Online isolated handwriting and text recognition based on annotated image features

Abstract

The representation schemes of input pattern and model database are of particular importance since a classification method depends largely on them (Liu et al ., 2004). Selecting the data representation is one of the most fundamental decisions to make (Jong, 2001). This chapter describes the simple techniques involved in extracting the annotated image features from online handwriting as well as printed isolated English alphabets and their representation in a standard form to be used by the recognition stage. Conventionally, the data obtained needs a lot of preprocessing including filtering, smoothing, slant removing and size normalization before recognition process. Instead of doing such lengthy preprocessing, here we present an easy approach to extract the useful character information. Here, the neural network approaches have been used for a writer-independent recognition system.