This paper presents a novel fusion algorithm that combines fingerprint match scores to provide high accuracy under non-ideal conditions.
Existing algorithms that fuse level-2 and level-3 fingerprint match scores perform well when the number of features are adequate and the quality of images are acceptable. In practice, fingerprints collected under unconstrained environment neither guarantee the requisite image quality nor the minimum number of features required. In the current project, the match scores obtained from level-2 and level-3 classifiers were first augmented with a quality score that was quantitatively determined by applying redundant discrete wavelet transform to a fingerprint image. The authors next applied the generalized belief functions of Dezert–Smarandache theory to effectively fuse the quality-augmented match scores obtained from level-2 and level-3 classifiers. Unlike statistical and learning based fusion techniques, the proposed plausible and paradoxical reasoning approach effectively mitigates conflicting decisions obtained from classifiers, especially when the evidence is imprecise due to poor image quality or limited fingerprint features. The proposed quality-augmented fusion algorithm is validated using a comprehensive database which consists of rolled and partial fingerprint images of varying quality with arbitrary number of features. The performance is compared with existing fusion approaches for different challenging realistic scenarios. (Published abstract provided)