Color Segmentation Based on Human Perception Using Fuzzy Logic

Color segmentation is important in the field of remote sensing and Geographic Information System (GIS). Most of the color vision systems need to classify pixel color in a given image. Human perception-based approach to pixel color segmentation is done by fuzzy logic. Fuzzy sets are defined on the H, S and V components of the HSV color space. Three values (H, S and V), the fuzzy logic model has three antecedent variables (Hue, Saturation and Value) and one consequent variable, which is a color class ID are fuzzified with Triangular Fuzzy Numbering Method. Fuzzy Rules are constructed according to the linguistic fuzzy sets. One of Discrete Defuzzification method based on zero-order takagi-Sugeno model is used for color segmentation. To define the output color value, Fuzzy reasoning with zero order Takagi-Sugeno model is used for assigning the color of the given. There are sixteen output colors: Black, White, Red, Orange, Yellow, Dark Gray, Light Gray, Pink, Light Brown, Dark Brown, Aqua, Blue, Olive, Light Green, Dark Green and Purple.