Some novel digital image filters for suppression of impulsive noise

Abstract

In digital imaging, quality of image degrades due to contamination of various types of noise during the process of acquisition, transmission and storage. Especially impulse noise appears during image acquisition and transmission, which severely degrades the image quality and cause a great loss of information details in an image. Various filtering technique are found in literature for removal of impulse noise. Nonlinear filter such as standard median, weight median filter, center weight median and switching based median filter out perform the linear filters. This thesis investigates the performance analysis of different nonlinear filtering schemes. The performance of these filters can be improved by incorporating the mechanism of noise detection and then applying switching based adaptive filtering approach. Three novel filtering approaches that incorporate the above principles are proposed. It is found that all three approaches give noticeable performance improvement of over many filters reported in literature.