Abstract
Abstract: This paper presents a new fuzzy-logic approach for character perclassification which gives us a precise way of calculating the baseline detection algorithm with tolerance analysis through analyzing typographical structure of textual blocks. The other virtual reference lines are extracted from clustering techniques. In order to ensure character preclassification correctly, a fuzzy-logic approach is used to assign a membership to each typographical category for ambiguous classes. The results prove that and improved character recognition rate can be achieved by means of typographical categorization. Fuzzy Typographical Analysis (FTA) can correctly preclassify characters and can efficiently process more than 10,000 characters per second.