Spectroscopy and Spectral Analysis, Volume. 42, Issue 6, 1792(2022)
Research on Non-Destructive Testing of Navel Orange Shelf Life Imaging Based on Hyperspectral Image and Spectrum Fusion
Figures & Tables(12)
Fig. 1. Hyperspectral image of navel orange sample
(a): Day 0 navel orange; (b): Day 7 navel orange; (c): Day 14 navel orange
Fig. 2. Comparison chart of representative spectra of navel oranges with different shelf life
Fig. 3. The prediction set classification results of RBF-kernel in LS-SVM
Fig. 4. The prediction set classification results of LIN-kernel in LS-SVM
Fig. 5. The prediction set classification results of LIN-kernel in LS-SVM
Table 1. PLS-DA model results based on spectral characteristics
View tableView in ArticleTable 1. PLS-DA model results based on spectral characteristics
输入变
量个数RMSEP Rp 误判率
/%预测集误判个数 第0天 第7天 第14天 176 0.29 0.94 8 3 0 3
Table 2. LS-SVM model results based on spectral characteristics
View tableView in ArticleTable 2. LS-SVM model results based on spectral characteristics
输入变
量个数核函数 参数 总误判
率/%预测集误判个数 第0天 第7天 第14天 176 LIN-Kernel γ=1.4 9.3 1 5 1 176 RBF-Kernel γ=59 078,
σ2=6 3595.33 2 1 1
Table 3. Results of PLS-DA model based on image features
View tableView in ArticleTable 3. Results of PLS-DA model based on image features
输入变
量个数RMSEP Rp 误判率
/%预测集误判个数 第0天 第7天 第14天 11 0.238 0.88 21.3 1 9 6
Table 4. LS-SVM model results based on image features
View tableView in ArticleTable 4. LS-SVM model results based on image features
输入变
量个数核函数 参数 总误判
率/%预测集误判个数 第0天 第7天 第14天 11 LIN-Kernel γ=3 795 20 0 9 6 11 RBF-Kernel γ=124,
σ2=17722.2 0 11 6
Table 5. Results of PLS-DA model based on mixed features
View tableView in ArticleTable 5. Results of PLS-DA model based on mixed features
输入变
量个数RMSEP Rp 误判率
/%预测集误判个数 第0天 第7天 第14天 187 0.2 0.97 1.3 0 1 0
Table 6. LS-SVM model results based on mixed features
View tableView in ArticleTable 6. LS-SVM model results based on mixed features
输入变
量个数核函数 参数 总误判
率/%预测集误判个数 第0天 第7天 第14天 187 LIN-Kernel γ=8.5 1.33 0 1 0 187 RBF-Kernel γ=24 810,
σ2=7 5952.67 0 2 0
Table 7. Result statistics of two qualitative discriminant models with different characteristics
View tableView in ArticleTable 7. Result statistics of two qualitative discriminant models with different characteristics
模型 不同类
型特征变量
个数核函数 参数 预测集误
判率/%LS-SVM 光谱 176 RBF-Kernel γ=59 078,
σ2=6 3595.3 LS-SVM 图像 11 LIN-Kernel γ=3 795 20 LS-SVM 融合 187 LIN-Kernel γ=8.5 1.33
Tools
Get Citation
Copy Citation Text
Yan-de LIU, Shun WANG. Research on Non-Destructive Testing of Navel Orange Shelf Life Imaging Based on Hyperspectral Image and Spectrum Fusion[J]. Spectroscopy and Spectral Analysis, 2022, 42(6): 1792
Paper Information
Category: Research Articles
Received: Apr. 24, 2021
Accepted: --
Published Online: Nov. 14, 2022
The Author Email: LIU Yan-de (jxliuyd@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20