A computer vision system for color grading wood boards using Fuzzy Logic

Abstract

This paper describes the development of a project based on fuzzy logic applied to color histograms for color grading wood boards. During this development a fuzzy min-max inference system, with bell membership functions adjusted to the histogram, was implemented and evaluated. This system performs image matching. Images given as training samples are used to define the classes that determine the several wood board color intervals. In that way the system is capable to classify an image by its color in order to group wood boards with the same tonality-color in a short period of time.