이미지 내 유사도를 이용한 Non-Local Means 알고리즘 개선
Improvement of Non-Local Means Algorithm Using Similarity in Image
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
스마트폰의 보급화에 의해 영상은 쉽게 획득할 수 있지만 야간의 조명 조건의 불균형성 그리고영상 데이터의 전송과 압축 과정에서 열화와 잡음(Noise)이 생성되기도 한다. 이러한 잡음을 최소화하고 영상 화질을 개선하기 위해 Non-Local Means(NLM)은 주변의 픽셀값이 아닌 이미지 내에서 현재 patch와 유사한 patch를 찾아 잡음을 제거한다. 하지만, 유사도를 측정하는 데 있어서 유사한 pactch가 커질수록 유용성이 떨어지는 단점을 가지고 있다. 본 논문에서는 Sum of Absolute Differences 연산을 이용하여 유사도를 계산하고 유사도에 따라 가중치를 적용하는 잡음 제거 방법을 제안한다. 제안한 알고리즘을 사용하여 Salt and Pepper 잡음 이미지에 PSNR 개선이 평균7.98dB 향상되며 NLM 대비 1.06dB 개선된다. 제안한 알고리즘을 기존 NLM 최적화 논문에 적용하였을 때 성능 향상을 기대할 수 있다.
Abstract
With the widespread adoption of smartphones, acquiring images has become easier. However, challenges arise due to uneven lighting conditions at night and the degradation and noise introduced during image transmission and compression. To minimize this noise and improve image quality, Non-Local Means (NLM) techniques are used, which unlike traditional methods, seek out patches within the image that are similar to the current patch to eliminate noise. However, a drawback of NLM is the diminishing utility as the similar patches become larger. This paper proposes a noise reduction method that utilizes the Sum of Absolute Differences to calculate similarity and applies weights accordingly. The proposed algorithm demonstrates an average improvement of 6.911dB in Peak Signal-to-Noise Ratio (PSNR) on Salt and Pepper noise images, showing a 0.713dB improvement over traditional NLM. When the proposed algorithm is applied to existing NLM optimization papers, performance improvements can be expected.
참고문헌 (18)
- Jihun Jung, "A Study on the detection of photo of urine test strip using white balancing algorithm", Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp.1335~1336 (2022)
- Ji-Hyeon Baek, "Noise Removal Method using Entropy in High-Density Noise Environments", Journal of the Korea Institute of Information and Communication Engineering, 24(10), pp.1255~1261 (2020)
- Sung Jun Kim, "Deep Network for Detail Enhancement in Image Denoising", Journal of Korea Multimedia Society, 22(6), pp.646~654 (2019)
- MoonWon Choo, "Image Contrast Enhancement Based on Genetic Algorithm Using A Variant Histogram Equalization", The Journal of Image and Cultural Contents, 14, pp.219~230 (2018)[DOI]
- Eon Seung Seong, "Medical image denoising using convolutional dual-decoder autoencoder", Journal of the Korean Data And Information Science Society, 33(6), pp.1065~1083 (2022)[DOI]
- Young-Ro Kim, "Spatio-temporal Non-local Means Filter for Noise Reduction", Journal of the Institute of Electronics and Information Engineers, 59(12), pp.97~103 (2022)[DOI]
- A. Buades, "A non-local algorithm for image denoising", 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2, pp.60~65 (2005)
- D. Van De Ville, "SURE-Based Non-Local Means", IEEE Signal Processing Letters, 16(11), pp.973~976 (2009)[DOI]
- J. Wang, "Fast Non-Local Algorithm for Image Denoising", 2006 International Conference on Image Processing, pp.1429~1432 (2006)
- Y. Wu, "Probabilistic Non-Local Means", IEEE Signal Processing Letters, 20(8), pp.763~766 (2013)[DOI]
- J. Orchard, "Efficient nonlocal-means denoising using the SVD", 2008 15th IEEE International Conference on Image Processing, pp.1732~1735 (2008)
- Antoni Buades, "Non-Local Means Denoising", Image Processing On Line, 1, pp.208~212 (2011)[DOI]
- Jeonghwan Kim, "A Study to Calculate an Efficient Covariance Matrix of Non-local Means with Principal Components Analysis", Proceedings of the Korean Society of Broadcast Engineers Conference, pp.205~207 (2015)
- Yang-Soo Kim, "Enhanced RGB Video Coding Based on Correlation in the Adjacent Block", The transactions of The Korean Institute of Electrical Engineers, 58(12), pp.2538~2541 (2009)
- R. Verma, "Non local means algorithm with adaptive isotropic search window size for image denoising", 2015Annual IEEE India Conference(INDICON), pp.1~5 (2015)
- "Praveen Venkatesh, Non-Local-Means"[URL]
- "opencv"[URL]
- "Python-Median-Filter"[URL]