• Spectroscopy and Spectral Analysis
  • Vol. 41, Issue 1, 210 (2021)
Hai-yong WENG1、1、*, Jun-kun HUANG1、1, Liang WAN1、1, and Da-peng YE1、1
Author Affiliations
  • 1[in Chinese]
  • 11. College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou 350002, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2021)01-0210-06 Cite this Article
    Hai-yong WENG, Jun-kun HUANG, Liang WAN, Da-peng YE. Rapidly Detecting Chlorophyll Content in Oilseed Rape Based on Spectral Reconstruction and Its Device Development[J]. Spectroscopy and Spectral Analysis, 2021, 41(1): 210 Copy Citation Text show less
    The handheld multispectral imaging system (a), the layout of LEDs (b), the central wavelength of each LED (c), the software (d) and the in-house hyperspectral imaging system (e)
    Fig. 1. The handheld multispectral imaging system (a), the layout of LEDs (b), the central wavelength of each LED (c), the software (d) and the in-house hyperspectral imaging system (e)
    The mean spectral reflectance measured by the indoor hyperspectral imaging system (a) and the handheld multispectral imaging system (b), the original hyperspectral reflectance and reconstructed hyperspectral reflectance (c), the correlation coefficient between the original hyperspectral reflectance and reconstructed hyperspectral reflectance (d)
    Fig. 2. The mean spectral reflectance measured by the indoor hyperspectral imaging system (a) and the handheld multispectral imaging system (b), the original hyperspectral reflectance and reconstructed hyperspectral reflectance (c), the correlation coefficient between the original hyperspectral reflectance and reconstructed hyperspectral reflectance (d)
    The performance of PLSR model based on spectral reflectance at 225 wavelengths in visible range measured by the indoor hyperspectral imaging system (a) and the spectral reflectance at four wavelengths in visible range measured by the handheld multispectral imaging system (b)
    Fig. 3. The performance of PLSR model based on spectral reflectance at 225 wavelengths in visible range measured by the indoor hyperspectral imaging system (a) and the spectral reflectance at four wavelengths in visible range measured by the handheld multispectral imaging system (b)
    The impact of different numbers of standard samples on the predicting ability of PLSR model (a) and the performance of PLSR model based on the reconstructed hyperspectra using 5 standard samples (b)
    Fig. 4. The impact of different numbers of standard samples on the predicting ability of PLSR model (a) and the performance of PLSR model based on the reconstructed hyperspectra using 5 standard samples (b)
    Hai-yong WENG, Jun-kun HUANG, Liang WAN, Da-peng YE. Rapidly Detecting Chlorophyll Content in Oilseed Rape Based on Spectral Reconstruction and Its Device Development[J]. Spectroscopy and Spectral Analysis, 2021, 41(1): 210
    Download Citation