Sparse Convolution Neural Network for Image Denoising

Authors

  • Dheeraj Kumar Chaturvedi
  • Saima Khan

Keywords:

Image Denoising, Convolution Neural Network, Residual Learning, Sparse Representation, Image Reconstruction.

Abstract

In this paper, Convolution neural network (CNN) is used to enhance the efficiency and adaptability of image noise reduction. To increase de-noising efficacy, the component enlarges the receiving area of the region employing dilated and traditional convolutions in the sparse representation stage. The feature augmentation phase uses system global and regional features to increase image de-noising interpretation. The Sparse representation comprised of dilated and generalized convolutions is given to improve de-noising acceleration and efficiency. The reconstructive stage is then employed to collect noise information completely. Finally, employing the residue learning approach, this phase manages to generate the noise free image. The result analysis shows the efficiency of proposed framework over existing works.

Downloads

Download data is not yet available.

Author Biographies

Dheeraj Kumar Chaturvedi

Department of Electronics and Communication Engineering

Technocrat Institute of Technology

Excellence Bhopal, MP, India

Saima Khan

Department of Electronics and Communication Engineering

Technocrat Institute of Technology, Excellence

Bhopal, MP, India

References

Goyal, B., Dogra, A., Agrawal, S., Sohi, B. S., & Sharma, A. (2020). Image denoising review: From classical to state-of-the-art approaches. Information Fusion, 55(September 2019), 220–244. https://doi.org/10.1016/j.inffus.2019.09.003

Thakur, R. S., Yadav, R. N., & Gupta, L. (2019). State-of-art analysis of image denoising methods using convolutional neural networks. IET Image Processing, 13(13), 2367–2380. https://doi.org/10.1049/iet-ipr.2019.0157

Pardo, A. (2011). Analysis of non-local image denoising methods. Pattern Recognition Letters, 32(16), 2145–2149. https://doi.org/10.1016/j.patrec.2011.06.022

Knaus, C., & Zwicker, M. (2013). DUAL-DOMAIN IMAGE DENOISING Claude Knaus Matthias Zwicker. 4, 440–444.

Gondara, L. (2016). Medical Image Denoising Using Convolutional Denoising Autoencoders. IEEE International Conference on Data Mining Workshops, ICDMW, 0, 241–246. https://doi.org/10.1109/ICDMW.2016.0041

Liu, Z., Yan, W. Q., & Yang, M. L. (2018). Image denoising based on a CNN model. Proceedings - 2018 4th International Conference on Control, Automation and Robotics, ICCAR 2018, 389–393. https://doi.org/10.1109/ICCAR.2018.8384706

Shahdoosti, H. R., & Hazavei, S. M. (2018). Combined ripplet and total variation image denoising methods using twin support vector machines. Multimedia Tools and Applications, 77(6), 7013–7031. https://doi.org/10.1007/s11042-017-4618-9

Zhang, F., Cai, N., Wu, J., Cen, G., Wang, H., & Chen, X. (2018). Image denoising method based on a deep convolution neural network. IET Image Processing, 12(4), 485–493. https://doi.org/10.1049/iet-ipr.2017.0389

Ghimpeteanu, G., Batard, T., Bertalmio, M., & Levine, S. (2016). A decomposition framework for image denoising algorithms. IEEE Transactions on Image Processing, 25(1), 388–399. https://doi.org/10.1109/TIP.2015.2498413

Zhang, F., Cai, N., Wu, J., Cen, G., Wang, H., & Chen, X. (2018). Image denoising method based on a deep convolution neural network. IET Image Processing, 12(4), 485–493. https://doi.org/10.1049/iet-ipr.2017.0389

Downloads

Published

05/30/2022

How to Cite

Chaturvedi, D. K. ., & Khan, S. . (2022). Sparse Convolution Neural Network for Image Denoising. SMART MOVES JOURNAL IJOSCIENCE, 8(5), 1.5. Retrieved from https://ijoscience.com/ojsscience/index.php/ojsscience/article/view/486

Issue

Section

Articles