Image Denoising by Exploring External and Internal Correlations

   December 11, 2017    Comments Off on Image Denoising by Exploring External and Internal Correlations    Posted in: IEEE 2017, MATLAB

Image Denoising by Exploring External and Internal Correlations

ABSTRACT:

Single image denoising suffers from limited data collection within a noisy image. In this paper, we propose a novel image denoising scheme, which explores both internal and external correlations with the help of web images. For each noisy patch, we build internal and external data cubes by finding similar patches from the noisy and web images, respectively. We then propose reducing noise by a two-stage strategy using different filtering approaches. In the first stage, since the noisy patch may lead to inaccurate patch selection, we propose a graph based optimization method to improve patch matching accuracy in external denoising. The internal denoising is frequency truncation on internal cubes. By combining the internal and external denoising patches, we obtain a preliminary denoising result. In the second stage, we propose reducing noise by filtering of external and internal cubes, respectively, on transform domain. In this stage, the preliminary denoising result not only enhances the patch matching accuracy but also provides reliable estimates of filtering parameters. The final denoising image is obtained by fusing the external and internal filtering results. Experimental results show that our method constantly outperforms state-of-the-art denoising schemes in both subjective and objective quality measurements, e.g., it achieves >2 dB gain compared with BM3D at a wide range of noise levels.

EXISTING SYSTEM:

  • During few past decades we were using pixel level filtering methods, like Gaussian filtering, Bilateral filtering and total variation regularization and patch filtering methods, such as non-local means block matching 3D filtering(BM3D) and low rank regularization.
  • Besides Single-image based de-noising methods, other promising de-noising methods are learning based such as fields of experts, maximizing expected patch log likelihood (EPLL) and neural network training.
  • They restore the noisy image by integrating natural image priors into the under-constrained restoration problem. The image denoising performance was then go with using landmark and multi-view images as a consideration of getting correlated images as an external dataset.
  • This process of using correlated images has springed up in many computer vision and image completion, image compression sketch to photo, image super-resolution DE blurring and de-noising.

DISADVANTAGES OF EXISTING SYSTEM:

  • Single image based de-noising performance is dropped seriously due to increasing noise level after recovery.
  • Since the noise level is high, the accuracy will suffer from significant loss.
  • BM3D is noteworthy that they utilize the same database for all kinds of noisy images. i.e., there is no prior for the noisy image scene being used.it will result in annoying artifacts.
  • The system which obtain the correlated images as external datasets and images captured by multi-view camera will explore only the external correlation without exploring internal correlations

 

 

PROPOSED SYSTEM:

  • In this paper we propose our system with the extension of existing system for image denoising by exploring both internal and external correlations. Correlations and a graph optimization method to improve patch matching accuracy and introduce a more effective filtering methods.
  • In this paper we have two contribution in first stage we design different external and internal filtering strategies to remove its noise. In the external denoising, the graph based optimization method to improve patch matching accuracy between a noisy patch and clean patches in external correlated images is proposed.
  • In the internal denoising, 3D frequency domain filtering is performed. These two denoising results are then combined in frequency domain to produce a preliminary denoising image.
  • In second stage, we propose a two-stage based denoising strategy to fully take advantage of external and internal correlations. The de-noising result at the first stage is used to improve image registration, patch matching and estimation of filtering parameters.

 

ADVANTAGES OF PROPOSED SYSTEM:

  • In our system, the correlated images captured by different settings like focal length, view point, resolution.
  • Our scheme could well handle noisy patches that have no matched patches in the external dataset.

 

SYSTEM ARCHITECTURE:

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

 

  • System : Pentium IV 2.4 GHz.
  • Hard Disk : 40 GB.
  • Floppy Drive : 44 Mb.
  • Monitor : 15 VGA Colour.
  • Mouse :
  • Ram : 512 Mb.

 

SOFTWARE REQUIREMENTS:

 

  • Operating system : Windows XP/7.
  • Coding Language : MATLAB
  • Tool : MATLAB R 2007B

 

REFERENCE:

Huanjing Yue, Xiaoyan Sun, Senior Member, IEEE, Jingyu Yang, Member, IEEE, and Feng Wu, Fellow, IEEE, “Image Denoising by Exploring External and Internal Correlations”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 24, NO. 6, JUNE 2015.

  

Comments are closed.