A smoothness index based approach for off-line signature verification

Proposes a method to tackle the problem of detecting skilled forgeries in off-line signature verification. Inspired by the approach adopted by expert examiners, it is based on a smoothness criterion. From a collection of genuine and forged signatures, it is observed that, although skilled forgery signatures are very similar to genuine ones on a global scale, they are generally less smooth and natural on a detailed scale than the genuine ones, especially for those skilled forgery signatures which consist of cursive graphic patterns. A smoothness index is derived from such signatures. This is combined with other global shape features and used for verification. Satisfactory results are obtained.