Digital Filter Design Using Evolvable Hardware Chip for Image Enhancement

Images acquired through modern cameras may be contaminated by a variety of noise sources (e.g. photon or on chip electronic noise) and also by distortions such as shading or improper illumination. Therefore a preprocessing unit has to be incorporated before recognition to improve image quality. Generalpurpose image filters lacks the flexibility and adaptability for un-modeled noise types. The EHW architecture evolves filters without any apriori information. Adaptability is accomplished by calculating a score for the results obtained by the system on a set of data. This score is then used to manipulate the system in such a way that the system output will converge towards a desired result. Using evolutionary techniques on a digital filtersystem is a possible method for obtaining system adaptability. The approach chosen here is based on functional level evolution whose architecture contains many nonlinear functions and uses an evolutionary algorithm to evolve the best configuration. The proposed filter considers spatial domain approach and uses the overlapping window to remove the noise in the image.