Skip to main content

Advertisement

Table 4 Summary of selected references applying hyperspectral imaging to seed fungus damage 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 (1000–1600) 1 variety, 2 fungi 6300 Spectra and image PCA Reflectance PWb prediction map and OWc (single kernels) LDA, QDA, MDA Fungus (Ochratoxin A and Penicillium) damage detection > 82% Senthilkumar et al. [43]
Canola 960–1700 (1000–1600) 1 variety, 2 fungi, 3300 Spectra and image PCA Reflectance OW (single kernels) LDA, QDA, MDA Fungus (Aspergillus glaucus and Penicillium spp.) damage detection > 90% Senthilkumar et al. [44]
Corn 900–1700 3 varieties, 5 treatments 585 Spectra No Reflectance OW (single kernels), PW prediction map PLS-DA Fungus (Aflatoxin B1) damage detection 96.90% Kandpal et al. [49]
Corn 400–900 for fluorescence 1 variety, 3 treatments 492 Spectra No Reflectance PW spectra spectral index Fungus (Aflatoxin A. flavus) damage detection 93% Yao et al. [54]
Corn 400–701 for fluorescence, 461–877 for reflectance 1 variety, 3 treatments 300 Spectra PCA Reflectance OW (single kernels), PW PCA LS-SVM, KNN Fungus (Aflatoxin A. flavus) damage detection > 91% (KNN) Zhu et al. [53]
Hick peas, green peas, lentils, pinto beans and kidney beans 960–1700 (1000–1600) 5 different pulses, 2 fungi Over 10,000 kernels Spectra and image PCA Reflectance OW (single kernels), PW PCA LDA, QDA Fungus (Penicillium commune Thom, C. and A. flavus Link, J.) damage detection 96%-100% Karuppiah et al. [48]
Maize 850–2800 (1000–2500) 4 varieties 120 Spectra PCA Reflectance OW (single kernels), PW prediction map SVM, SVR Fungus (Aflatoxin B1) damage detection R2 = 0.77 Chu et al. [63]
Maize 1000–2500 1 variety, 5 treatments 150 Spectra PCA, FDA Reflectance OW (single kernels), PW PCA FDA Fungus (Aflatoxin B1) damage detection 88% Wang et al. [58]
Maize 1000–2500 1 variety, 5 treatments 120 Spectra PCA Reflectance OW (single kernels) FDA Fungus (Aflatoxin B1) damage detection 98% Wang et al. [41]
Maize 960–1662 (1000–2498) 1 variety, 3 treatments 36 Spectra No Reflectance OW (single kernels), PW prediction map PLS-DA Fungus (Fusarium) damage detection 77% (PLS-DA) Williams et al. [60]
Maize 1000–2498 1 variety, nine treatments 160 Spectra PCA, variable importance plots Reflectance OW (single kernels), PW PCA and prediction map PLSR Fungus damage detection R2 = 0.87 Williams et al. [59]
maize 400–700 1 variety, 2 fungi, 3 treatments 180 Spectra No Reflectance OW (single kernels) discriminant analysis Fungus (Toxigenic and atoxigenic A. flavus) damage detection 94.40% Yao et al. [56]
Maize 400–1000 12 varieties, 4 fungi Unknown Spectra PCA Reflectance OW (bulk samples), PW PCA ANOVA, Fisher’s LSD test Fungus (Aspergillus strains) damage detection Fisher’s LSD test Del Fiore et al. [51]
Oat50 1000–2500 1 variety, 4 treatments 180 Spectra PLSR Reflectance OW (single kernels), PW prediction map PLSR, PLS-LDA Fungus (Fusarium) damage detection R2 = 0.8 Tekle et al. [61]
Peanut 970–2570 (1000–2000) 1 variety, 2 treatments 149 Spectra PCA Reflectance OW (single kernels), PW prediction map PCA Moldy kernel detection 98.73% Jiang et al. [50]
Peanut 967–2499 1 variety, 2 treatments More than 10,000 pixels Spectra ANOVA, NWFE Reflectance OW (single kernels), PW prediction map SVM Fungus (Aflatoxin) damage detection > 94% Qiao et al. [45]
Rice 400–1000 1 variety, 6 treatments 210 Spectra No Reflectance OW (bulk samples) SOM, PLSR Fungus (Aspergillus) damage detection R2 = 0.97 Siripatrawan and Makino [62]
Watermelon 948–2016 1 variety, 2 treatments 96 Spectra Intermediate PLS (iPLS) Reflectance OW (single kernels) PW prediction map PLS-DA, LS-SVM Fungus (Cucumber green mottle mosaic virus) damage detection 83.3% (LS-SVM) Lee et al. [47]
Watermelon 400–1000 1 variety, 2 treatments 336 Spectra Intermediate PLS (iPLS) Reflectance OW (single kernels), PW prediction map PLS-DA, LS-SVM Fungus (Acidovorax citrulli) damage detection > 90% Lee et al. [46]
Wheat 528–1785 4 varieties, 2 fungi 803 Spectra PCA Reflectance OW (single kernels), PW spectra LDA Fungus (Fusarium) damage detection > 91% Barbedo et al. [55]
Wheat 528–1785 33 varieties, 3 treatments 10,862 Spectra No Reflectance OW (single kernels), PW spectra spectral index Fungus (Fusarium head blight) damage detection 81% Barbedo et al. [52]
Wheat 400–1000 (450–950) 1 variety, 3 treatments 800 Spectra and image PCA, STEPDISC Reflectance OW (single kernels) LDA Fungus (Fusarium) damage detection 92% Shahin and Symons [42]
Wheat 900–1700 (1000–1600) 1 variety, 3 fungi 1200 Spectra and image STEPDISC, GLCM, GLRM, PCA Reflectance OW (single kernels) LDA, QDA, MDA Fungus (Penicillium spp., Aspergillus glaucus group, and Aspergillus niger) damage detection > 95% Singh et al. [64]
Wheat 1000–1700 (1013–1650) 3 varieties Spectra PCA Reflectance OW (bulk, single kernels), PW PCA PLS-DA, iPLS-DA Fungus (Fusarium) damage detection 99% Serranti et al. [57]
  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)