This paper presents a neuro-fuzzy system by using the Kohonen 's self-organizing feature map algorithm, not only for its vector quantitization feature, but also for its topological property This property prevents the proposed neuro-fuzzy system from suffering from a drawback like any of the conventional clustering algorithm based fuzzy systems, i.e. the optimal number of clusters or some kind of similarity threshold must be predetermined. Associated with the self-organizing feature-map-based fuzzy system is a hybrid learning algorithm, which is for initial parameters setting and fine-tuning the parameters of the system. Application of the proposed fuzzy systems in optical handwritten digits recognition is reported. High recognition rates can be achieved.