Professional Documents
Culture Documents
Abstract traction.
Many kinds of enhancement methods for fingerprint im-
In rhis pape,: an improved algorirhm for enhancemenr age have been proposed in the literatures [I]-[7]. Most of
of fingerprim image is proposed on the basis of rhe image them are based on image binarization, while some others
normalizarion and Gabor filrer Firsrly, rhe adaptive nor- enhance images directly from gray scale images [11-[6]. In
malizarion based on block processing is suggesrrd for im- the approach for the gray scale images, the enhancement al-
prnvemenr offngerprinr images. An inpur image is parri- gorithm includes the following main steps 121 as shown in
rioned inro sub-blocks wirh rhe size of K x L arfirsr and Fig. I : I ) Normalization. 2) Local orientation estimation,
rhe region of inreresr (ROI) of rhe fingerprinr i m g e is ac- 3) Local frequency estimation, and 4) Filtering by a hank of
quired. The parameters for the image normalizarion are the designed filters.
adaptively determined according ro rhe srarislics of each In the normalization step. an input fingerprint image is
block. By urilizing these paramerers. the block image is normalized to decrease the dynamic range of the gray scale
normalized for the nexr process. Secondly, a new rechnique between ridges and valleys of the image in order to facilitate
for selecrion of hvo imporranr parameters of Caborfilrer is the processing of the following steps. And the orientation
devised. Thest parameters are rhe ridge direcrion and rhe image is estimated from the normalized lingerprint image
ridge frequency. In this sfudy, the ridge direction of a block by employing the gradient information. In the next step. the
i m g e is derermined by rhe probabilistic approach unlike frequency image is computed from the normalized image
orher works. Wirh rhis ridge direction, rhe ridge frequency and the estimated orientation image. A hank of pre-tuned
is selected by urilizing rhe direcrional projecrion. The pro- filters is applied to the ridge and valley pixels in the nor-
posed algorirhms are rested wirh NISTfingerprinr images malized fingerprint image to obtain an enhanced fingerprint
and show significmr improvemenr in the experiments. image in the last step. In general, Gabor filter is employed
for enhancement of the fingerprint image.
G(i,j)=
2.2 Automatic Selection of Parameters for Gabor
filter
880
proposes an automatic selection technique of 8 and f for
Gabor filter.
-
to obtain the ridge direction, the range of angle of the ridge
is given as [-goo +90°]. In this range, the angle is
quantized by an equi-interval q to compute the distribution
Figure 3. Scheme for Ihe direction projection
881
(C) (dl
the frequency of the ridge lines can be easily selected. [2] L. Hong. Y. Wan and A. Jain. “Fingerprint Images
Finally, the enhanced fingerprint images are displayed Enhancement Algorithm and Performance Evaluation,”
in Fig. 6. As shown in the result. it can he known that the I&&€ Trans. on Parrern Analysis and Machine Inrelli-
proposed enhancement algorithm produces very reliable re- genre. Vol. 20, No. 8,pp. 777-789. 1998.
sults. 131 S. Greenberg, M. Alsdjem. D.Kogan and 1. Dimitrov,
”Fingerprint Image Enhancement Using Filtering Tech-
4 Conclusions niques.” Proceedings of the 15-rh Inrernarionnl Con-
ference on Paffern Recognition. Vol. 3 , pp. 322.325,
In this study. a new enhancement algorithm for finger- 2000.
print images is proposed by utilizing the adaptation for the 141 S:I. Park, M. 1. T. Smith and J.-J. Lee. “Fingerprint
propenies of the local regions and the automatic selection Enhancement Based on the Directional Filter Bank,”
of parameters for Gabor filter. By taking the local property Proceedings oflnrernarional Conference on Image Pro-
into account. the adaptive normalization process could en- cessing. Vol. 3. pp. 793- 796,2000.
sure the reliable fingerprint texture region of the given fin-
gerprint image. although the image has a poor quality. [SI A. K. Jain, R. B o k and S. Pankanti. Biomerrics: Per-
To obtain the final enhanced image by employing Gahor sonal Idenr$calion in Nenvorked Society,Kluwer Aca-
filter, the automatic selection technique for two important demic Publishers. 1999.
parameters of filter is devised. As shown in experiments. 161 G:S. Choi. K.-W. Lee and et al., “Fingerprint Verifi-
the proposed algorithms are very useful for enhancing the cation System with Improved Image Enhancement and
fingerprint images. Reliable Matching:’ Proceedings of Inrernarional Con-
ference on Consumer &/ectmnics, pp. 4-5.2000.
References 171 Xiping Luo and J. Tian. “Knowledge Based Fingerprint
Image Enhancement:’ Proceedings of rhe 6 t h Inter-
[ I ] D.Simon-Zorita, J. Onega-Garcia. S. Cmz-Llanas. 1. narional Conference on Parrern Recognirion.Vol. 4. pp.
L. Sanchez-Bote, and J. Glez-Rodriguez, “An Improved 783-786.2000.
Image Enhancement Scheme for Fingerprint Minutiae
882