Linear in the parameter model for Homomorphic filter: Volterra series based approach

Abstract

This paper introduces a linear in the parameter model for Homomorphic filter using Volterra series approach. To obtain these parameters we propose a model where we choose a sub image from the response of Homomorphic filter as reference image to reduce computational complexity. We apply non uniform illuminated images to the proposed filter and compare its performance against standard Homomorphic filter. The proposed filter outperforms the traditional Homomorphic filter in all experiments. Also we compare the error convergence and steady-state error of Sparse aware LMS with LMS algorithm to calculate proposed filter coefficients.