Quaternion-Based Impulse Noise Removal From Color Video Sequences

• Published in: IEEE transactions on circuits and systems for video technology 2013-05, Vol.23 (5), p.741-755
• Main Authors: Jin, Lianghai, Liu, Hong, Xu, Xiangyang, Song, Enmin
• Format: Article
• Language: English
• Subjects: Applied sciences; Color images; Colored noise; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Filtering; filters; Image color analysis; Image processing; impulse noise; Information, signal and communications theory; motion estimation; Noise measurement; Quaternions; Signal and communications theory; Signal processing; Signal, noise; Telecommunications and information theory; vector processing; Vectors; video denoising
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2012.2207272

In this paper, a new quaternion vector filter for removal of random impulse noise in color video sequences is presented. First, luminance distances and chromaticity differences that are represented in quaternion form are combined together to measure color distances between color pixels. Then, based on this new color distance mechanism, the samples along horizontal, vertical, and diagonal directions in current frame and the samples of adjacent frames on motion trajectory are used to detect whether each pixel is noisy or not. By analyzing the spatiotemporal order-statistic information about these directional samples, the video pixels are classified into noise free and noisy. Finally, 3-D weighted vector median filtering is performed on the pixels that are judged as noisy, and the other pixels remain unchanged. The experimental results show that the proposed algorithm significantly outperforms other state-of-the-art video denoising methods in terms of both objective measure and visual evaluation.