A novel modality independent score-level quality measure

The performance of biometric systems deployed in real world scenarios is affected adversely by the degradation in the input quality. This degradation can take place either in the input or due to inherent design of the deployed system. Quality Measures aim to provide a quantitative indication of this degradation which can be utilized to help access the probability that the provided biometric decision is correct. In this paper we present a novel, modality independent, score level quality measure based on Mahalanobis Distance. This measure exploits the inter-dependencies which exist between the data and matching score to reduce the error rates and improve the performance of the deployed biometric system. The effectiveness of the proposed approach is verified by extensive testing using the standard databases available of fingerprints and Iris data.