한국정보기술학회논문지 (The Journal of Korean Institute of Information Technology)

한국정보기술학회 (Korean Institute of Information Technology)
권호 표지
DOI QR코드

DOI QR Code

구조 인식 심층 합성곱 신경망 기반의 영상 잡음 제거

Image Denoising Via Structure-Aware Deep Convolutional Neural Networks

  • 박기태 (군산대학교 소프트웨어융합공학과) ;
  • 손창환 (군산대학교 소프트웨어융합공학과)
  • 투고 : 2018.08.28
  • 심사 : 2018.10.04
  • 발행 : 2018.11.30
⟨ 이전 논문 다음 논문 ⟩

초록

스마트폰의 보급이 확산되고 대중화됨에 따라 대부분의 사람들은 사진을 촬영하기 위해 모바일 카메라를 애용하고 있다. 하지만 저조도 환경에서 사진을 촬영할 때 광량이 부족한 이유로 원치 않는 잡음이 발생할 수 있다. 이런 잡음을 제거하기 위해, 최근 심층 합성곱 신경망에 기반한 잡음 제거 기법이 제안되었다. 이 기법은 성능 측면에서 큰 진전을 보였을지라도 여전히 텍스처 및 에지 표현 능력이 부족하다. 따라서 본 논문에서는 영상의 구조를 향상시키기 위해 에지의 방향 정보를 나타내는 호그 영상을 활용하고자 한다. 그리고 잡음 영상과 호그 영상을 스택으로 쌓은 후, 입력 텐서를 형성하여 심층 합성곱 신경망을 학습시키는 기법을 제안하고자 한다. 실험 결과를 통해, 제안한 기법은 기존의 기법보다 정량적인 화질 평가에서 더 우수한 결과를 얻을 수 있었으며 시각적인 측면에서도 텍스처 및 에지의 향상을 달성할 수 있었다.

With the popularity of smartphones, most peoples have been using mobile cameras to capture photographs. However, due to insufficient amount of lights in a low lighting condition, unwanted noises can be generated during image acquisition. To remove the noise, a method of using deep convolutional neural networks is introduced. However, this method still lacks the ability to describe textures and edges, even though it has made significant progress in terms of visual quality performance. Therefore, in this paper, the HOG (Histogram of Oriented Gradients) images that contain information about edge orientations are used. More specifically, a method of learning deep convolutional neural networks is proposed by stacking noise and HOG images into an input tensor. Experiment results confirm that the proposed method not only can obtain excellent result in visual quality evaluations, compared to conventional methods, but also enable textures and edges to be improved visually.

키워드

과제정보

연구 과제 주관 기관 : 한국연구재단

참고문헌

  1. H. W. Lee and S. W. Lee, "Improving image noise reduction by shapley value normalization", Journal of Korean Institute of Information Technology, Vol. 11, No. 10, pp. 29-34, Oct. 2013.
  2. M. R. Gu, K. S. Lee, and D. S. Kang, "Image noise reduction using modified gaussian filter by estimated standard deviation of noise", Journal of Korean Institute of Information Technology, Vol. 8, No. 12, pp. 111-117, Dec. 2010.
  3. C. Tomasi and R. Manduchi, "Bilateral filtering for gray and color Images", IEEE International Conference on Computer Vision, Bombay, India, pp. 839-846, Jan. 1998.
  4. A. Buades, B. Coll, and J. M. Morel, "A non-local algorithm for image denoising", IEEE International Conference on Computer Vision and Pattern Recognition, San Diego, CA, U.S.A, pp. 60-65, Jun. 2005.
  5. D. Krishnan, R. Fergus, "Fast image deconvolution using hyper-laplacian priors", Advances in Neural Information Processing Systems, pp. 1033-1041, Dec. 2009.
  6. H. C. Burger, C. J. Schuler, and S. Harmeling, "Image denoising: Can plain neural networks compete with BM3D?", IEEE Conference on Computer Vision and Pattern Recognition, RI, U.S.A, pp. 4321-4328, Jun. 2012.
  7. V. Jain and H. S. Seung, "Natural image denoising with convolutional networks", Advances in Neural Information Processing Systems, pp. 769-776, Dec. 2008.
  8. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection", IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 886-893, Jun. 2005.
  9. M. Elad and M. Aharon, "Image denoising via sparse and redundant representations over learned dictionaries", IEEE Transactions on Image Processing, Vol. 15, No. 12, pp. 3736-3745, Dec. 2006. https://doi.org/10.1109/TIP.2006.881969
  10. K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, "Image denoising by sparse 3d transform domain collaborative filtering", IEEE Transactions on Image Processing, Vol. 16, No. 8, pp. 2080-2095, Aug. 2007. https://doi.org/10.1109/TIP.2007.901238
  11. Y. Xie, S. Gu, Y. Liu, W. Zuo, W. Zhang, and L. Zhang, "Weighted schatten p-norm minimization for image denoising and background subtraction", IEEE Transactions on Image Processing, Vol. 25, No. 10, pp. 4842-4857, Oct. 2016. https://doi.org/10.1109/TIP.2016.2599290
  12. Y. Chen, W. Yu, and T. Pock, "On learning optimized reaction diffusion processes for effective image restoration", IEEE Conference on Computer Vision and Pattern Recognition, pp. 5261-5269, Jun. 2015.
  13. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, "Beyond a gaussian denoiser: residual learning of deep CNN for image denoising", IEEE Transactions on Image Processing, Vol. 27, No. 7, pp. 3142-3155, Jul. 2017.

피인용 문헌

  1. Multi-Stream Networks with Multi-Loss Layers and Image Structure Map Predictor for Inverse Halftoning vol.17, pp.4, 2018, https://doi.org/10.14801/jkiit.2019.17.4.43