• Laser & Optoelectronics Progress
  • Vol. 57, Issue 14, 141017 (2020)
Yiming Fang1, Fan Yang2, and Xiaoqin Li1、*
Author Affiliations
  • 1Key Laboratory of Modern Agricultural Engineering, Tarim University, Alaer, Xinjiang 843300, China
  • 2Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology, Zhejiang A & F University, Hangzhou, Zhejiang 311300, China;
  • show less
    DOI: 10.3788/LOP57.141017 Cite this Article Set citation alerts
    Yiming Fang, Fan Yang, Xiaoqin Li. Detection of Damage on the Surface of Korla Fragrant Pear Using Hyperspectral Images[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141017 Copy Citation Text show less
    Schematic of hyperspectral imaging device
    Fig. 1. Schematic of hyperspectral imaging device
    Collected hyperspectral images of typical Korla pear samples at different wavelengths. (a) 400 nm; (b) 494 nm; (c) 587 nm; (d) 681 nm; (e) 774 nm; (f) 868 nm
    Fig. 2. Collected hyperspectral images of typical Korla pear samples at different wavelengths. (a) 400 nm; (b) 494 nm; (c) 587 nm; (d) 681 nm; (e) 774 nm; (f) 868 nm
    Spectra of Korla pear surfaces and background areas. (a) Spectra; (b) average value and variance of spectral curves
    Fig. 3. Spectra of Korla pear surfaces and background areas. (a) Spectra; (b) average value and variance of spectral curves
    Hyperspectral images and their histogram plots at three wavelengths. (a) 433 nm; (b) 631 nm; (c) 863 nm
    Fig. 4. Hyperspectral images and their histogram plots at three wavelengths. (a) 433 nm; (b) 631 nm; (c) 863 nm
    Results of OTSU threshold segmentation and morphological analysis for hyperspectral images at three wavelengths. (a) 433 nm; (b) 631 nm; (c) 863 nm
    Fig. 5. Results of OTSU threshold segmentation and morphological analysis for hyperspectral images at three wavelengths. (a) 433 nm; (b) 631 nm; (c) 863 nm
    The first six primary component images obtained by PCA. (a) PC 1; (b) PC 2; (c) PC 3; (d) PC 4; (e) PC 5; (f) PC 6
    Fig. 6. The first six primary component images obtained by PCA. (a) PC 1; (b) PC 2; (c) PC 3; (d) PC 4; (e) PC 5; (f) PC 6
    Results of the ratio enhancement and image segmentation. (a) Result of ratio enhancement; (b) result of threshold segmentation; (c) result of morphological calculation
    Fig. 7. Results of the ratio enhancement and image segmentation. (a) Result of ratio enhancement; (b) result of threshold segmentation; (c) result of morphological calculation
    Type ofsampleNumber ofsamplesDetection result
    IntactDamaged
    Intact sample40355
    Damaged sample40040
    Table 1. Detection results of surface damage of fragrant pear using hyperspectral images
    Yiming Fang, Fan Yang, Xiaoqin Li. Detection of Damage on the Surface of Korla Fragrant Pear Using Hyperspectral Images[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141017
    Download Citation