Edge preserving algorithm for impulse noise removal using FPGA

Abstract

Impulse noise is caused by malfunctioning pixels in camera sensors, faulty memory locations in hardware, or transmission in a noisy channel. Several distortions limit the quality of digital images during image acquisition, formation, storage and transmission. Impulse noise is introduced in the images from some digital sources due to acquisition error or transmission error or a problem in the ground processing systems. In this paper, an efficient edge preserving impulse noise removal technique has been proposed. The algorithm has been simulated on MATLAB and implemented using FPGA. The results show that the proposed technique preserves the finer edge details of the image during the impulse noise removal process. The technique has high performance in terms of qualitative analysis as well as visual quality using PSNR and MAE. Also, synthesis results prove that the design is of low computational complexity and lesser hardware cost.