Enhancement of Fingerprint Images Using Gabor Filter
Keywords:
image enhancement, Gabor filter, direction field, coherence, fingerprintAbstract
The paper deals with fingerprint image filter method using Gabor filter. Enhancement is often required in verification, identification and classification problems as a preprocessing step for robust feature extraction. Gabor filter is one of the most efficient methods to enhance images with periodic structure. However, Gabor filter needs parameterization due to different line orientations at different regions of fingerprint images. Modified Gabor filter, designed considering direction field of the image, can solve this problem. In addition, calculation of coherence allows to select the clearest image segments, which are considered as regions of interest for further calculations.References
Bazen A.M. Fingerprint Identification – Feature Extraction, Matching, and Database Search, Ph.D. Dissertation. Univ. of Twente, Enschede, The Netherlands, 2002. 187 p.
Maltoni D., Maio D., Jain A.K., Prabhakar S. Handbook of Fingerprint Recognition. New York, Springer-Verlag, 2003. 510 p.
Hong L., Wan Y., Jain A.K. Fingerprint Image Enhancement: Algorithm and Performance Evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, vol. 20, pp. 777–789.
Yang J.W., Liu L.F., Jiang T.Z., Fan Y. A Modified Gabor Filter Design Method for Fingerprint Image Enhancement. Pattern Recognition Letters, 2003, vol. 24, no. 12, pp. 1805–1817.
Wang W., Li J., Huang F., Feng H. Design and Implementation of Log-Gabor Filter in Fingerprint Image Enhancement. Pattern Recognition Letters, 2008, vol. 29, no. 3, pp. 301–308.
Гонсалес Р. Цифровая обработка изображений. М.: Техносфера, 2005. 1072 с. [Gonzales R., Woods R. Tsifrovaya obrabotka izobrazheniy (Digital Processing of the Images). Мoscow, Tekhnosfera Publ., 2005. 1072 p.]
