Image Segmentation using fuzzy logic and genetic algorithms

Abstract

Genetic algorithms (GAs) and fuzzy logic (FL) have been playing important roles in solving many problems in pattern recognition and image processing. This paper presents a hybrid approach of GAs and FL that is used to fuse (combine) extracted features from intensity and range images. GAs are used to help construct member- shi functions that are necessar to classif the stren th of existence of ima e features through FL. Since range and intensity images provide different types of sensory modality, fusing the extracted features from these images reveals more accurate info- rmation about the scene. The extracted features are fused to generate a segmented image of the scene. The segmented image is compared with its ideal counterpart for the purpose of experimental evaluation.