可见/近红外光谱技术无损识别苹果品种的研究
|
摘要
为了能快速无损鉴别苹果的品种,基于高光谱成像技术结合模式识别算法,分别建立了判别苹果品种K最近邻(KNN)识别模型与偏最小二乘判别分析(PLS-DA)识别模型。综合比较了不同光谱预处理方法(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,并利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99.9%的前10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;MSC预处理方法对光谱反射率预处理的效果最好;2种判别模型均能基本满足实际要求,且MSC+KNN识别模型的识别性能最优,对预测集样本的正确识别率高达100%。
In order to achieve rapid nondestructive identification of apple varieties, the recognition models of apple varieties were established based on hyperspectral imaging technology combined with K Nearest Neighbor(KNN) and Partial Least-Square Discriminant Analysis(PLS-DA), respectively. Then the effectiveness of the discriminant model using Second Derivation(SD), Standard Normal Variation(SNV) and Multi-Scatter Calibration(MSC) was compared and evaluated. Finally, the characteristic spectrums of apples were extracted by the Principal Component Analysis(PCA). The results showed that, the first 10 principal components with cumulative contribution rate of99.9% were selected by the principal component analysis as the characteristic spectral data in the sample set, and the dimensionality reduction of the spectral data was well realized. The preprocessing effect of MSC on spectral reflectivity was the best. Both models could basically meet the practical requirements, and MSC+KNN model had the optimal recognition performance with an accuracy recognition rate of 100%.
In order to achieve rapid nondestructive identification of apple varieties, the recognition models of apple varieties were established based on hyperspectral imaging technology combined with K Nearest Neighbor(KNN) and Partial Least-Square Discriminant Analysis(PLS-DA), respectively. Then the effectiveness of the discriminant model using Second Derivation(SD), Standard Normal Variation(SNV) and Multi-Scatter Calibration(MSC) was compared and evaluated. Finally, the characteristic spectrums of apples were extracted by the Principal Component Analysis(PCA). The results showed that, the first 10 principal components with cumulative contribution rate of99.9% were selected by the principal component analysis as the characteristic spectral data in the sample set, and the dimensionality reduction of the spectral data was well realized. The preprocessing effect of MSC on spectral reflectivity was the best. Both models could basically meet the practical requirements, and MSC+KNN model had the optimal recognition performance with an accuracy recognition rate of 100%.
引文
[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. DOI:10.1016/j.foodchem.2015.06.106.
[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. DOI:10.1016/j.postharvbio.2015.09.027.
[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(1):38-47. DOI:10.1007/s12161-015-0165-z.
[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. DOI:10.1016/j.foodcont.2017.04.036.
[5] MO C, KIM G, KIM M S, et al. Fluorescence hyperspectral imaging technique for foreign substance detection on freshcut lettuce[J]. Journal of the Science of Food&Agriculture,2017, 97(12):3985-3993. DOI:10.1002/jsfa.8262.
[6]李海峰,房萌萌.可见/近红外光谱技术无损检测新鲜鸡蛋pH及蛋白质的研究[J].食品工业科技, 2017, 38(20):280-283. DOI:10.13386/j.issn1002-0306.2017.20.050.
[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. DOI:10.6041/j.issn.1000-1298.2015.07.033.
[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(1):235-244. DOI:10.1007/s12161-015-0186-7.
[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. DOI:10.1016/j.postharvbio.2016.07.007.
[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. DOI:10.3969/j.issn.1009-6221.2018.02.015.
[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. DOI:10.1016/j.foodchem.2017.05.064.
[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. DOI:10.3969/j.issn.1002-6819.2015.04.046.
[13] KERESZTES J, 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. DOI:10.1016/j.foodcont.2016.02.007.
[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. DOI:10.1016/j.lwt.2016.11.063.
[15] PIECZYWEK P M, CYBULSKA J, SZYMA'NSKA-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. DOI:10.1016/j.foodcont.2017.10.013.
[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. DOI:10.6041/j.issn.1000-1298.2017.04.040.
[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. DOI:10.11937/bfyy.201620001.
[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. DOI:10.3969/j.issn.1002-6819.2013.01.036.
[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. DOI:10.3964/j.issn.100-0593(2017)03-0836-05.
[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. DOI:10.1016/j.postharvbio.2015.09.027.
[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(1):38-47. DOI:10.1007/s12161-015-0165-z.
[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. DOI:10.1016/j.foodcont.2017.04.036.
[5] MO C, KIM G, KIM M S, et al. Fluorescence hyperspectral imaging technique for foreign substance detection on freshcut lettuce[J]. Journal of the Science of Food&Agriculture,2017, 97(12):3985-3993. DOI:10.1002/jsfa.8262.
[6]李海峰,房萌萌.可见/近红外光谱技术无损检测新鲜鸡蛋pH及蛋白质的研究[J].食品工业科技, 2017, 38(20):280-283. DOI:10.13386/j.issn1002-0306.2017.20.050.
[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. DOI:10.6041/j.issn.1000-1298.2015.07.033.
[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(1):235-244. DOI:10.1007/s12161-015-0186-7.
[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. DOI:10.1016/j.postharvbio.2016.07.007.
[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. DOI:10.3969/j.issn.1009-6221.2018.02.015.
[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. DOI:10.1016/j.foodchem.2017.05.064.
[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. DOI:10.3969/j.issn.1002-6819.2015.04.046.
[13] KERESZTES J, 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. DOI:10.1016/j.foodcont.2016.02.007.
[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. DOI:10.1016/j.lwt.2016.11.063.
[15] PIECZYWEK P M, CYBULSKA J, SZYMA'NSKA-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. DOI:10.1016/j.foodcont.2017.10.013.
[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. DOI:10.6041/j.issn.1000-1298.2017.04.040.
[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. DOI:10.11937/bfyy.201620001.
[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. DOI:10.3969/j.issn.1002-6819.2013.01.036.
[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. DOI:10.3964/j.issn.100-0593(2017)03-0836-05.