11 3 15 PDF
11 3 15 PDF
11 3 15 PDF
Introduction
traction.
Many kinds of enhancement methods for fingerprint image have been proposed in the literatures [1]-[7]. Most of
them are based on image binarization, while some others
enhance images directly from gray scale images [1]-[6]. In
the approach for the gray scale images, the enhancement algorithm includes the following main steps [2] as shown in
Fig. 1: 1) Normalization, 2) Local orientation estimation,
3) Local frequency estimation, and 4) Filtering by a bank of
the designed filters.
In the normalization step, an input fingerprint image is
normalized to decrease the dynamic range of the gray scale
between ridges and valleys of the image in order to facilitate
the processing of the following steps. And the orientation
image is estimated from the normalized fingerprint image
by employing the gradient information. In the next step, the
frequency image is computed from the normalized image
and the estimated orientation image. A bank of pre-tuned
filters is applied to the ridge and valley pixels in the normalized fingerprint image to obtain an enhanced fingerprint
image in the last step. In general, Gabor filter is employed
for enhancement of the fingerprint image.
Inp ut image
No rmalizatio n
O rientatio n
Image
Lo cal freq uency
estimatio n
Enhanced image
F iltering
of the fingerprint image. To get the enhanced fingerprint image, the original input image is partitioned into sub-blocks
with the size of K L and normalized with the local property for the next process. Unlike other works which employed the average method of the gradient image, we devise
a probabilistic approach for determination of the ridge direction. Also, the ridge frequency is obtained by employing
the directional projection with the acquired ridge direction.
This paper is organized as follows. In Section 2, the
adaptive image normalization, which is based on the block
processing, is explained in brief. Also, new method for selection of two important parameters of Gabor filter is proposed in Section 2. For the performance validation of the
proposed algorithm, the proposed algorithm is tested with
NIST fingerprint images in Section 3. Finally, we will draw
conclusion for this work in Section 4.
2
2.1
and V ARi are the computed mean and variance of the ith
block, respectively.
The second terms in the right side of the above equations are the variations which are considered as the local
properties of the ith block. As these terms contribute to the
desired parameters, the desired parameters are changed according to local properties of the current block.
Figure 2 shows the result of the adaptive image normalization based on block processing. Figure 2 present the result when 1 = 2 = 0.5 and M0d = 100 and V AR0d = 50.
As shown in Fig 2(a), we can see that the fingerprint image
is not uniform due to some causes. As shown in the result,
the proposed algorithm that utilizes the block based processing can improve the original image by using the devised
adaptive normalization method. This is due to the consideration of the local properties.
q
M + V AR0 (I(i,j)M )2 , I(i, j) > M ,
0
V AR
q
(1)
M V AR0 (I(i,j)M )2 , otherwise,
0
V AR
i M d ),
M0d + 1 (M
0
V ARid
i V ARd ), (3)
V AR0d + 2 (V AR
0
(2)
(a)
(b)
Figure 2. Result for the image normalization of NISTf05: (a) Original image, (b) Adaptive normalization based
on block processing
2.2
y2
1 x2
h(x, y : , f ) = exp{ [ 2 + 2 ]} cos(2f x )
y
2 x
(4)
where is the orientation of the Gabor filter, f is the frequency, x and y are the space constants of the Gaussian
envelope along x and y axes, respectively.
To make use of Gabor filter, two important parameters
must be tuned. These are and f in Eq. (4). This study
Most methods, which utilize the ridge direction to design a filter, use the minimum square adjustment algorithm
or the gradient-based averaging algorithm [1, 2] to implement , easily. But, these algorithms are sensitive to noise.
Thus, we try to make a probabilistic approach in this study.
Firstly, a gradient image is generated to compute the angle of the ridge at each pixel. For a probabilistic approach
to obtain the ridge direction, the range of angle of the ridge
is given as [90o +90o ]. In this range, the angle is
quantized by an equi-interval q to compute the distribution
of the angle or direction of the ridge.
Then, the distribution of the direction of the ridge is generated by the nearest neighbor level concept as following:
Arg minl{90o ,90o +qo ,90o +2qo , ,+90o } |i l|,
(5)
Simulation Results
To verify the proposed algorithm, we have used fingerprint image from the database of NIST Fingerprint Image
Groups. The NIST images derived from digitized inked fingerprints, each consisting of 512 480 pixels, in 8-bits gray
scale. For processing the block unit, the size of the partitioned block is selected 24 24 in this work.
Figure 4 shows the estimation results of the ridge direction in NIST Fingerprint image. Although the noisy clut-
(6)
For estimation of the ridge frequency, the estimated direction of the ridge is employed. Since the direction of the
ridge is given in priori, the ridge image is projected onto the
perpendicular axis of the given ridge direction. The projection data can provide the frequency of the ridge lines in the
current block.
Figure 3 shows the scheme for the directional projection
to estimate the frequency of the ridge. It can be seen that
the waveform from the projection data can give the information of the ridge frequency. By utilizing this waveform,
the frequency of the ridge lines is determined for each block
image, adaptively.
(a)
(b)
(c)
(d)
(a)
(a)
(b)
(c)
(d)
300
250
Magnitude
200
150
100
50
0
0
10
15
30
25
20
Perpendicular axis
35
40
45
50
(b)
Conclusions
In this study, a new enhancement algorithm for fingerprint images is proposed by utilizing the adaptation for the
properties of the local regions and the automatic selection
of parameters for Gabor filter. By taking the local property
into account, the adaptive normalization process could ensure the reliable fingerprint texture region of the given fingerprint image, although the image has a poor quality.
To obtain the final enhanced image by employing Gabor
filter, the automatic selection technique for two important
parameters of filter is devised. As shown in experiments,
the proposed algorithms are very useful for enhancing the
fingerprint images.
References
[1] D. Simon-Zorita, J. Ortega-Garcia, S. Cruz-Llanas, J.
L. Sanchez-Bote, and J. Glez-Rodriguez, An Improved
Image Enhancement Scheme for Fingerprint Minutiae
Figure 6. Final results of the NIST images: (left column)Original images, (right column)-The enhanced images