Adaptive Image Enhancement Filter Design using FPGA and Handel-C

초록

In this paper, adaptive image enhancement filter scheme is proposed and implemented on FPGA chip using Handel-C. Handel-C is a high-level programming tool for designing hardware. Software-like design style makes HDL-based design easier. Genetic Algorithm (GA) evolves filter blocks to make the best image enhancement filter. Conventional filtering methods require a priori noise information for image enhancement. In general, if a priori information of noise is not available, heuristic intuition or time-consuming recursive calculations are required for image enhancement. Contrary to the conventional filtering methods, the proposed filter system can find optimal combination of filters and their parameter values adaptively to unknown noise types using the GA. Some of the commonly used filters such as median filter, histogram equalization filter, homomorphic filter and illumination compensation filter are designed and verified by debugging and simulating on hardware. Total system is composed of image enhancement part (filter blocks) and the face recognition part (Gabor filter). GA evolves the connection (combination) and parameters of image enhancement filters as well as coefficients of Gabor filter. Experimental results show that proposed scheme can generate optimal set of filters adaptively without a priori noise information and face recognition is accomplished successfully.