Khamis A. Zidan, Dhafer Zaghar, Ekhlas Hameed Karam,
Abstract
A nonlinear filtering is an important part of processing and restoring image sequence. The computation complexity of these filtering algorithms makes them difficult for real-time processing. This paper presents the design and implementation of a pure fuzzy filter, which is effective to remove the impulse noise, and a new method for hardware implementation into single chip FPGA is proposed. The construction of the fuzzy filter is simple and depends on a set of fuzzy rules to well detect and remove noise pulses. Simulation results show that the fuzzy filter exhibits better filtering properties than standard median filters. The basic FPGA implementation of the filter cannot reach the limit for real time processing with good efficiency. The proposed fuzzy filter is implemented by modifying the input data locations and increase the speed of processing seven times without any increase in the cost.
أ د خميس عواد زيدان | Khamis A. Zidan | 10653