| Summary: | 碩士 === 國立中山大學 === 機械與機電工程學系研究所 === 94 === As information technologies advanced greatly in recent years, the security problem of information networks becomes all the more important. As a result, biometric identification techniques have been given considerable attention. Fingerprint-related techniques, due to these desirable properties, i.e., universality, perpetuity, collectability and particularity, are most widely applied and documented.
However, in practice, collected fingerprint images are not always of good quality. They often are noisy or are even partial images. Therefore, in this research, we propose a new minutiae matching method, while using a coefficient of variation of orientation difference, a coefficient of frequency correlation, along with other image features to obtain a match based on only partial fingerprints.
By the proposed method, when a score is arrived at and the test image and the database image have five minutia points matched, we have both FRR and FAR values close to 29%, and the correctness of matching reaches 70.56%.
|
|---|
