방향성필터뱅크 기반의 새로운 지문영상의 처리 방법

A New Method of Fingerprint Image Processing Based on a Directional Filter Bank

  • 오상근 (경북대학교 전자공학과 영상신호처리연구실) ;
  • 이준재 (동서대학교 인터넷공학부) ;
  • 박길흠 (경북대학교 전자공학과 영상신호처리연구실)
  • 발행 : 2002.08.01

초록

본 논문에서는 방향성필터뱅크(Directional Filter Bank; DFB)에 기반하여 지문영상을 해석하여 처리하는 새로운 방법을 제안한다. 지문에서 융선의 방향성는 방향성지도를 구성하고, 이로부터 방향성 필터링을 통한 영상 향상을 행하는 등 지문 영상을 해석하는 전처리과정에서 매우 중요한 요소이다. DFB는 입력영상을 방향성대역영상으로 분해한 다음 이로부터 원영상을 완전하게 복원하는 필터이다. 본 논문에서는 DFB를 이용하여 지문영상을 여러 개의 방향성대역영상으로 분해하고, 이로부터 국부 방향성 에너지를 정의한 다음, 이를 기반으로 방향성지도의 제작, 영상분할, 특이점추출 및 영상개선의 처리과정들을 일관되게 수행하는 알고리듬을 제안한다.

This paper presents a new algorithm of fingerprint image analysis and processing using directional filter bank(DFB). The directional components of ridge is very important in pre-processing steps of fingerprint image processing such as image enhancement by directional filtering followed by estimationg the directional image of ridge patterns. The DFB analyzes input image into directional subband images and synthesizes them to the perfectly reconstructed image. In this paper, a new fingerprint processing algorithm using the DFB is proposed. The algorithm decomposes the fingerprint image into directional subband images and performs directional map generation, foreground segmentation, singular points extraction and image enhancement based on local directional energy estimate.

키워드

참고문헌

  1. B.M.Mehtre, 'A Minutiae Based FIngerprintIdentification System', 2nd Int. Conf Advancesin Pattern Recognition and Digital Techniques,Catcutta, 1986
  2. B.M.Mehtre, N.N.Murthy, S.Kapoor,B.Chatterjee, 'Segmentation of FmgerprintImages Using the Directional Image,' Pattern Recognition, 20(4), pp. 429-435, 1987 https://doi.org/10.1016/0031-3203(87)90069-0
  3. B.M.Mehtre, B.Chatterjee, 'Segmentation ofFingerprint Images - A Composite Method',Pattern Recognition, 22(4), pp. 381-385, 1989 https://doi.org/10.1016/0031-3203(89)90047-2
  4. M.Tico, 'A Multiresolution Method for SingularPoints Detection in Fingerprint Images',Proceedings of the 1999 IEEE InternationalSymposium on Circuits and Systems, 4, pp.183-186, 1999
  5. A.K.Jain, S.Prabhakar, L. Hong, 'A Multi-channel Approach to Fingerprint Classification,'IEEE Trans. on PAMI, 21(4), pp. 348-359, Apr.1999 https://doi.org/10.1109/34.761265
  6. A.K.Jain, S.Prabhakar, L.Hong, S.Pankanti,'Filterbank-Based Fingerprint Matching' IEEETrans. Image Processing, 9(5), pp. 849-859,2000
  7. A.Wahab, S.H.Chin, E.C.Tan, 'Novel Approachto Automated Fingerprint Recognition', IEEProc. VISP, 145(3), pp. 160-166, 1998
  8. L.Hong, Y.Wan, A.Jain, 'Fingerprint ImageEnhancement Algorithm and Performance Evaluation', IEEE Trans. on PAMl, 20(8), pp.777-789, 1998 https://doi.org/10.1109/34.709565
  9. B.G.Sherlock, D.M.Monro, K.Millard, 'Finger-print Enhancement by Directional FourierFiltering', IEE Proc. VISP, 141(2), pp. 87-94,1994
  10. R.H.Bamberger, 'The Directional Fitter Bank:A Multirate Filter Bank for the DirectionalDecomposition of Images', PhD thesis, GeorgiaInstitute of Technology, Nov. 1990
  11. R.H.Bamberger, M.J.T.Smith, 'A Filter Bankfor the Directional Decomposition of Images :Theory and Design', IEEE Trans. on Signal Processing, 40(4), pp. 882-893, 1992 https://doi.org/10.1109/78.127960
  12. S.I.Park, M.J.T.Smith, R.M.Mersereau, 'A newDirectional Filter Bank For Image Analysis AndClassification', IEEE International Conference on ASSP, 3, pp. 1417-1420, 1999
  13. 오상근, 박철현, 윤옥경, 이준재, 박길흠, '방향성필터뱅크에 기반한 지문영상의 향상', 한국통신학회 논문지, 27(4A), pp. 345-355, Jul. 2002
  14. C.T.Hsieh, 'An Efficient Method to ExtractFingerprint Singular Point', 4th International Conference/Exhibition on High PerformanceComputing in the Asia-Pacific Region, 2, pp.696-699, 2000
  15. S.I.Park, M.J.T.Smith, J.J.Lee, 'FingerprintEnhancement Based on The Directional FilterBank', International Conference on ImageProcessing, 3, pp. 793-796, 2000
  16. Y.S.Chen, W.H.Hsu, 'A Modified Fast ParallelAlgorithm for Thinning Digital Patterns,'Pattern Recognition Letters, 7(2), pp. 99-106,1988 https://doi.org/10.1016/0167-8655(88)90124-9