Noise reduction based on iterative hybrid vector filter and detail correction employing correlation among RGB components

作者：Suetake Noriaki^*; Tanaka Go; Matsuoka Jyohei; Uchino Eiji

来源：Journal of the Franklin Institute, 2012, 349(7): 2357-2368.

DOI：10.1016/j.jfranklin.2012.05.002

One of the important image processing tasks is to effectively reduce a noise from a digital image while keeping its features intact. In this paper, a new noise removal method for color images corrupted by the mixture of the impulsive and Gaussian noises is proposed. In the proposed method, firstly, a tentative output image, in which the noise is removed almost perfectly, is obtained by using the iterative robust switching vector median-based vector epsilon-filter, which is realized by hybridizing the robust switching vector median filter and the vector epsilon-filter and is newly proposed here. Then the residual components between the input and the tentative output images are calculated, and image components constituting edges, corner and other image details are extracted from the residual components by using the correlation characteristic in ROB components. Consequently, a final output is obtained by adding the extracted image components into the tentative output image. The effectiveness and the validity of the proposed method are verified by some experiments using the natural color images.

• 出版日期2012-9