On object classification by means of fuzzy sets' theory

Abstract

Presents a practical method for a supervised object classification by means of a decision-making approach using fuzzy sets. The unknown object membership function, as well as the distance between the input symbol and the chosen prototypes, are computed. The classification is made according to the input pattern which maximizes the membership function. The insensitivity of the classification algorithms to the pattern size, misalignment, the possibility of non-complete symbols recognition, and identification of the information source, are accomplished.<>