• Laser & Optoelectronics Progress
  • Vol. 56, Issue 11, 113001 (2019)
Libo Rao1, Tao Pang1, Ranshi Ji1, Xiaoyan Chen2、3、*, and Jie Zhang2
Author Affiliations
  • 1 College of Mechanical and Electrical Engineering, Sichuan Agricultural University, Yaan, Sichuan 625014, China
  • 2 College of Information Engineering, Sichuan Agricultural University, Yaan, Sichuan 625014, China
  • 3 Sichuan Provincial Key Laboratory of Agricultural Information Engineering, Sichuan Agricultural University, Yaan, Sichuan 625014, China
  • show less
    DOI: 10.3788/LOP56.113001 Cite this Article Set citation alerts
    Libo Rao, Tao Pang, Ranshi Ji, Xiaoyan Chen, Jie Zhang. Firmness Detection for Apples Based on Hyperspectral Imaging Technology Combined with Stack Autoencoder-Extreme Learning Machine Method[J]. Laser & Optoelectronics Progress, 2019, 56(11): 113001 Copy Citation Text show less
    Structural diagram of hyperspectral imaging system
    Fig. 1. Structural diagram of hyperspectral imaging system
    Original spectrum of pixel points
    Fig. 2. Original spectrum of pixel points
    Basic network structure of ELM
    Fig. 3. Basic network structure of ELM
    Network structures of basic auto-encoder and SAE-ELM. (a) Basic auto-encoder; (b) SAE-ELM
    Fig. 4. Network structures of basic auto-encoder and SAE-ELM. (a) Basic auto-encoder; (b) SAE-ELM
    Flow chart of training in SAE-ELM
    Fig. 5. Flow chart of training in SAE-ELM
    Scatter plots of prediction and measurements for samples in calibration set and prediction set.(a) SAE-ELM (18); (b) ELM
    Fig. 6. Scatter plots of prediction and measurements for samples in calibration set and prediction set.(a) SAE-ELM (18); (b) ELM
    SetNumber ofsamplesMin /NMax /NMean /NBias
    Total12628.97555.90036.4384.147
    Calibration9028.97555.90036.7204.579
    Prediction3630.80044.50035.7332.717
    Table 1. Statistics of apple firmness in calibration set and prediction set
    IndexIndexCalibrationPrediction
    RC2RRMSECRP2RRMSEPRRPD
    ELMFull spectral0.84421.79980.70991.44271.883
    ELMOptimal spectral0.89401.44450.73451.62971.968
    SAE-ELM(15)Full spectral0.83471.85170.73351.38281.965
    SAE-ELM(16)Full spectral0.82851.88600.68661.49941.812
    SAE-ELM(17)Full spectral0.80751.99840.62521.63981.657
    SAE-ELM (18)Full spectral0.83991.82220.77031.28372.116
    SAE-ELM (19)Full spectral0.86331.68360.70971.44321.882
    SAE-ELM (20)Full spectral0.83621.84310.66011.56181.740
    SAE-ELM(21)Full spectral0.86741.62840.74401.35532.004
    SAE-ELM(22)Full spectral0.85381.74120.72251.41111.925
    Table 2. Calibration and prediction results of apple firmness using ELM and SAE-ELM
    Libo Rao, Tao Pang, Ranshi Ji, Xiaoyan Chen, Jie Zhang. Firmness Detection for Apples Based on Hyperspectral Imaging Technology Combined with Stack Autoencoder-Extreme Learning Machine Method[J]. Laser & Optoelectronics Progress, 2019, 56(11): 113001
    Download Citation