Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Image denoising method based on a deep convolution neural network

© The Institution of Engineering and Technology
Received 26/04/2017, Accepted 12/11/2017, Revised 29/07/2017, Published 16/11/2017

Image denoising is still a challenging problem in image processing. The authors propose a novel image denoising method based on a deep convolution neural network (DCNN). Different from other learning-based methods, the authors design a DCNN to achieve the noise image. Thus, the latent clear image can be achieved by separating the noise image from the contaminated image. At the training stage, the gradient clipping scheme is employed to prevent gradient explosions and enables the network to converge quickly. Experimental results demonstrate that the proposed denoising method can achieve a better performance compared with the state-of-the-art denoising methods. Also, the results indicate that the denoising method has the ability of suppressing different noises with different noise levels by means of one single denoising model.

Inspec keywords: gradient methods; feedforward neural nets; convergence of numerical methods; image denoising

Other keywords: training stage; DCNN; noise levels; gradient clipping scheme; contaminated image; deep convolution neural network; image denoising method; latent clear image; single denoising model

Subjects: Computer vision and image processing techniques; Neural computing techniques; Interpolation and function approximation (numerical analysis); Optical, image and video signal processing; Interpolation and function approximation (numerical analysis)

References

    1. 1)
      • 25. Wenzhe, S., Jose, C., Ferenc, H., et al: ‘Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network’. Computer Vision and Pattern Recognition, 2016, vol. 12, pp. 27–30.
    2. 2)
      • 23. Xie, J., Xu, L., Chen, E.: ‘Image denoising and inpainting with deep neural networks’. Advances in Neural Information Processing Systems, 2012, vol. 1, pp. 341–349.
    3. 3)
      • 39. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, arXiv:1409.1556, 2014.
    4. 4)
      • 38. Jia, Y., Shelhamer, E., Donahue, J., et al: ‘Caffe: convolutional architecture for fast feature embedding’, 2014, arXiv:1408.5093.
    5. 5)
      • 30. Huang, D.A., Kang, L.W., Wang, Y.C.F., et al: ‘Self-learning based image decomposition with applications to single image denoising’, IEEE Trans. Multimed., 2013, 16, (1), pp. 83–93.
    6. 6)
      • 28. Koziarski, M., Cyganek, B.: ‘Deep neural image denoising’. Int. Conf. Computer Vision and Graphics, 2016, pp. 163–173.
    7. 7)
      • 5. Donoho, L.: ‘De-noising by soft-thresholding’, IEEE Trans. Inf. Theor., 1995, 1, (3), pp. 613–627.
    8. 8)
      • 15. Luo, E., Chan, S.H., Nguyen, T.Q.: ‘Adaptive image denoising by mixture adaptation’, IEEE Trans. Image Process., 2016, 6, (10), pp. 4489–4503.
    9. 9)
      • 34. Razvan, P., Tomas, M., Yoshua, B.: ‘Understanding the exploding gradient problem’. Tech. Rep., Université De Montréal, 2012, arXiv:arXiv:1211.5063.
    10. 10)
      • 8. Elad, M., Aharon, M.: ‘Image denoising via sparse and redundant representations over learned dictionaries’, IEEE Trans. Image Process., 2006, 3, (12), pp. 3736–3745.
    11. 11)
      • 13. Ji, H., Liu, C., Shen, Z., et al: ‘Robust video denoising using low rank matrix completion’. Computer Vision and Pattern Recognition, 2010, vol. 2, pp. 1791–1798.
    12. 12)
      • 11. Xu, J., Zhang, L., Zuo, W., et al: ‘Patch group based nonlocal self-similarity prior learning for image denoising’. Int. Conf. Computer Vision, 2015, vol. 6, pp. 244–252.
    13. 13)
      • 40. Vedaldi, A., Lenc, K., Matconvnet, C.: ‘Convolutional neural networks for matlab’, CoRR, abs/1412.4564, 2014.
    14. 14)
      • 7. Starck, J.L., Candés, E.J., Donoho, D.L.: ‘The curvelet transform for image denoising’, IEEE Trans. Image Process., 2002, 1, (6), pp. 670–684.
    15. 15)
      • 12. Dabov, K., Foi, A., Katkovnik, V., et al: ‘Image denoising by sparse 3-D transform-domain collaborative filtering’, IEEE Trans. Image Process., 2007, 6, (8), pp. 2080–2095.
    16. 16)
      • 42. Martin, D., Fowlkes, C., Tal, D., et al: ‘A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics’. Int. Conf. on Computer Vision, 2001, vol. 2, pp. 416–423.
    17. 17)
      • 21. Jain, V., Seung, S.: ‘Natural image denoising with convolutional networks’. Advances in Neural Information Processing Systems, 2009, pp. 769–776.
    18. 18)
      • 43. Szegedy, C., Liu, W., Jia, Y., et al: ‘A going deeper with convolutions’, 2015, pp. 1–9.
    19. 19)
      • 27. Wang, X., Tao, Q., Wang, L., et al: ‘Deep convolutional architecture for natural image denoising’. Int. Conf. Wireless Communications and Signal Processing, 2015, vol. 5, issue 53, pp. 1–4.
    20. 20)
      • 14. Gu, S., Zhang, L., Zuo, W., et al: ‘Weighted nuclear norm minimization with application to image denoising’. Computer Vision and Pattern Recognition, 2014, vol. 6, pp. 2862–2869.
    21. 21)
      • 32. Brunet, D., Vrscay, E.R., Wang, Z.: ‘The use of residuals in image denoising’. Int. Conf. Image Analysis and Recognition, 2009, vol. 5627, pp. 1–12.
    22. 22)
      • 29. Lefkimmiatis, S.: ‘Non-local color image denoising with convolutional neural networks’, arXiv, 2016.
    23. 23)
      • 35. Tomas, M.: ‘Statistical language models based on neural networks’. PhD thesis, Brno University of Technology, 2012.
    24. 24)
      • 16. Fei, C., Lei, Z., Huimin, Y.: ‘External patch prior guided internal clustering for image denoising’. Int. Conf. Computer Vision, 2015, vol. 6, pp. 7–13.
    25. 25)
      • 2. Perona, P., Malik, J.: ‘Scale-space and edge detection using anisotropic diffusion’, IEEE Trans. Pattern Anal. Mach. Intell., 1990, 1, (7), pp. 629–639.
    26. 26)
      • 31. Boaventura, M.: ‘A decomposition and noise removal method combining diffusion equation and wave atoms for textured images’, Math. Probl. Eng., 2010, 2010, pp. 242–256.
    27. 27)
      • 41. Yang, J., Wright, J., Huang, T.S., et al: ‘Image superresolution via sparse representation’, IEEE Trans. Image Process., 2010, 5, (10), pp. 2861–2873.
    28. 28)
      • 37. Szegedy, C., Ioffe, S., Vanhoucke, V., et al: ‘Inceptionv4, inception-resnet and the impact of residual connections on learning’, arXiv:1602.07261, 2016.
    29. 29)
      • 22. Burger, H.C., Schuler, C.J., Harmeling, S.: ‘Image denoising: can plain neural networks compete with BM3D?’. Computer Vision and Pattern Recognition, 2012, pp. 2392–2399.
    30. 30)
      • 24. Dong, C., Loy, C.C., He, K., et al: ‘Learning a deep convolutional network for image super-resolution’. European Conf. Computer Vision, 2014, pp. 184–199.
    31. 31)
      • 18. Yuan, X., Shuhang, G., Yan, L., et al: ‘Weighted schatten p-norm minimization for image denoising and background subtraction’, IEEE Trans. Image Process., 2016, 8, (10), pp. 4842–4857.
    32. 32)
      • 6. Chang, S.G., Yu, B., Vetterli, M.: ‘Adaptive wavelet thresholding for image denoising and compression’, IEEE Trans. Image Process., 2000, 1, (9), pp. 1532–1546.
    33. 33)
      • 19. Burger, H.C., Schuler, C., Harmeling, S.: ‘Learning how to combine internal and external denoising methods’. Pattern Recognition, 2013, pp. 121–130.
    34. 34)
      • 20. Chen, Y., Pock, T.: ‘Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration to appear’, IEEE Trans. Pattern Analysis and Machine Intelligence, 2016, 8, (10), pp. 1–1.
    35. 35)
      • 3. Rudin, L.I., Osher, S., Fatemi, E.: ‘Nonlinear total variation based noise removal algorithms’, Physica D, 1992, 1, (1), pp. 259–268.
    36. 36)
      • 26. Dong, C., Chen, C.L., Tang, X.: ‘Accelerating the super-resolution convolutional neural network’. European Conf. Computer Vision, 2016, pp. 391–407.
    37. 37)
      • 36. Bengio, Y., Goodfellow, I.J., Courville, A.: ‘Deep learning’ (MIT Press, Cambridge, MA, 2015).
    38. 38)
      • 4. Osher, S., Burger, M., Goldfarb, D., et al: ‘An iterative regularization method for total variation-based image restoration’, Multiscale Model. Simul., 2005, 5, (2), pp. 460–489.
    39. 39)
      • 17. Gu, S., Zhang, L., Zuo, W., et al: ‘Weighted nuclear norm minimization with application to image denoising’. Computer Vision and Pattern Recognition, 2014, vol. 3, pp. 2862–2869.
    40. 40)
      • 1. Tomasi, C., Manduchi, R.: ‘Bilateral filtering for gray and color images’. Int. Conf. Computer Vision, 1998, pp. 839–846.
    41. 41)
      • 9. Mairal, J., Bach, F., Ponce, J., et al: ‘Non-local sparse models for image restoration’. Int. Conf. Computer Vision, 2009, vol. 6, pp. 2272–2279.
    42. 42)
      • 33. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Advances in Neural Information Processing Systems, 2012, vol. 1, issue 2, pp. 1097–1105.
    43. 43)
      • 10. Dong, W., Zhang, L., Shi, G., et al: ‘Nonlocally centralized sparse representation for image restoration’, IEEE Trans. Image Process., 2013, 6, (4), pp. 1620–1630.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.0389
Loading

Related content

content/journals/10.1049/iet-ipr.2017.0389
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address