基于高光谱技术苹果硬度快速无损检测方法的建立
|
摘要
目的利用高光谱技术建立苹果内部品质无损检测的方法。方法将高光谱图像的光谱信息和空间信息结合,采用洛伦兹函数对苹果高光谱的空间散射曲线进行拟合,提取拟合曲线的相关参数,利用拟合参数对苹果硬度进行建模分析。结果拟合曲线与原散射曲线的相关系数R达到0.99以上。分析比较多种统计建模方法对不同拟合参数的建模效果,结果表明:在524～1016nm波段范围内,利用偏最小二乘法(partialleastsquares,PLS)对拟合曲线的峰值建立硬度的预测模型,校正集预测值与标准值的相关系数Rc=0.89,校正集标准误差SEC=0.71×105Pa,验证集预测值与标准值的相关系数Rv=0.88,验证集标准误差SEV=0.88×105Pa。结论利用高光谱散射成像技术,采用偏最小二乘的方法对拟合峰值建模,可以实现苹果硬度的快速无损检测。
Objective To establish a new method for apple firmness assessment by using the hyperspectral imaging technology.Methods Based on the spectral information and spatial information of hyperspectral images,Lorentzian distribution function was proposed to fit spectral scattering profiles at individual wavelengths,and fitting parameters was used for modeling analysis of the firmness of the apple.Results The average correlation coefficient R between fitting curve and scattering profile was greater than 0.99.Comparison of various image analysis and modeling methods with different fitting parameters of prediction results,partial least squares(PLS) model with fitting parameter had a good prediction of apple firmness at the wavelength of 400～ 1100 nm with R c =0.89,SEC=0.71×10 5 Pa,and R v =0.88,SEV=0.88×10 5 Pa,respectively.Conclusion Hyperspectral scattering imaging method is useful for rapid and non-destructive measurement of apple firmness.
Objective To establish a new method for apple firmness assessment by using the hyperspectral imaging technology.Methods Based on the spectral information and spatial information of hyperspectral images,Lorentzian distribution function was proposed to fit spectral scattering profiles at individual wavelengths,and fitting parameters was used for modeling analysis of the firmness of the apple.Results The average correlation coefficient R between fitting curve and scattering profile was greater than 0.99.Comparison of various image analysis and modeling methods with different fitting parameters of prediction results,partial least squares(PLS) model with fitting parameter had a good prediction of apple firmness at the wavelength of 400～ 1100 nm with R c =0.89,SEC=0.71×10 5 Pa,and R v =0.88,SEV=0.88×10 5 Pa,respectively.Conclusion Hyperspectral scattering imaging method is useful for rapid and non-destructive measurement of apple firmness.
引文
[1]洪添胜,李震,吴春胤,等.高光谱图像技术在水果品质无损检测中的应用[J].农业工程学报,2007,23(11):280285.
[2]Nourain J,应义斌,王剑平,等.Finite element models of wa-termelon and their applications[J].Trans CSAE,2005,21(1):1722
[3]史波林,庆兆珅,籍保平,等.应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究[J].光谱学与光谱分析,2009,29(3):665670.
[4]傅霞萍,应义斌,陆辉山,等.应用多种近红外建模方法分析梨的坚实度[J].光谱学与光谱分析,2007,27(5):911915.
[5]曾一凡,刘春生,孙旭东,等.可见/近红外光谱技术无损检测果实坚实度的研究[J].农业工程学报,2008,24(5):250.
[6]马本学,应义斌,饶秀勤,等.高光谱成像在水果内部品质无损检测中的研究进展[J].光谱学与光谱分析,2009,29(6):16111615.
[7]李民赞.光谱分析技术及其应用[M].北京:科学出版社,2006.
[8]郭恩有,刘木华,赵杰文,等.脐橙糖度的高光谱图像无损检测技术[J].农业机械学报,2008,39(5):9193.
[9]Peng YK,Lu RF.An LCTF-based multispectral imaging system for estimation of apple fruit firmness:Part I.Acquisition and characterization of scattering images[J].Trans ASAE,2006,49(1):259267.
[10]Peng YK,Lu RF.Prediction of apple fruit Firmness and soluble solids content using characteristics of multispectral scattering images[J].J Food Eng,2006,82:142152.
[11]Lu RF,Peng YK.Hyperspectral Scattering for assessing peach fruit firmness[J].Biosyst Eng,2006,93(2):161171.
[12]Peng YK,Lu RF.Modeling multispectral scattering profiles for prediction of apple fruit firmness[J].Am Soc Agric Eng,2005,48(1):235242.
[13]曹乐平.数字图像处理技术结合偏最小二乘法定量分析柑橘质量[J].食品科学,2009,30(14):200203.
[14]Peng YK,Lu RF.Analysis of spatially resolved hyperspectralscattering images for assessing apple fruit firmness and soluble solids content[J].Postharv Biol Technol,2007,48(2008):5262.
[2]Nourain J,应义斌,王剑平,等.Finite element models of wa-termelon and their applications[J].Trans CSAE,2005,21(1):1722
[3]史波林,庆兆珅,籍保平,等.应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究[J].光谱学与光谱分析,2009,29(3):665670.
[4]傅霞萍,应义斌,陆辉山,等.应用多种近红外建模方法分析梨的坚实度[J].光谱学与光谱分析,2007,27(5):911915.
[5]曾一凡,刘春生,孙旭东,等.可见/近红外光谱技术无损检测果实坚实度的研究[J].农业工程学报,2008,24(5):250.
[6]马本学,应义斌,饶秀勤,等.高光谱成像在水果内部品质无损检测中的研究进展[J].光谱学与光谱分析,2009,29(6):16111615.
[7]李民赞.光谱分析技术及其应用[M].北京:科学出版社,2006.
[8]郭恩有,刘木华,赵杰文,等.脐橙糖度的高光谱图像无损检测技术[J].农业机械学报,2008,39(5):9193.
[9]Peng YK,Lu RF.An LCTF-based multispectral imaging system for estimation of apple fruit firmness:Part I.Acquisition and characterization of scattering images[J].Trans ASAE,2006,49(1):259267.
[10]Peng YK,Lu RF.Prediction of apple fruit Firmness and soluble solids content using characteristics of multispectral scattering images[J].J Food Eng,2006,82:142152.
[11]Lu RF,Peng YK.Hyperspectral Scattering for assessing peach fruit firmness[J].Biosyst Eng,2006,93(2):161171.
[12]Peng YK,Lu RF.Modeling multispectral scattering profiles for prediction of apple fruit firmness[J].Am Soc Agric Eng,2005,48(1):235242.
[13]曹乐平.数字图像处理技术结合偏最小二乘法定量分析柑橘质量[J].食品科学,2009,30(14):200203.
[14]Peng YK,Lu RF.Analysis of spatially resolved hyperspectralscattering images for assessing apple fruit firmness and soluble solids content[J].Postharv Biol Technol,2007,48(2008):5262.