IMAGE SEGMENTATION USING FUZZY LOGIC AND GENETIC
Department of Computer Science, Sultan Qaboos University
P.O Box 36, Al-Khod 123
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 membership functions that are necessary to classify the strength of existence of image features through FL. Since range and intensity images provide different types of sensory modality, fusing the extracted features from these images reveals more accurate information 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.
Keywords: Edge detection; Fusion systems; Fuzzy set; GAs; Image segmentation.