Rapid prediction of moisture content of dehydrated prawns using online hyperspectral imaging system
Rapid prediction of moisture content of dehydrated prawns using online hyperspectral imaging system
复制标题
利用在线高光谱成像系统快速预测脱水虾的水分含量
DOI：
10.1016/j.aca.2012.03.038
复制
发表时间：
2012-05-13
影响因子：
6.2
通讯作者：
Liu, Kangsheng
中科院分区：
文献类型：
--
作者：
Wu, Di;Shi, Hui;Liu, Kangsheng
由于对虾的形状不是圆形的，光谱仪器无法在不包含背景信息的情况下测量整个对虾的光谱。本研究利用380-1100 nm光谱范围内的在线高光谱成像系统，对不同脱水程度的对虾水分含量进行了检测。在不同的脱水时期，获得了对虾的高光谱图像。然后分别基于“手动虾掩模”和“自动虾掩模”从高光谱图像中提取虾的光谱。分别采用偏最小二乘回归（PLSR）和最小二乘支持向量机（LS-SVM）对光谱数据进行分析，建立校正模型。首次将连续投影算法（SPA）应用于高光谱图像分析中的最优波长选择。在482个波长中，只有12个波长（428、445、544、569、629、672、697、760、827、917、958和999 nm）被SPA选择为用于水分预测的最佳波长。基于这些最佳波长，建立了多元线性回归（MLR）校准模型，并用于获得每只对虾的水分分布。本研究的总体结果揭示了高光谱成像作为一种客观的和非破坏性的方法来获得的虾，形状不圆的水分含量和分布的潜力。(c)2012爱思唯尔有限公司版权所有。
Because the shape of prawn is not round, spectroscopy instruments cannot measure the spectra of the whole prawn without containing background information. In this study, an online hyperspectral imaging system in the spectral region of 380-1100 nm was developed to determine the moisture content of prawns at different dehydrated levels. Hyperspectral images of prawns were acquired at different dehydration periods. The spectra of prawns then were extracted from hyperspectral images based on 'Manual Prawn Mask' and 'Automatic Prawn Mask', respectively. Spectral data were analyzed using partial least squares regression (PLSR) and least-squares support vector machines (LS-SVM) to establish the calibration models, respectively. Successive projections algorithm (SPA) was first applied for the optimal wavelength selection in the hyperspectral image analysis. Out of 482 wavelengths, only twelve wavelengths (428, 445, 544, 569, 629, 672, 697, 760, 827, 917, 958, and 999 nm) were selected by SPA as the optimum wavelengths for moisture prediction. Based on these optimum wavelengths, a multiple linear regression (MLR) calibration model was established and used to obtain the moisture distribution of each prawn. The overall results of this study revealed the potentiality of hyperspectral imaging as an objective and non-destructive method to obtain the content and distribution of moisture of prawns whose shapes are not round. (c) 2012 Elsevier B.V. All rights reserved.