A NEURO-FUZZY GRAPHIC OBJECT CLASSIFIER WITH MODIFIED DISTANCE MEASURE ESTIMATOR
نویسندگان
1 DEPARTMENT OF COMPUTER-AIDED CONTROL SYSTEMS, AZERBAIJAN STATE OIL ACADEMY, BAKU, AZERBAIJAN
2 EASTERN MEDITERRANEAN UNIVERSITY, NORTH CYPRUS
3 MEMBER IEEE, DEPARTMENT OF COMPUTER-AIDED CONTROL SYSTEMS, AZERBAIJAN STATE OIL ACADEMY, BAKU, AZERBAIJAN
doi
10.22111/ijfs.2004.489چکیده
The paper analyses issues leading to errors in graphic object classifiers. Thedistance measures suggested in literature and used as a basis in traditional, fuzzy, andNeuro-Fuzzy classifiers are found to be not suitable for classification of non-stylized orfuzzy objects in which the features of classes are much more difficult to recognize becauseof significant uncertainties in their location and gray-levels. The authors suggest a neurofuzzygraphic object classifier with modified distance measure that gives betterperformance indices than systems based on traditional ordinary and cumulative distancemeasures. Simulation has shown that the quality of recognition significantly improveswhen using the suggested method.
