Automatic hand writer identification using the feed forward neural networks

Abstract

The paper justifies the necessity to use the hand writer identification using the feed forward neural networks. Identifying the authors of a handwritten sample using automatic image-based processing methods is an interesting pattern recognition problem with direct applicability in the legal and historic documents. Leading a worrisome life among the harder forms of biometrics, the identification of a writer on the basis of handwriting samples still remains a useful biometric modality, mainly due to its applicability in historical and the forensic field.