A hybrid fingerprint matcher in memory constrained environments

Hybrid fingerprint matchers are well known as a powerful tool for high security applications where the reliability of a single fingerprint characteristic is not high enough for the intended application. In this paper, we propose a novel method, which due to its compressibility can be applied in memory constrained environments. This is important for application in smart cards and independent identification modules, which recently gained popularity. The proposed method uses minutia point matcher as the first stage of matching, and, after successfully completing this stage, the second stage of matching is based on comparing the homogeneity of a direction map. The direction map is compressed using a quad tree.