Offline Verification for Handwritten Signatures Using Chain Code

Background

Many systems have been implemented for signature verification. Ahmed et al. (Abdelrahman et al., 2013) presented an offline signature verification system using support vector machine technique. Global features are extracted from the signatures using radon transform. For each registered user in the database system, several reference signatures are enrolled and aligned for statistical information extraction about his/her signature. Dynamic time warping algorithm is used to align two signatures. During support vector machine classifier training, many genuine and forged signatures are chosen. A signature’s verification is established by first aligning it with each reference signature for the claimed user. The signature is then classified as genuine or forgery, according to the alignment scores which are normalized by reference statistics, using standard pattern classification techniques. Using a database of 2250 signatures (genuine signatures and skilled forgeries) from 75 writers in the proposed signature verification system, a performance of approximately 82% is achieved.