基于近红外高光谱成像技术的涩柿SSC含量无损检测

发布时间：2018-02-02 07:04

本文关键词： 近红外高光谱成像可溶性固形物柿子无损检测　出处：《食品与机械》2017年10期 　论文类型：期刊论文

【摘要】：对150个涩柿采集900~1 700nm波段的近红外高光谱图像信息,利用蒙特卡罗—无信息变量消除(MC-UVE)和连续投影算法(SPA)对感兴趣区域光谱进行波长优选。通过MC-UVE-SPA优选出924.69,928.05,1 112.72,1 270.91,1 365.3,1 402.42,1 453.06,1 547.69nm 8个特征波长,对应的光谱反射率作为柿子可溶性固性物含量(SSC)检测的偏最小二乘回归(PLSR)检测模型输入,其预测集相关系数rpre=0.942,预测集均方根误差RMSEP=1.009°Brix。结果表明,MC-UVE-SPA可以有效提取与柿子SSC含量相关的特征信息,从而保留较少的波长建立较好的预测模型。
[Abstract]:150 astringent persimmons were collected from near infrared hyperspectral images in the wavelength of 900,700 nm. Elimination of MC-UVEand continuous projection algorithm using Monte Carlo and Information Free variables (spa). The wavelength of the region of interest spectrum was optimized. 924.69 was selected by MC-UVE-SPA. The characteristic wavelengths of 928.05 (1 1112.72) (1 270.91) 1 365.3 (1 402.42N) 1 453.06 (1 547.69 nm) were measured. The corresponding spectral reflectance was used as the input of the partial least squares regression model for the determination of soluble solids in persimmon, and the correlation coefficient of the prediction set was rpre=0.942. The root mean square error of prediction set RMSEP=1.009 掳Brix. the results showed that MC-UVE-SPA could effectively extract the characteristic information related to the content of SSC in persimmon. Thus, a better prediction model is established by reserving less wavelengths.
【作者单位】：福建农林大学机电工程学院;华中农业大学工学院;
【基金】：福建省自然科学基金(编号:2017J05041) 福建农林大学现代农林装备及其自动化创新平台(编号:612014017)
【分类号】：O657.33;TS255.7
【正文快照】： (1.College of Mechanical and Electronic Engineering,Fujian Agriculture and Forestry University,Fuzhou,Fujian,350002,China;2.College of Engineering,Huazhong Agricultural University,Wuhan,Hubei 430070,China)柿子具有较高的经济和营养价值,深受人们的喜爱[1]。

【相似文献】