Abstract
The paper presents a random-valued impulse noise (RVIN) removal algorithm by using distinct impulse noise detection and correction stages. In the noise detection phase, the local luminance adaption of an image is used to detect the obvious noise pixels firstly, and the just noticeable difference (JND) is introduced to detect the noise pixels hiding in image details afterward. In the noise candidate correction phase, the obvious noise pixels, almost distributing in the smooth region, are restored by a weighted mean filter. For the noise candidates hiding in image details, we adopt a weighted detail-preserving variation method to restore them. Since human visual perception and detail-preserving are taken into account during the course of the noises detection and restoration, our method outperforms some existing methods, both in visual and quantitative measurements.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Zhu Zhu
Zhu Zhu received his BS degree in Science and Technology of Electronic Information from Huaibei Normal University, Huaibei, China, in 2007. He received his MS degrees in Optical Engineering from Soochow University, Suzhou, China, in 2010. He received his PhD degrees in Instrument Science and Technology from Southeast University, Nanjing, China, in 2013. He is currently an associate professor in Anqing Normal University. His research interests include digital image processing, pattern recognition, and image quality assessment.
Xiaoguo Zhang
Xiaoguo Zhang received the M.S. and Ph.D. degrees in the CAD and GPS/DR/MM integrated vehicle navigation field from Southeast University, Nanjing, China, in 1998 and 2001 respectively. He is currently with the School of Instrument Science and Engineering, Southeast University, as an associate professor and master graduate supervisor. His research interests include digital image processing, pattern recognition, and image quality assessment.