This paper describes the application of fuzzy logic to cotton color grading in an attempt to improve the accuracy of the machine grading for cotton colors. Color grades of cotton are a number of classes in the (R_d, b) color space. Adjacent color classes have blur and overlapping boundaries, making crisp-boundary methods ineffective for the cotton color classification. Fuzzy logic is specialized in dealing with uncertainty and imprecision in a decision-making process, and thus offers a new approach for grading cotton colors. In this paper, we will present the procedures of constructing a fuzzy inference system (FIS) using fuzzy logic to classify major classes of cotton colors, and the preliminary results to demonstrate the FIS’s effectiveness in reducing machine-classer disagreements in color grading. The results from the FIS have shown great consistency for multiple years’ cotton color data.