A novel approach for off-line signature recognition system is
presented in this work, which is based on local radon features. The
proposed system functions in three stages. Pre-processing stage; which
consists of three steps: gray scale conversion, binarisation and fitting
boundary box in order to make signatures ready for feature extraction,
Feature extraction stage; where totally 16 radon transform based
projection features are extracted which are used to distinguish the
different signatures. Finally in Neural Network stage; an efficient Back
Propagation Neural Network (BPNN) is designed and trained with 16
extracted features. The trained Neural Network is further used for
signature recognition after the process of feature extraction. The average
recognition accuracy obtained using this model ranges from 97%-87%
with the training set of 10–40 persons.