Skip to main content

Advertisement

Table 2 Summary of selected references applying hyperspectral imaging to seed viability and vigor detection

From: Hyperspectral imaging for seed quality and safety inspection: a review

Seed Spectral rangea Varieties Sample numbers Features Signal mode Data analysis strategies Main application type Classification result (highest accuracy) References
Spectra/image Extraction/selection methods Analysis level Classification/regression methods
Barley 900–1700 (1002–1626) 1 variety, 8 treatments 755 Spectra PCA, MNF Reflectance PWb prediction map and OWc (single kernels) Maximum likelihood multinomial, regression classifier Germination level detection 97% when single kernels grouped into the three categories Arngren et al. [28]
Corn 400–1000 (1000–2500) 3 varieties, 2 treatments 900 Spectra No Reflectance OW (single kernels) PLS-DA Viability prediction > 95.6% Ambrose et al. [27]
Cryptomeria japonica and Chamaecyparis obtuse 400–980 (1250–2500) 2 treatments of each kind of seed 2320 Spectra No Reflectance OW (single kernels) Spectral index Viability prediction 98.30% Matsuda et al. [31]
Cucumber 400–1000(blue, green and red LED induced region) 1 variety, 2 treatments 200 Spectra No Reflectance OW (single kernels), PW prediction map PLS-DA Viability prediction 100% Mo et al. [32]
Muskmelon 948–2498 1 variety, 4 treatments 288 Spectra VIP, SR, and SMC Reflectance OW (single kernels) PLS-DA Viability prediction 94.60% Kandpal et al. [30]
Norway spruce 400–1000 (1000–2500) 1 variety, 3 treatments 1606 Spectra and image L1-regularized logistic regression based feature selection Reflectance OW (single kernels) SVM Viability prediction > 93% Dumont et al. [29]
Pepper 400–1000(blue, green and red LED induced region) 1 variety, 2 treatments 600 Spectra No Reflectance OW (single kernels), PW prediction map PLS-DA Germination level detection > 85% Mo et al. [33]
Tree seeds 392–889 (424–879) 3 varieties, 8 treatments 600 Spectra LDA Reflectance OW (single kernels) LDA Germination level detection > 79% Nansen et al. [34]
Wheat, barley and sorghum 1000–2498 B: 3 varieties W: 3 varieties S: 2, varieties 6 treatments 1200 Spectra PCA Reflectance OW (single kernels), PW prediction map PLS-DA, PLSR Viability prediction R = 0.92 (PLS-DA) McGoverin et al. [35]
  1. aThe spectral range without brackets relates to the range acquisition of instrument, while the spectral range in brackets represents the spectral range for practical analysis
  2. bPW means pixel-wise analysis, which is the analysis on the pixels
  3. cOW means objective-wise analysis, which means the analysis on ROIs (ROI can be bulk, single kernel or self-defined)