DOI QR코드

DOI QR Code

AWGN 환경에서 쿼드트리 분할을 사용한 변형된 가우시안 필터 알고리즘

Modified Gaussian Filter Algorithm using Quadtree Segmentation in AWGN Environment

  • Cheon, Bong-Won (Dept. of Smart Robot Convergence and Application Eng., Pukyong National University) ;
  • Kim, Nam-Ho (Dept. of Control and Instrumentation Eng., Pukyong National University)
  • 투고 : 2021.06.17
  • 심사 : 2021.07.16
  • 발행 : 2021.09.30

초록

최근 인공지능과 IoT 기술의 발달에 따라 다양한 분야에서 자동화와 무인화가 진행되고 있으며, AI 객체인식의 기반이 되는 영상처리에 대한 중요성이 높아지고 있다. 특히 세밀한 데이터 처리가 필요한 시스템에서는 전처리 단계로 잡음 제거를 사용하고 있으나, 기존 알고리즘은 영상의 잡음 수준을 고려하지 않아 필터링 과정에서 블러링 현상이 나타나는 단점을 가지고 있다. 따라서 본 논문에서는 영상의 잡음 수준을 판단하여 가중치를 결정하는 변형된 가우시안 필터를 제안한다. 제안한 알고리즘은 쿼드트리 분할을 사용하여 영상의 AWGN에 대한 잡음추정치를 구하여 가우시안 가중치와 화소가중치를 정하며, 로컬마스크와 컨벌루션하여 최종출력을 구한다. 제안한 알고리즘을 평가하기 위해 기존 방법과 비교하여 시뮬레이션하였으며, 기존 방법에 비해 우수한 성능을 확인하였다.

Recently, with the development of artificial intelligence and IoT technology, automation, and unmanned work are progressing in various fields, and the importance of image processing, which is the basis of AI object recognition, is increasing. In particular, in systems that require detailed data processing, noise removal is used as a preprocessing step, but the existing algorithm does not consider the noise level of the image, so it has the disadvantage of blurring in the filtering process. Therefore, in this paper, we propose a modified Gaussian filter that determines the weight by determining the noise level of the image. The proposed algorithm obtains the noise estimate for the AWGN of the image using quadtree segmentation, determines the Gaussian weight and the pixel weight, and obtains the final output by convolution with the local mask. To evaluate the proposed algorithm, it was simulated compared to the existing method, and superior performance was confirmed compared to the existing method.

키워드

과제정보

This work was supported by the Technology development Program(S3038447) funded by the Ministry of SMEs and Startups(MSS, Korea).

참고문헌

  1. Y. Zeng, Z. Zhang, X. Zhou, and Y. Liu, "High Dynamic Range Infrared Image Compression and Denoising," in 2019 International Conference on Information Technology and Computer Application, Guangzhou : China, pp. 65-69, 2019. DOI:10.1109/ITCA49981.2019.00022.
  2. P. S. V. S. Sridhar and R. Caytiles, "Efficient Cloud Data Hosting Availability," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508-9080, vol. 3, no. 2, pp. 11-19, Jun. 2017. DOI:10.21742/APJCRI.2017.06.02.
  3. X. Liu, M. Tanaka, and M. Okutomi, "Signal Dependent Noise Removal from a Single Image," in 2014 IEEE International Conference on Image Processing, Paris: France, pp. 2679-2683, 2014. DOI:10.1109/ICIP.2014.7025542.
  4. L. Li, Z. Li, B. Li, D. Liu, and H. Li, "Quadtree-based Coding Framework for High-Density Camera Array-based Light Field Image," IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 8, pp. 2694-2708, Aug. 2020. DOI:10.1109/TCSVT.2019.2924313.
  5. L. Xuegang, L. Junrui, and W. Juan, "Nonconvex Low Rank Approximation with Phase Congruency Regularization for Mixed Noise Removal," IEEE Access, vol. 7, no. 1, pp. 179538-179551, Dec. 2019. DOI:10.1109/ACCESS.2019.2958821.
  6. X. Long and N. H. Kim, "An Improved Weighted Filter for AWGN Removal," Journal of the Korea Institute of Information and Communication Emn ngineering, vol. 17, no. 5, pp. 1227-1232, Mar. 2013. DOI: 10.6109/jkiice.2013. 17.5.1227.
  7. M. Chowdhury, J. Gao, and R. Islam, "Fuzzy Logic Based Filtering for Image De-noising," in 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Vancouver, BC : Canada, pp. 2372-2376, 2016. DOI: 10.1109/FUZZIEEE.2016.7737990.
  8. B. W. Cheon and N. H. Kim, "AWGN Removal using Pixel Noise Characteristics of Image," Journal of the Korea Institute of Information and Communication Engineering, vol. 23, no. 12, pp. 1551-1557, Dec. 2019. DOI: 10.6109/jkiice.2019.23.12.1551.
  9. S. Trambadia and P. Dholakia, "Design and Analysis of an Image Restoration using Wiener Filter with a Quality based Hybrid Algorithms," in 2015 2nd International Conference on Electronics and Communication Systems, Coimbatore : India, pp. 1318-1323, 2015. DOI: 10.1109/ECS.2015.7124798.
  10. D. Chowdhury, S. K. Das, S. Nandy, A. Chakraborty, R. Goswami, and A. Chakraborty, "An Atomic Technique for Removal of Gaussian Noise from a Noisy Gray Scale Image using Low-Pass Convoluted Gaussian Filter," in 2019 International Conference on Opto-Electronics and Applied Optics (Optronix), Kolkata:India, pp. 1-6, 2019. DOI: 10.1109/OPTRONIX.2019.8862330.