Regions of interest in static signature verification

The identification and subsequent utilisation of regions of interest within biometric sample images can provide useful information that can benefit recognition performance . If a specific area of a biometric sample contains an enhanced quantity of feature information then these regions-of-specific-interest can be exploited for example in terms of processing and information weighting. Also, if intra-area stability/feature repeatability can be obtained apriori this information can be used to enhance biometric systems. The objective of the work documented in this paper is to develop a best practice framework for the utilisation of sub-regions-of-interest within biometric signature images to enable an optimisation of systems. Our hypothesis is that by sub-dividing a signature image, information richness within sub-divisions can be exploited by weighting grid zones. Signature images were divided using 14 experimental template patterns. Using the GPDS-960 off-line signature corpus, the verification performance achieved using each weighted method was compared against a non-gridded baseline implementation. Significant improvements were noted for a number of the defined grid zones indicting the potential for the approach.