• Laser & Optoelectronics Progress
  • Vol. 55, Issue 12, 121005 (2018)
Lihua Wang1、2, Zhengzheng Tu2、*, and Zeliang Wang1
Author Affiliations
  • 1 School of Information Engineering, Huangshan University, Huangshan, Anhui 245041, China
  • 2 School of Computer Science and Technology, Anhui University, Hefei, Anhui 230601, China
  • show less
    DOI: 10.3788/LOP55.121005 Cite this Article Set citation alerts
    Lihua Wang, Zhengzheng Tu, Zeliang Wang. Image Saliency Detection Based on Manifold Regularized Random Walk[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121005 Copy Citation Text show less
    Flow chart of proposed algorithm
    Fig. 1. Flow chart of proposed algorithm
    Global graph illustration
    Fig. 2. Global graph illustration
    Comparison results between initial saliency maps and final saliency maps. (a) Input images; (b) initial saliency maps; (c) final saliency maps; (d) ground truth
    Fig. 3. Comparison results between initial saliency maps and final saliency maps. (a) Input images; (b) initial saliency maps; (c) final saliency maps; (d) ground truth
    Local regular graph illustration
    Fig. 4. Local regular graph illustration
    PR curves of proposed method and AMC on three datasets. (a) ASD dataset; (b) SED dataset; (c) MSRA10K dataset
    Fig. 5. PR curves of proposed method and AMC on three datasets. (a) ASD dataset; (b) SED dataset; (c) MSRA10K dataset
    (a) PR curves and (b) F-measure values of all methods on ASD dataset
    Fig. 6. (a) PR curves and (b) F-measure values of all methods on ASD dataset
    (a) PR curves and (b) F-measure values of all methods on MSRA10K dataset
    Fig. 7. (a) PR curves and (b) F-measure values of all methods on MSRA10K dataset
    (a) PR curves and (b) F-measure values of all methods on SED dataset
    Fig. 8. (a) PR curves and (b) F-measure values of all methods on SED dataset
    Visual comparisons between all methods
    Fig. 9. Visual comparisons between all methods
    Lihua Wang, Zhengzheng Tu, Zeliang Wang. Image Saliency Detection Based on Manifold Regularized Random Walk[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121005
    Download Citation