Handwritten Indian numeral recognition system using template matching approaches

A recognition system for identifying handwritten Indian (Arabic) numerals one to nine (1-9) has been developed. A graphical user interface was developed using advanced object oriented techniques that incorporates Matlab^(R) as a technical tool. The process involved extracting a feature vector to represent the handwritten sketch based on the “object” centroid and boundary points. A template vector was derived for each digit by taking the average feature vector of 30 handwritten sketches made by 30 different students. The test sketch is compared against all nine templates and a distance measure is used to perform the recognition. An overall hit ratio of 87.22% was achieved in the preliminary results. The ratio reached 100% for some of the digits. But there was misinterpretation between similar digits such as 7 and 4. This study is meant to be the initial stage of building a recognition system for Arabic language characters