• Acta Optica Sinica
  • Vol. 38, Issue 10, 1010001 (2018)
Hongqiang Ma1、*, Shiping Ma1、*, Yuelei Xu1, Chao Lü2, and Mingming Zhu1
Author Affiliations
  • 1 Aeronautics Engineering College, Air Force Engineering University, Xi'an, Shaanxi 710038, China
  • 2 Unit 95876 of PLA, Shandan, Gansu 734100, China
  • show less
    DOI: 10.3788/AOS201838.1010001 Cite this Article Set citation alerts
    Hongqiang Ma, Shiping Ma, Yuelei Xu, Chao Lü, Mingming Zhu. Adaptive Image Denoising Based on Improved Stacked Sparse Denoising Auto-Encoder[J]. Acta Optica Sinica, 2018, 38(10): 1010001 Copy Citation Text show less
    Algorithm flow of DAE
    Fig. 1. Algorithm flow of DAE
    Network diagram of SSDA
    Fig. 2. Network diagram of SSDA
    Network diagram of SRDA
    Fig. 3. Network diagram of SRDA
    Network model of ASRDA
    Fig. 4. Network model of ASRDA
    Comparison of convergence effects
    Fig. 5. Comparison of convergence effects
    Comparison of denoising performance of different algorithms. (a) Noisy; (b) G-SRDA; (c) S&P-SRDA; (d) MC-SRDA; (e) ASRDA; (f) BM3D
    Fig. 6. Comparison of denoising performance of different algorithms. (a) Noisy; (b) G-SRDA; (c) S&P-SRDA; (d) MC-SRDA; (e) ASRDA; (f) BM3D
    Noisy typeG-SRDAS&P-SRDAS-SRDAMC-SRDAASRDABM3D
    G127.63/0.815625.39/0.750425.41/0.756127.44/0.807529.87/0.851729.88/0.8486
    G225.39/0.723323.13/0.619422.78/0.600325.38/0.717125.44/0.732125.39/0.7232
    S&P128.27/0.840634.90/0.985123.9/0.679526.62/0.800236.87/0.986319.50/0.4326
    S&P225.75/0.799831.66/0.966122.92/0.628423.79/0.734733.66/0.971113.71/0.1646
    S123.87/0.685124.45/0.697128.58/0.841124.91/0.702928.22/0.839619.40/0.4743
    S223.6/0.659623.85/0.664427.75/0.814724.24/0.671327.77/0.813616.64/0.3769
    P123.79/0.684524.44/0.742023.90/0.687724.26/0.672028.83/0.847927.13/0.8289
    P223.4/0.652023.77/0.656122.92/0.631023.40/0.646325.63/0.751720.61/0.7454
    U123.65/0.677024.11/0.673825.05/0.673924.14/0.681525.05/0.666916.98/0.3098
    U219.28/0.636819.41/0.636620.21/0.650019.88/0.644321.10/0.661014.13/0.3036
    Average24.46/0.721025.51/0.739124.80/0.701424.35/0.708328.25/0.812220.34/0.5208
    Table 1. Average PSNR/SSIM of the experimental results of different algorithms on the Set12 data set
    Hongqiang Ma, Shiping Ma, Yuelei Xu, Chao Lü, Mingming Zhu. Adaptive Image Denoising Based on Improved Stacked Sparse Denoising Auto-Encoder[J]. Acta Optica Sinica, 2018, 38(10): 1010001
    Download Citation