DOI QR코드

DOI QR Code

히스토그램의 변곡점을 이용한 영상 신호의 잡음 제거

Noise Removal of Image Signals using Inflection Points on Histogram

  • Baek, Ji-Hyeon (Dept. of Smart Robot Convergence and Application Eng., Pukyong National University) ;
  • Kim, Nam-Ho (Dept. of Control and Instrumentation Eng., Pukyong National University)
  • 투고 : 2020.07.30
  • 심사 : 2020.08.06
  • 발행 : 2020.11.30

초록

현대사회에서 CCTV, 블랙박스 등 다양한 영상기기로 편리함을 도모한다. 하지만 야간에서 촬영된 영상이나 영상 신호가 송, 수신되는 과정에서 잡음이 빈번하게 발생한다. 이러한 잡음을 제거하지 않으면 영상의 식별이 어렵다는 문제점이 발생한다. 따라서 영상 정보에서 영상의 잡음 제거는 필수불가결한 단계이다. 영상 잡음 중 대표적인 임펄스 잡음으로 Salt and Pepper 잡음이 있다. 잡음을 제거하기 위한 방법으로 선행연구가 진행되어져 왔고 그중 대표적인 방법으로 CWMF, MMF, A-TMF 등이 있다. 이러한 필터들은 공통적으로 저밀도 잡음 영역에서는 우수한 성능을 보이지만 고밀도 잡음 영역에서 잡음 제거 성능이 다소 부족하다는 단점이 있다. 따라서 제안한 알고리즘은 히스토그램 그래프의 변곡점을 이용하여 영역을 나누어 특이점을 제거하고, 히스토그램 분포를 이용한 가중치 필터를 제안한다. 객관적인 판단을 위해 PSNR을 이용하였다.

In modern society, various video devices such as CCTV and black boxes are used for convenience. However, noise is frequently generated in the process of transmitting and receiving video images and video signals photographed at night. If such noise is not eliminated, the problem that the image is difficult to identify is generated. Accordingly, noise elimination of images in the image information is an indispensable step. Salt and Pepper noises are typical impulse noises among image noises. Previous research has been carried out as a method for eliminating noise, and CWMF, MMF and A-TMF are typical methods. In common, such a filter exhibits excellent performance in a low-density noise area, but a disadvantage is that noise elimination performance in a high-density noise area is somewhat insufficient. Accordingly, the proposed algorithm uses the inflection point of the histogram graph to separate areas and remove singular points, and proposes a weighting filter utilizing histogram distribution. PSNR was used for objective judgment.

키워드

참고문헌

  1. J. H. Baek and N. H. Kim, "Salt and Pepper Noise Removal using Processed Pixels," Journal of the Korea Institute of Information and Communication Engineering, vol. 23, no. 9, pp. 1076-1081, Sep. 2019.
  2. R. Kunsoth and M. Biswas, "Modified Decision Based Median Filter for Impulse Noise Removal," in International Conference on Wireless Communications, Signal Processing and Networking(WISPNET), Chennai, India, Mar. 2016.
  3. Dang N. H. Thanh, V. B. Surya Prasath, and L. T. Thanh, "Total Variation L1 Fidelity Salt-and-Pepper Denoising with Adaptive Regularization Parameter," in International Conference on Information and Computer Science(NICS), Ho Chi Minh City, Vietnam, 2018.
  4. S. Vishaga and S. L. Das, "A Survey On Switching Median Filter for Impulse Noise Removal," in International Conference on Circuits, Power and Computing Technologies, Nagercoil, India, 2015.
  5. Y. R. Kim and S. D. Dong, "Modified median filter based on multi-step," Journal of the Institute of Information Engineers, Vol. 51, No. 2, pp. 207-213, Feb, 2014. https://doi.org/10.5573/ieie.2014.51.2.207
  6. S. Y. Jung, J. H. Hwang and J. H. Shin, "Impulse Noise Reduction Using Histogram Distribution," in Conference on The Institute of Electronics and Information Engineers, pp. 593-596, Apr. 1997.
  7. S. I. Kwon and N. H. Kim, "Mixed Noise Removal using Histogram and Pixel Information of Local Mask," Journal of the Korea Institute of Information and Communication Engineering, vol. 20, no. 3, pp. 647-653, Mar. 2016. https://doi.org/10.6109/jkiice.2016.20.3.647
  8. J. H. Baek and N. H. Kim, "Noise Removal using Histogram Distribution in the Salt and Pepper Noise," in Proceedings Conference on Korea Information and Communication Engineering, Korea: Gyeongju, pp. 468-470, 2020.
  9. D. W. Kim, S. W. Wee, and J. C. Jeong, "Improved Histogram Processing Techniques Using Zone-Specific Histogram," in Conference on The Korean Society of Broad Engineers, pp. 46-49, Nov. 2019.
  10. O. Green, "Efficient Scalable Median Filtering Using Histogram-Based Operations," IEEE Transactions on Image Processing, vol. 27, no. 5, pp. 2217-2228, Dec. 2017. https://doi.org/10.1109/TIP.2017.2781375
  11. D. J. Kim and P. L. Manjusha, "Building Detection in High Resolution Remotely Sensed Images based on Automatic Histogram-Based Fuzzy C-Means Algorithm," Asia-pacific Journal of Convergent Research Interchange, vol. 3, no. 1, pp. 57-62, Mar. 2017. https://doi.org/10.21742/apjcri.2017.12.11
  12. S. Esakkirajan, T. Veerakumar, A. N. Subramanyam, and C. H. PremChand, "Removal of High Density Salt and Pepper Noise Through Modified Decision Based Unsymmetric Trimmed Median Filter," IEEE Signal Processing Letters, vol. 18, no. 5, pp. 287-290, Mar. 2011. https://doi.org/10.1109/LSP.2011.2122333