Quaternion switching filter for impulse noise reduction in color image

• Published in: Signal processing Vol. 92; no. 1; pp. 150 - 162
• Main Authors: Geng, Xin, Hu, Xiaoguang, Xiao, Jin
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 2012; Elsevier
• Subjects: Applied sciences; Color; Color image; Computer simulation; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Filtering; Impulse noise; Impulses; Information, signal and communications theory; Noise; Noise reduction; Quaternion unit transform; Quaternions; Signal and communications theory; Signal, noise; Switching filter; Telecommunications and information theory; Impulse noise; Switching filter; Quaternion unit transform; Color image; Filtering; Quaternion; Noise reduction; Computational complexity; Pulse noise; Digital filter; Simulation; Signal processing; Non correlated noise; Median filter
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/j.sigpro.2011.06.015

A novel approach to impulse noise reduction in color image is introduced in this paper. By applying the quaternion unit transform theory, the difference between two color pixels can be represented in the quaternion form. Based on the difference mentioned above, an efficient filter that can switch between the vector median filter (VMF) and the identity filter (no filtering operation) is proposed. Extensive simulation result indicates that the proposed filter achieves a trade-off between noise suppression and detail preservation in both correlated and uncorrelated impulse noise scenarios when compared with other widely used filters. Furthermore, the computational complexity analysis shows that the proposed filter is quite efficient. ► We propose a color pixel difference using the quaternion unit transform.► The difference quantifies the intensity and chromaticity differences simultaneously.► A switching vector median filter based on this difference is proposed.► The filter achieves a balance between noise suppression and detail preservation.► The filter has a lower computational complexity.