影像雜訊評估與消除

Noise Estimation and Reduction

何庭輝(Ting-Fai Ho)

指導教授 ： 林祺政

共同指導教授 ： 陳世明

國立臺北藝術大學/美術學院學術論文/科技藝術研究所碩士班/碩士(2014年)

https://doi.org/10.6835/TNUA.2014.00177

摘要

隨著數位影像日漸的普及廣泛的應用，如互動藝術，舞台表演等。為了滿足應用上的需求，改善影像的品質變得很重要。本論文把一個快速的灰階影像雜訊處理的方法，改良應用在彩色影像中，根據色彩空間轉換後的影像特性使用不同參數的演算法，以求得出一個快速及效果不錯的方法。最後根據實驗結果可知，本文所提出的方法可有效率消除高斯雜訊並保留一定的影像細節。

關鍵字

影像處理 ； 雜訊評估 ； 雜訊消除

並列摘要

Due to the population of digital image and the broadening usage of digital image data, like interactive installation art, performance art, etc. In order to fulfill the requirements, improving the quality of digital images is very important. In this thesis, we apply a fast monochrome image noise reduction method to color images. We improve the method by adjusting parameters due to different properties of different color space layers. This thesis propose a fast and proper method for color image noise reduction, which is efficient removing Gaussian noise without blurring much image detail.

並列關鍵字

Image Processing ； Noise Estimation ； Noise Reduction

參考文獻

[2] Saeed V. Vaseghi. 'Advanced Digital Signal Processing and Noise Reduction', John Wiley & Sons Ltd., vol., pp., 2000

[3] S. I. Olsen. 'Estimation of noise in images: an evaluation', Graph. Models Image Process, vol., pp.319-323, Jul. 1993

[4] A. Amer and E. Dubois. 'Fast and reliable structure-oriented video noise estimation', IEEE Trans. on Circuits and Syst. for Video Tech., vol.15, pp.113-118, Jan. 2005

[6] T. Seemann and P. Tischer. 'Structure preserving noise ‾ltering of images usingexplicit local segmentation', Proc. Int. Conf. on Pattern Recognition, vol.2, pp.1610-1612, Aug. 1998

[7] J. Lee. 'Digital image smoothing and the sigma filter', Computer Vision, Graphics and Image Processing, vol.24, pp.225-269, 1983