ABSTRACT

Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a personal Digital Assistant (PDA), in postal addresses on envelopes, in amounts in bank checks, in handwritten fields, in forms etc. To solve the problem of writer identification with intermediate classes (writers) and objects (characters) , it is a good way to extract the features with clear physical meanings. The extracted features are in variant under translation scaling and stroke width.The off-line (which pertains to scanned images) is considered. Algorithms of preprocessing, character and word recognition, and performance with practical system are indicated. The recognition rate of Radial Basis Function (RBF) is found to be better compared to that of Back Propagation Network (BPN). The recognition rate in the proposed system lies between 90% to 100%.

Keywords: - Neural Network, writer identification, back propagation and Radial Basis Function (RBF)