A Short Method for On-line Handwritten Character Recognition Bandara G.E.M.D.C. University of Peradeniya dcb@pdn.ac.lk Pathirana S.B University of Peradeniya Ranawana R.M. University of Peradeniya rranawana@sltnet.lk Abstract Handwritten characters differ from person to person. Thus, when using traditional methods like Neural Networks and Image Processing techniques, extensive training of the system is needed. Due to this reason, an attempt was made to develop a system that used the methods that humans use to perceive handwritten characters. Thus, a system that recognizes features in handwritten characters using Fuzzy Logic was developed. The reasons for the selection of Fuzzy Logic were as follows: 1. Fuzzy Logic can be used to model human perception 2. The mathematics that Fuzzy Logic requires is extremely fundamental. Thus, any algorithm developed using fuzzy logic would require relatively simple and short calculations. 3. Due to simplicity of fuzzy calculations, they can be implemented on any hardware or software platform without too much concern for computing power. The objectives in the development of this method were: 1. The development of a short and efficient algorithm that tries as much as possible to model human perception. 2. The development of an algorithm that can be implemented on any hardware or software platform through low computational power requirements. 1. Introduction The goal of handwriting recognition is to interpret the contents of an incoming sequence of data, and to generate a description of it in the desired format. There are two distinct areas of research concerning Handwritten Character Recognition, Off-line Character recognition and On-line Character Recognition. Off-line character description data only provides the list of coordinates. This is due to the reason that these images are usually of characters that were written earlier and later converted to digital format using a digital scanner. In contrast, On-line character description data provides much more information for perception. Features like, the direction of movement, the number of pen-ups and pen- downs etc. are extremely useful. Also, the coordinates are presented in a time-ordered fashion, which allow the system to know the order of the coordinates and segments in which the writer wrote the character. The challenge with On-line character recognition is the development of a system that can recognize these characters in real-time. This requires a system that requires very simple and short calculations. If not, the time taken to recognize the characters will render the system useless. Thus, the method selected for this research was Fuzzy Logic. 2. Method Used Fig ure 1. M et ho d u s ed 3. Data Structure Used Information about each segment is stored in a separate variable. TYPE Segment points(0 To MAX_POINTS) As Coordinate number_of_points As Integer