• Laser & Optoelectronics Progress
  • Vol. 56, Issue 19, 191005 (2019)
Haijun Wang1、*, Tao Jin1, and Ke Neimule Men2
Author Affiliations
  • 1Department of Mathematics and Computer Engineering, Ordos Institute of Technology, Ordos, Inner Mongolia 0 17000, China
  • 2Department of Information Engineering, Ordos Institute of Technology, Ordos, Inner Mongolia 0 17000, China
  • show less
    DOI: 10.3788/LOP56.191005 Cite this Article Set citation alerts
    Haijun Wang, Tao Jin, Ke Neimule Men. Application of FA-LMBP Hybird Neural Network Algorithm in Image Compression[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191005 Copy Citation Text show less
    Basic BP algorithm training curve
    Fig. 1. Basic BP algorithm training curve
    LMBP algorithm training curve
    Fig. 2. LMBP algorithm training curve
    FA-LMBP algorithm flow
    Fig. 3. FA-LMBP algorithm flow
    Data matrix of 128 pixel×128 pixel Lena original image
    Fig. 4. Data matrix of 128 pixel×128 pixel Lena original image
    Normalized partial sample matrix
    Fig. 5. Normalized partial sample matrix
    BP model structure used in compression model
    Fig. 6. BP model structure used in compression model
    Comparison of decompression and reconstruction effects of different BP algorithms for Lena training images when K=2. (a) Original image; (b) BP reconstruction image; (c) LMBP reconstruction image; (d) FA-LMBP reconstruction image
    Fig. 7. Comparison of decompression and reconstruction effects of different BP algorithms for Lena training images when K=2. (a) Original image; (b) BP reconstruction image; (c) LMBP reconstruction image; (d) FA-LMBP reconstruction image
    Comparison of decompression and reconstruction effects of different BP algorithms for Cameraman testing images when K=2. (a) Original image; (b) BP reconstruction image; (c) LMBP reconstruction image; (d) FA-LMBP reconstruction image
    Fig. 8. Comparison of decompression and reconstruction effects of different BP algorithms for Cameraman testing images when K=2. (a) Original image; (b) BP reconstruction image; (c) LMBP reconstruction image; (d) FA-LMBP reconstruction image
    Comparison of decompression and reconstruction effects of different BP algorithms for Brain testing images when K=2. (a) Original image; (b) BP reconstruction image; (c) LMBP reconstruction image; (d) FA-LMBP reconstruction image
    Fig. 9. Comparison of decompression and reconstruction effects of different BP algorithms for Brain testing images when K=2. (a) Original image; (b) BP reconstruction image; (c) LMBP reconstruction image; (d) FA-LMBP reconstruction image
    AlgorithmLenaCameramanBrain
    PSNRSSIMPSNRSSIMPSNRSSIM
    BP10.15380.04239.37610.03567.08350.0243
    LMBP28.0590.863525.00340.756522.79340.7541
    FA-LMBP28.5290.882926.70530.806924.76110.8148
    Table 1. Reconstruction image evaluation of compression models based on different algorithms when K=2
    AlgorithmLenaCameramanBrain
    PSNRSSIMPSNRSSIMPSNRSSIM
    BP9.85990.03739.17890.02617.15210.0208
    LMBP27.28780.862724.53020.768522.49390.711
    FA-LMBP27.36330.863825.45250.812423.32010.8193
    Table 2. Reconstruction image evaluation of compression models based on different algorithms when K=4
    Haijun Wang, Tao Jin, Ke Neimule Men. Application of FA-LMBP Hybird Neural Network Algorithm in Image Compression[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191005
    Download Citation