANG Y,XIAO H,et al.Hyperspectral imaging detection of decayed honey peaches based on their chlorophyll content[J].Food Chemistry,2017,235:194-202.[12]田有文,程怡,王小奇,等.基于高光谱成像的苹果虫伤缺陷与果梗/花萼识别方法[J].农业工程学报,2015,31(4):325-331.[13]KERESZTES J C,GOODARZI M,SAEYS W.Real-time pixel based early apple bruise detection using short wave infrared hyperspectral imaging in combination with calibration and glare correction techniques[J].Food Control,2016,66:215-226.[14]MUNERA S,BESADA C,ALEIXOS N,et al.Non-destructive assessment of the internal quality of intact persimmon using colour and VIS/NIR hyperspectral imaging[J].LWT-Food Science and Technology,2017,77:241-248.[15]PIECZYWEK P M,CYBULSKA J,SZYMAN〖JX-+0.8mm〗〖KG-*2〗＇SKA-CHARGOT M,et al.Early detection of fungal infection of stored apple fruit with optical sensors-comparison of biospeckle,hyperspectral imaging and chlorophyll fluorescence[J].Food Control,2018,85:327-338.[16]马惠玲,王若琳,蔡骋,等.基于高光谱成像的苹果品种快速鉴别[J].农业机械学报,2017,48(4):305-312.[17]倪力军,张立国.基础化学计量学及其应用[M].上海:华东理工大学出版社,2011.[18]刘亚,郭俊先,木合塔尔?米吉提,等.光谱预处理对苹果可溶性固形物含量VIS/NIR预测模型的影响[J].北方园艺,2016(20):1-4.[19]黄文倩,陈立平,李江波,等.基于高光谱成像的苹果轻微损伤检测有效波长选取[J].农业工程学报,2013,29(1):272-277.[20]樊阳阳,裘正军,陈俭,等.基于近红外高光谱成像技术的干制红枣品种鉴别[J].光谱学与光谱分析,2017,37(3):836-840.

备注/Memo

第一作者简介：尚静(1988-)，女，硕士，助教，现主要从事农产品无损检测等研究工作。E-mail：shji0124@163.com.责任作者：张艳(1977-)，女，博士，教授，硕士生导师，现主要从事农产品无损检测等研究工作。E-mail：Eileen_zy001@sohu.com.基金项目：国家自然科学基金资助项目(61505036)；贵州省普通高等学校工程研究中心资助项目(黔教合KY字[2016]017)；贵州省教育厅青年科技人才成长资助项目(黔教合KY字[2018]290)；博士科研启动经费资助项目(GYU-ZRD[2018]-012)。收稿日期：2019-03-28

更新日期/Last Update: 2019-08-29