Direct gray-scale minutiae detection in fingerprints.pdf

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 19, NO. 1, JANUARY 1997 27 YO Direct Gray-Scale Minutiae Detection In Fingerprints A ... Dario Maio, Member, /€€E, and Davide Maltoni Abstract-Most automatic systems for fingerprint comparison are based on minutiae matching. Minutiae are essentially terminations and bifurcations of the ridge lines that constitute a fingerprint pattern. Automatic minutiae detection is an extremely critical process, especially in low-quality fingerprints where noise and contrast deficiency can originate pixel configurations similar to minutiae or hide real minutiae. Several approaches have been proposed in the literature; although rather different from each other, all these methods transform fingerprint images into binary images. In this work we propose an original technique, based on ridge line following, where the minutiae are extracted directly from gray scale images. The results achieved are compared with those obtained through some methods based on image binarization. In spite of a greater conceptual complexity, the method proposed performs better both in terms of efficiency and robustness. Index Terms-Fingerprints, minutiae, feature extraction, gray scale images, directional image 1 INTRODUCTION INGERPRINT-BASED identification has been known and F used for a very long time 151, 191, [ l l ] and 1241. Owing to their uniqueness and immutability 1191, fingerprints are today the most widely used biometric features. Most auto- matic systems for fingerprint comparison are based on mi- nutiae matching 1121, [22], [26] and 1361. Minutiae, or Gal- ton’s characteristics 191, are local discontinuities in the fin- gerprint pattern. The American National Standards Insti- tute has proposed a minutiae classification based on four classes: terminations, bifurcations, frifurcations (or crossovers) and undetermined [l]. In this work we adopt the identifica- tion model used by the Federal Bureau of Inv