Defect detection on wooden surfaces using Gabor Filters with evolutionary algorithm design

We apply a model of texture segmentation using multiple spatially and spectrally localized (-)lters, known as Gabor (-)lters, to the analysis of texture and defect regions found on wooden boards. Speci(-)cally we present a method to (-)nd an optimal set of parameters for a given two-dimensional object detection method. We use feature selection techniques to maximize discrimination. The selection method uses a genetic algorithm to optimize various parameters of the system including Gabor weights, and the parameters of morphological pre-processing, We demonstrate the applicability of the method to the task of classifying wooden textures, and report experimental results using the proposed method.