Exploiting Data-Rich 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 is data-rich in terms of feature quantity or quality then these regions of specific interest can be exploited, for example in terms of processing algorithm selection and information weighting. Also, if intra-area stability/feature repeatability can be obtained a-priori this information may 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 indicating the potential for the approach.