• Spectroscopy and Spectral Analysis
  • Vol. 41, Issue 2, 599 (2021)
Peng ZHAO1、1, Jin-cheng HAN1、1, and Cheng-kun WANG1、1
Author Affiliations
  • 1[in Chinese]
  • 11. School of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2021)02-0599-07 Cite this Article
    Peng ZHAO, Jin-cheng HAN, Cheng-kun WANG. Wood Species Classification With Microscopic Hyper-Spectral Imaging Based on I-BGLAM Texture and Spectral Fusion[J]. Spectroscopy and Spectral Analysis, 2021, 41(2): 599 Copy Citation Text show less
    Two-dimensional grayscale images of eight sample woods(a): Red oak; (b): Merbau; (c): Talisai; (d): African padauk; (e): Basralocus; (f): Teak; (g): Silky oak; (h): Medang
    Fig. 1. Two-dimensional grayscale images of eight sample woods
    (a): Red oak; (b): Merbau; (c): Talisai; (d): African padauk; (e): Basralocus; (f): Teak; (g): Silky oak; (h): Medang
    Image preprocessing(a): Feature band selection; (b): Image fusion
    Fig. 2. Image preprocessing
    (a): Feature band selection; (b): Image fusion
    Pixel value compression results(a): The original image; (b): Compressed image
    Fig. 3. Pixel value compression results
    (a): The original image; (b): Compressed image
    I-BGLAM characteristic curve
    Fig. 4. I-BGLAM characteristic curve
    Average spectral curves of 8 wood samples
    Fig. 5. Average spectral curves of 8 wood samples
    Flow chart of the experimental process
    Fig. 6. Flow chart of the experimental process
    NumberChineseLatin
    1美国红橡Quercus rubra
    2印尼菠萝格Intsia bijuga
    3非洲卡斯拉Terminalia catappa
    4红花梨Terocarpus angolensis
    5南美柚木Dicorynia guianensis
    6水煮柚Tectona grandis L.F.
    7桦木Grevillea robusta
    8香樟木Cinnamomum camphora
    Table 1. Details of the sample wood
    MethodTexture/%Spectrum/%Texture+Spectrum/%
    187.587.5100
    288.5492.71100
    385.4281.2598.96
    486.458389.5898.96
    581.2584.38100
    Table 2. Classification accuracy using different features
    MethodAccuracy/%
    本文方法100
    GLCM76.04
    SPPE64.58
    文献[19]SPPD+I-BGLAM91.67
    Fuzzy+SPPD+I-BGLAM87.5
    文献[18]GA
    GA+KDA
    68.75
    48.96
    Table 3. The highest classification accuracy rate of this article and other methods
    Peng ZHAO, Jin-cheng HAN, Cheng-kun WANG. Wood Species Classification With Microscopic Hyper-Spectral Imaging Based on I-BGLAM Texture and Spectral Fusion[J]. Spectroscopy and Spectral Analysis, 2021, 41(2): 599
    Download Citation