access icon free Image noise types recognition using convolutional neural network with principal components analysis

This study presents a model to effectively recognise image noise of different types and levels: impulse, Gaussian, Speckle and Poisson noise, and a mixture of multiple types of the noise. To classify image noise type, the convolutional neural network (CNN) method with backpropagation algorithm and stochastic gradient descent optimisation techniques are implemented. In order to reduce the training time and computational cost of the algorithm, the principal components analysis (PCA) filters generating strategy is deployed to obtain data adaptive filter banks. The authors validated their designed CNN with PCA for noise types recognition model with degraded images containing noise of single and combination of multiple types, with a total of 11,000 and 1650 datasets for training and testing purposes, respectively. The variety and complexity of data have never been addressed before in any other research work. The capability of their intelligent system in handling images degraded under this complicated environment has surpassed human-eye performance in noise types recognition. The authors’ experiments have proven the reliability of the proposed noise types recognition model by having achieved an overall average accuracy of 99.3% while recognising eight classes of noise.

Inspec keywords: image filtering; principal component analysis; gradient methods; Gaussian noise; speckle; adaptive filters; impulse noise; stochastic programming; backpropagation; image classification; channel bank filters

Other keywords: CNN method; data complexity; intelligent system; impulse noise; convolutional neural network; training time reduction; computational cost reduction; human-eye performance; backpropagation algorithm; image noise types recognition model; PCA filter generating strategy; speckle; Gaussian noise; Poisson noise; stochastic gradient descent optimisation techniques; data adaptive filter banks; image noise type classification; principal components analysis

Subjects: Computer vision and image processing techniques; Filtering methods in signal processing; Optimisation techniques; Other topics in statistics; Neural computing techniques; Other topics in statistics; Optimisation techniques; Image recognition

References

    1. 1)
      • 7. Grewenig, S., Zimmer, S., Weickert, J.: ‘Rotationally invariant similarity measures for nonlocal image denoising’, J. Vis. Commun. Image Represent., 2011, 22, (2), pp. 117130.
    2. 2)
      • 19. Huang, Y., Wu, R., Sun, Y., et al: ‘Vehicle logo recognition system based on convolutional neural networks with a pretraining strategy’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (4), pp. 19511960.
    3. 3)
      • 18. Fang, J., Zhou, Y., Yu, Y., et al: ‘Fine-grained vehicle model recognition using a coarse-to-fine convolutional neural network architecture’, IEEE Trans. Intell. Transp. Syst., 2016, PP, (99), pp. 111.
    4. 4)
      • 20. Le Cun, B.B., Denker, J.S., Henderson, D., et al: ‘Handwritten digit recognition with a back-propagation network’. Proc. in Neural Information Processing Systems, 1990.
    5. 5)
      • 30. Hubel, D.H., Wiesel, T.N.: ‘Receptive fields, binocular interaction and functional architecture in the cat's visual cortex’, J. Physiol., 1962, 160, (1), pp. 106154.
    6. 6)
      • 25. Feng, B.-Y., Ren, M., Zhang, X.-Y., et al: ‘Automatic recognition of serial numbers in bank notes’, Pattern Recognit., 2014, 47, (8), pp. 26212634.
    7. 7)
      • 3. Gonzalez, R.C., Woods, R.E.: ‘Digital image processing’ (Pearson Education, 1992, 2008, 3rd edn.).
    8. 8)
      • 4. Rakhshanfar, M., Amer, M.A.: ‘Estimation of Gaussian, Poissonian-Gaussian, and processed visual noise and its level function’, IEEE Trans. Image Process., 2016, 25, (9), pp. 41724185.
    9. 9)
      • 6. Bouboulis, P., Slavakis, K., Theodoridis, S.: ‘Adaptive Kernel-based image denoising employing semi-parametric regularization’, IEEE Trans. Image Process., 2010, 19, (6), pp. 14651479.
    10. 10)
      • 24. Jammalamadaka, N., Zisserman, A., Jawahar, C.V.: ‘Human pose search using deep networks’, Image Vis. Comput., 2017, 59, pp. 3143.
    11. 11)
      • 5. Bo, X., Zhouping, Y.: ‘A universal denoising framework with a new impulse detector and nonlocal means’, IEEE Trans. Image Process, 2012, 21, (4), pp. 16631675.
    12. 12)
      • 11. Elad, M., Aharon, M.: ‘Image denoising via sparse and redundant representations over learned dictionaries’, IEEE Trans. Image Process., 2006, 15, (12), pp. 37363745.
    13. 13)
      • 14. Jain, V., Seung, S.: ‘Natural image denoising with convolutional networks’. Proc. in Neural Information Processing Systems, 2009, pp. 769776.
    14. 14)
      • 2. Bovik, A.: ‘Handbook of image and video processing’ (Elsevier Academic Press, 2000, 2005, 2nd edn.).
    15. 15)
      • 8. Mihcak, M.K., Kozintsev, I., Ramchandran, K., et al: ‘Low-complexity image denoising based on statistical modeling of wavelet coefficients’, IEEE Signal Process. Lett., 1999, 6, (12), pp. 300303.
    16. 16)
      • 16. Karibasappa, K.G., Karibasappa, K.: ‘Ai based automated identification and estimation of noise in digital images’, in El-Alfy, E.-S.M., Thampi, S.M., Takagi, H., Piramuthu, S., Hanne, T. (Eds.): ‘Advances in intelligent Informatics’ (Springer International Publishing, 2015).
    17. 17)
      • 21. Lawrence, S., Giles, C.L., Ah Chung, T., et al: ‘Face recognition: a convolutional neural-network approach’, IEEE Trans. Neural Netw. Learn. Syst., 1997, 8, (1), pp. 98113.
    18. 18)
      • 31. Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., et al: ‘Convolutional neural networks for medical image analysis: full training or fine tuning?’, IEEE Trans. Med. Imag., 2016, 35, (5), pp. 12991312.
    19. 19)
      • 34. Burger, H.C., Schuler, C., Harmeling, S.: ‘Learning how to combine internal and external denoising methods’. Pattern Recognition: 35th German Conf., Gcpr 2013, Saarbrücken, Germany, 3–6 September 2013.
    20. 20)
      • 10. Dabov, K., Foi, A., Katkovnik, V., et al: ‘Image denoising by sparse 3-D transform-domain collaborative filtering’, IEEE Trans. Image Process., 2007, 16, (8), pp. 20802095.
    21. 21)
      • 32. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Proc. of the 25th Int. Conf. Neural Information Processing Systems, 2012.
    22. 22)
      • 9. Zhang, L., Dong, W., Zhang, D., et al: ‘Two-stage image denoising by principal component analysis with local pixel grouping’, Pattern Recognit., 2010, 43, (4), pp. 15311549.
    23. 23)
      • 17. Vasuki, P., Bhavana, C., Roomi, S.M.M., et al: ‘Automatic noise identification in images using moments and neural network’. 2012 Int. Conf. Machine Vision and Image Processing (MVIP), 2012, pp. 6164.
    24. 24)
      • 23. Yan, C., Coenen, F., Zhang, B.: ‘Driving posture recognition by convolutional neural networks’, IET Comput. Vis., 2016, 10, (2), pp. 103114.
    25. 25)
      • 33. Zhang, K., Zuo, W., Chen, Y., et al: ‘Beyond a Gaussian denoiser: residual learning of deep Cnn for image denoising’, IEEE Trans. Image Process., 2017, 26, (7), pp. 31423155.
    26. 26)
      • 12. Xu, L., Ren, J.S., Liu, C., et al: ‘Deep convolutional neural network for image deconvolution’. Proc. in Neural Information Processing Systems, 2014, pp. 17901798.
    27. 27)
      • 13. Burger, H.C., Schuler, C.J., Harmeling, S.: ‘Image denoising: can plain neural networks compete with bm3d?’. IEEE Conf. on Computer Vision and Pattern Recognition, 2012, pp. 23922399.
    28. 28)
      • 22. Zhu, J., Liao, S., Lei, Z., et al: ‘Multi-label convolutional neural network based pedestrian attribute classification’, Image Vis. Comput., 2017, 58, pp. 224229.
    29. 29)
      • 27. Zhu, S.C., Wu, Y., Mumford, D.: ‘Filters, random fields and maximum entropy (frame): towards a unified theory for texture modeling’, Int. J. Comput. Vis., 1998, 27, (2), pp. 107126.
    30. 30)
      • 15. Yixin, C., Das, M.: ‘An automated technique for image noise identification using a simple pattern classification approach’. 50th Midwest Symp. on Circuits and Systems, 2007, pp. 819822.
    31. 31)
      • 26. Mercan, C.A., Celebi, M.S.: ‘An approach for chest tube detection in chest radiographs’, IET Image Process., 2014, 8, (2), pp. 122129.
    32. 32)
      • 1. Hosseini, H., Hessar, F., Marvasti, F.: ‘Real-time impulse noise suppression from images using an efficient weighted-average filtering’, IEEE Signal Process. Lett., 2015, 22, (8), pp. 10501054.
    33. 33)
      • 29. Chan, T.H., Jia, K., Gao, S., et al: ‘Pcanet: a simple deep learning baseline for image classification?’, IEEE Trans. Image Process., 2015, 24, (12), pp. 50175032.
    34. 34)
      • 28. Tian, L., Fan, C., Ming, Y., et al: ‘Stacked Pca network (Spcanet): an effective deep learning for face recognition’. IEEE Int. Conf. on Digital Signal Processing (DSP), 2015, pp. 10391043.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2017.0374
Loading

Related content

content/journals/10.1049/iet-ipr.2017.0374
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading