Абстрактный

A New Method for Recognition of Handwritten Characters Using Edge Detection, Segmentation and Pattern Matching

Monish Dutta, Pritha Roy, Sunanda Datta, Asoke Nath

To convert handwritten character to printed character is a very challenging problem in computer science and information technology. It can save time and makes human’s job easier. Character reorganization device is one of such smart devices that acquire partial human intelligence with the ability to capture and recognize various characters and digits. Character recognition comes into picture when various patterns of handwritten or printed characters are to be recognized digitally. Many researchers have proposed different approaches for character recognition in different languages. In this paper, a system is developed for the recognition of basic characters (vowels, consonants and numbers) in handwritten and printed English text, which can handle different font sizes and font types. The main important phases of character recognition include pre-processing, segmentation, feature extraction and matching. The authors proposed a new but simple method to recognize Handwritten Character. There is a scope for further enhancement of this method to make the algorithm more robust and intelligent.