Non-destructive determination of pericarp break force of Lingwu long jujube by hyperspectral imaging technology
-
摘要: 利用高光谱技术对灵武长枣果皮强度检测进行研究,为灵武长枣外部品质无损检测提供科学方法。采集120个灵武长枣的4001000 nm的高光谱图像,对光谱数据进行预处理;应用连续投影算法（SPA）、正自适应加权算法（CARS）和无信息变量消除法（UVE）对原始光谱数据提取特征波长;分别建立基于全光谱和特征波长的偏最小二乘回归（PLSR）和最小二乘支持向量机（LS-SVM）果皮强度预测模型。结果表明:采用标准正态变换（SNV）预处理算法效果最优,其PLSR模型的交叉验证相关系数（Rcv）为0.8207,交叉验证均方根误差（RMSECV）为9.9630;利用SPA、CARS和UVE法从全光谱的125个波长中分别选取出29个、31个和31个特征波长;而基于全光谱建立的LS-SVM模型效果最优,其预测相关系数（Rp）为0.9555,预测均方根误差（RMSEP）为3.8282;研究结果表明基于高光谱成像技术采集的灵武长枣漫反射光谱进行果皮强度无损检测具有可行性。Abstract: Using hyperspectral imaging technology to measure pericarp break force of Lingwu jujube could provide a scientific method for the non- destructive measurement of external quality of Lingwu jujube. The hyperspectral image of 120 Lingwu long jujubes were acquired from 400 nm to 1000 nm,and pretreatment methods were used to process diffuse reflectance spectroscopy. The successive projections algorithm( SPA),competitive adaptive reweighed sampling( CARS) and principal uninformative variable elimination( UVE) were used to select characteristic wavelengths.A partial least squares regression( PLSR) and a least squares support vector machine( LS-SVM) model were established based on full spectra and selected characteristic wavelengths for predicting pericarp break force of Lingwu long jujube.The result showed that standardized normal variate( SNV) pretreatment method was best,and the correlation coefficient of cross calibration( Rcv) of the PLSR model built was 0.8207,root mean square error of cross validation( RMSEP) reached 9.9630. The SPA,CARS and UVE method were used to select characteristic wavelengths with 29,31 and 31 from 125 wavelengths,respectively.LS- SVM model based on full spectra was the best,and correlation coefficient of prediction( Rp) and root- mean- square error of prediction( RMSEP) of the model was 0.9555 and 3.8282,respectively. The results indicated that the non- destructive measurement for pericarp break force of Lingwu jujube based on hyperspectral imaging technology was feasible.
-
[1] 李丹.基于高光谱成像技术的灵武长枣无损检测技术研究[D].银川:宁夏大学,2015. [2] 苟茜,王敏,冀晓龙,等.不同成熟度灵武长枣食用及营养品质研究[J].现代食品科技,2014,30(11):98-104. [3] 陈文涛,袁德义,张日清,等.鲜食枣品质的综合评价[J].湖南农业大学学报(自然科学版),2014,40(1):32-36. [4] 吴龙国,何建国,贺晓光,等.高光谱图像技术在水果无损检测中的研究进展[J].激光与红外,2013,9:990-996. [5] JohnsonⅢOwen N,Slidell Mark,Kreishman Peter,et al.Hyperspectral imaging:an emerging technology as a potential novel adjunct in assessing peripheral perfusion deficits and success oflower extremity revascularizations[J].Journal of the American College of Surgeons(S1072-7515),2008,207(3):S114.
[6] 单佳佳,彭彦昆,王伟,等.基于高光谱成像技术的苹果内外品质同时检测[J].农业机械学报,2011,42(3):140-144. [7] 侯宝路,李柏承,周瑶,等.基于可见-近红外高光谱成像技术的梨硬度和可溶性固体含量的预测[J].激光杂志,2015,10:70-74. [8] 刘卉,郭文川,岳绒.猕猴桃硬度近红外漫反射光谱无损检测[J].农业机械学报,2011,42(3):145-149. [9] 薛璐,刘小路,鲁晓翔,等.近红外漫反射无损检测蓝莓硬度的研究[J].浙江农业报,2015,27(9):1646-1651. [10] 王丹,鲁晓翔,张鹏,等.近红外无损检测甜柿果实质地和品质[J].食品工业科技,2013,34(24):53-56. [11] 郭文川,董金磊.高光谱成像结合人工神经网络无损检测桃的硬度[J].光学精密工程,2015(6):1530-1537. [12] 徐爽,何建国,贺晓光,等.基于高光谱技术长枣内外品质同时检测[J].光电子·激光,2013,24(10):1972-1976. [13] 徐爽,何建国,易东,等.基于高光谱图像技术的长枣糖度无损检测[J].食品与机械,2012,28(6):168-170. [14] El Masry G,Wang N,El Sayed A.Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry[J].Journal of Food Engineering,2007,81:98-107.
[15] 马庆华,王贵禧,梁丽松.质构仪穿刺实验检测冬枣质地品质方法的建立[J].中国农业科学,2011(6):1210-1217. [16] 董金磊,郭文川.采后猕猴桃可溶性固形物含量的高光谱无损检测[J].食品科学,2015,36(16):101-106. [17] 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(1):40-45. [18] 蒋蘋,罗亚辉,胡文武,等.基于高光谱的油茶籽内部品质检测最优预测模型研究[J].农机化研究,2015(7):56-60.
计量
- 文章访问数: 155
- HTML全文浏览量: 12
- PDF下载量: 307
下载:
