Development of Some Novel Nonlinear and Adaptive Digital Image Filters for Efficient Noise Suppression

Abstract

Some nonlinear and adaptive digital image filtering algorithms have been developed in this thesis to suppress additive white Gaussian noise (AWGN), bipolar fixed-valued impulse, also called salt and pepper noise (SPN), random-valued impulse noise (RVIN) and their combinations quite effectively. The present state-of-art technology offers high quality sensors, cameras, electronic circuitry: application specific integrated circuits (ASIC), system on chip (SOC), etc., and high quality communication channels. Therefore, the noise level in images has been reduced drastically. In literature, many efficient nonlinear image filters are found that perform well under high noise conditions. But their performance is not so good under low noise conditions as compared to the extremely high computational complexity involved therein. Thus, it is felt that there is sufficient scope to investigate and develop quite efficient but simple algorithms to suppress low-power noise in an image. When...