近红外高光谱成像技术快速鉴别国产咖啡豆品种

鲍一丹; 陈纳; 何勇; 刘飞; 张初; 孔汶汶

doi:doi:10.3788/ope.20152302.0349

光学精密工程, 2015, 23 (2): 349, 网络出版: 2015-03-23

近红外高光谱成像技术快速鉴别国产咖啡豆品种

Rapid identification of coffee bean variety by near infrared hyperspectral imaging technology

论文大纲

鲍一丹 ^*陈纳何勇刘飞张初孔汶汶

作者单位

浙江大学生物系统工程与食品科学学院, 浙江杭州 310058

摘要

结合近红外高光谱成像技术和不同的判别分析模型对4种国产咖啡豆品种进行了快速无损判别。通过高光谱成像仪提取874~1 734 nm波段内的光谱数据, 去除首尾噪声波段后, 分别基于925~1 680 nm波段的全谱波段和通过连续投影算法(SPA)选择的特征波长, 建立了偏最小二乘判别分析(PLS-DA)、随机森林(RF)、K最邻近算法(KNN)、支持向量机(SVM)模型和极限学习机(ELM)5种判别分析模型。基于上述判别模型对咖啡豆品种进行鉴别; 然后通过准确率、命中率和否定率3个参数对鉴别结果进行了评价。实验显示, 基于全谱和特征波段建立的模型均取得了较好的判别效果, 其中ELM模型效果均为最优, 每个品种建模集和预测集的准确率、命中率和否定率均在93.5%以上。研究结果表明, 基于近红外高光谱成像技术结合模型判别分析方法可以实现对国产咖啡豆品种的识别, 特征波长的选择减少了变量数, 但判别效果与全谱相当。

Abstract

Four different Chinese domestic coffee beans were identified rapidly by combining near infrared hyperspectral imaging technique and five kinds of discriminant models . A near-infrared hyperspectral imaging system covering the spectral range of 874-1 734 nm was set up to capture hyperspectral images of coffee bean samples. The head and end of the spectra with obvious noises were removed, and the spectral data in the range of 925-1 680 nm were extracted to establish discriminant models in the experiment. The sensitive wavelengths were selected from the full spectra by Successive Projections Algorithm (SPA). Five discriminant methods, including Partial Least Square-discriminant Analysis (PLS-DA), Random Forest (RF), K-nearest Neighbor algorithm (KNN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM) were applied to the establishment of discriminant models based on the full spectra and the selected sensitive wavelength variables. The properties of the models were compared and valuated by three parameters, sensitivity, precision and specificity. Among all discriminant models, the ELM models based on the full spectra and the selected sensitive wavelength variables show the best identification results, respectively. For each coffee bean cultivar, the sensitivity, precision and specificity of ELM models based on full spectra and the sensitive wavelengths are all over 93.5% in both the calibration set and the prediction set. It concludes that Chinese domestic coffee beans could be identified by near-infrared hyperspectral imaging combined with discriminant models rapidly. Selecting the sensitive wavelengths reduces variables, but the identification effect is the same as that of the full spectra.

参考文献

[1] 胡荣锁, 初众, 谷风林, 等. 海南主要地域生咖啡豆挥发性化学成分对比研究［J］. 光谱学与光谱分析, 2013, 33(2): 548-553.

HU R S, CHU ZH, GU F L, et al.. Comparison of green coffee beans volatiles chemical composition of Hainan main area［J］. Spectroscopy and Spectral Analysis, 2013, 33(2): 548-553. (in Chinese)

[2] 曾凡逵, 刘爱琴, 谭乐和, 等. 3个不同产地咖啡脂肪酸组成比较［J］.热带作物学报, 2011, 32(8): 1460-1463.

ZENG F K, LIU A Q, TAN L H, et al.. Fatty acid composition of coffee oil from three different origins ［J］. Chinese Journal of Tropical Crops, 2011, 32(8): 1460-1463. (in Chinese)

[3] SEMMELROCH P, LASKAWY G, BLANK I, et al.. Determination of potent odourants in roasted coffee by stable isotope dilution assays ［J］. Flavour and Fragrance Journal, 1995, 10: 1-7.

[4] 詹家芬, 陆舍铭, 曲国福, 等. 老挝咖啡的挥发性和半挥发性成分提取分析［J］. 食品研究与开发, 2008, 29(2): 125-129.

ZHAN J F, LU SH M, QU G F, et al.. Analysis on volatile and semi-volatie components of Laos' coffee ［J］. Food Research and Development, 2008, 29(2): 125-129. (in Chinese)

[5] 刘燕德, 周延睿, 彭彦颖. 基于近红外漫反射光谱检测鸡蛋品质［J］. 光学精密工程, 2013, 21(1): 40-45.

LIU Y D, ZHOU Y R, PENG Y Y. Detection of egg quality by near infrared diffuse reflectance spectroscopy［J］. Opt. Precision Eng., 2013, 21(1): 40-45. (in Chinese)

[6] 杜敏, 巩颖, 林兆洲, 等. 样品表面近红外光谱结合多类支持向量机快速鉴别枸杞子产地［J］. 光谱学与光谱分析, 2013, 32(5): 1211-1214.

DU M, GONG Y, LIN ZH ZH, et al.. Rapid identification of wolfberry fruit of different geographic regions with sample surface near infrared spectra combined with multi-class SVM ［J］. Spectroscopy and Spectral Analysis, 2013, 32(5): 1211-1214. (in Chinese)

[7] 王艳艳, 何勇, 邵永妮, 等. 基于可见-近红外光谱的咖啡品牌鉴别研究［J］. 光谱学与光谱分析, 2007, 27(4): 702-706.

WANG Y Y, HE Y, SH Y N, et al.. Discrimination among different brands of coffee by using vis-near infrared spectra［J］. Spectroscopy and Spectral Analysis, 2007, 27(4): 702-706. (in Chinese)

[8] IVANIRA M, IEDA S S. Chemometric discrimination of genetically modified coffea arabica cultivars using spectroscopic and chromatographic fingerprints ［J］. Talanta, 2013, 107: 416-422.

[9] ESTEBAN-DIEZ I, GONZALEZ-SAIZ J M, PIZARRO C. An evaluation of orthogonal signal correction methods for the characterisation of arabica and robusta coffee varieties by NIRS ［J］. Analytica Chimica Acta, 2004, 514(1): 57-67.

[10] ESTEBAN-DIEZ I, GONZALEZ-SAIZ J M, SAENZ-GONZALEZ C, et al.. Coffee varietal differentiation based on near infrared spectroscopy［J］. Talanta, 2007, 71(1): 221-229.

[11] DOWNEY G, BRIANDET R, WILSON R H, et al.. Near-and mid-infrared spectroscopies in food authentication: coffee varietal identification［J］. Journal of Agricultural and Food Chemistry, 1997, 45(11): 4357-4361.

[12] SANTOS K M, MOURA M F V, AZEVEDO F G, et al.. Classification of Brazilian coffee using near-infrared spectroscopy and multivariate calibration［J］. Analytical Letters, 2012, 45(7): 774-781.

[13] MYLES A J, ZIMMERMAN T A, BROWN S D. Transfer of multivariate classification models between laboratory and process near-infrared spectrometers for the discrimination of green Arabica and Robusta coffee beans［J］. Applied Spectroscopy, 2006, 60(10): 1198-1203.

[14] KONG W, LIU F, ZHANG C, et al.. Fast detection of peroxidase (POD) activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging［J］. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2014, 118: 498-502.

[15] XIONG Z J, SUM D W, ZENG X A, et al.. Recent developments of hyperspectral imaging systems and their applications in detecting quality attributes of red meats: a review ［J］. Journal of Food Engineering, 2014, 132: 1-13.

[16] 周扬, 戴曙光, 葛丁飞. 近红外光谱稀疏分量分析检测柴油品质参数［J］. 光学精密工程, 2014, 22(2): 296-303.

ZHOU Y, DAI SH G, GE D F. Detection of diesel quality parameters by near infrared spectroscopy with sparse component analysis［J］. Optics and Precision Engineering, 2014, 22(2): 296-303. (in Chinese)

[17] ZHU F L, ZHANG H L, SHAO Y N, et al.. Mapping of fat and moisture distribution in atlantic salmon using near-infrared hyperspectral imaging［J］. Food and Bioprocess Technology, 2014, 7: 1208-1214.

[18] LEE S, CHOI H, CHA K, et al.. Random forest as a potential multivariate method for near-infrared (NIR) spectroscopic analysis of complex mixture samples gasoline and naphtha ［J］. Microchemical Journal, 2013, 110: 739-748.

[19] ZHANG L G, ZHANG X, NI L J, et al.. Rapid identification of adulterated cow milk by non-linear pattern recognition methods based on near infrared spectroscopy ［J］. Food Chemistry, 2014, 145: 342-348.

[20] ALVES J C L, POPPI R J. Biodiesel content determination in diesel fuel blends using near infrared (NIR) spectroscopy and support vector machines (SVM) ［J］. Talanta, 2013, 104: 155-161.

[21] LIU F, HE Y. Discrimination of producing areas of auricularia auricula using visible/near infrared spectroscopy ［J］. Food and Bioprocess Technology, 2011, 4(3): 387-394.

[22] 刘燕德, 周延睿, 潘圆媛. 基于最小二乘支持向量机的辣椒可溶性固形物和维生素C含量近红外光谱检测［J］. 光学精密工程, 2014, 22(2): 281-288.

LIU Y D, ZHOU Y R, PAN Y Y. Determination of soluble solid contents and vitamin C of fresh peppers based on NIR spectrometry and least square support vector machines ［J］. Optics and Precision Engineering, 2014, 22(2): 281-288. (in Chinese)

[23] KONG W W, ZHANG C, LIU F, et al.. Irradiation dose detection of irradiated milk powder using visible and near-infrared spectroscopy and chemometrics ［J］. Journal of Dairy Science, 2013, 96(8): 4921-4927.

[24] 褚小立. 化学计量学方法与分子光谱分析技术［M］. 北京: 化学工业出版社, 2011.

ZHU X L. Molecular Spectroscopy Analytical Technology Combined with Chemometrics and Its Applications ［M］. Beijing: Chemical Industry Press, 2011. (in Chinese)

[25] OUYANG A, LIU J. Classification and determination of alcohol in gasoline using NIR spectroscopy and the successive projections algorithm for variable selection ［J］. Measurement Science and Technology, 2013, 24(2): 025502-025507.

[26] RIBEIRO J S, FERREIRA M M C, SALVA T J G. Chemometric models for the quantitative descriptive sensory analysis of Arabica coffee beverages using near infrared spectroscopy［J］. Talanta, 2011, 83: 1352-1358.

鲍一丹, 陈纳, 何勇, 刘飞, 张初, 孔汶汶. 近红外高光谱成像技术快速鉴别国产咖啡豆品种[J]. 光学精密工程, 2015, 23(2): 349. BAO Yi-dan, CHEN Na, HE Yong, LIU Fei, ZHANG Chu, KONG Wen-wen. Rapid identification of coffee bean variety by near infrared hyperspectral imaging technology[J]. Optics and Precision Engineering, 2015, 23(2): 349.

近红外高光谱成像技术快速鉴别国产咖啡豆品种

关于本站 Cookie 的使用提示

全站搜索

近红外高光谱成像技术快速鉴别国产咖啡豆品种

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索