Journal of Signal and Information Processing, 2013, 4, 150-153
doi:10.4236/jsip.2013.43B026 Published Online August 2013 (http://www.scirp.org/journal/jsip)
Local Orientation Field Based Nonlocal Means Method fo r
Fingerprint Image De-Noising
J. Zou, J. B. Feng, X. M. Zhang, M. Y. Ding
School of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China.
Received May, 2013.
ABSTRACT
The de-noising of the fingerprint image is one of the key tasks before the extraction of the minutiae in automatic finger-
print matching. When used for de-noising the fingerprint image, the nonlocal means method can not preserve the local
minutiae in the fingerprint image very well. To address this problem, we propose a local orientation field based nonlo-
cal means (NLM-LOF) method in this paper. Experimental results on the simulated and real images show that the pro-
posed method can suppress noise effectively while preserving edges and details in the fingerprint image and it outper-
forms the state-of-art nonlocal means method in terms of qualitative metrics and visual comparisons.
Keywords: Fingerprint Image Denoising; Nonlocal Means Filtering; Orientation Field
1. Introduction
As one of the most important biometric technologies,
fingerprint identification has been widely used in identity
recognition. Usually, fingerprint identification relies
heavily on the performance of the minutiae extraction
algorithm[1]. However, due to complex identify condi-
tio- ns, the acquired fingerprint images are usually con-
taminated with noise which is disadvantageous for the
minutiae extraction. So it is desirable and crucial to de-
sign a robust filter to preserve the local minutiae and
improve the clarity of the ridge structures.
Many de-noising algorithms have already been pre-
sented to remove noise in the fingerprint images. Liang,
et.al [2] proposed the morphological amoebas method to
simultaneously reduce noise and preserve useful details
with the help of pilot images from canny edge detection.
Liang, et.al [3] developed a combinatorial linear time
algorithm to eliminate impulsive noise and useless com-
ponents from fingerprint images using Euclidean dis-
tance transform. In [4], Bayesian de-noising in the wave-
let domain was presented to realize fingerprint image
de-noising. All these methods tend to damage edges and
details in the fingerprint images because they only use
local information in the images.
Different from the above mentioned methods, the
non-local means filter recently proposed by Buades [5]
takes advantage of the redundancy of similar patches in
the images and estimates the considered pixel with a
weighted average of all the pixels in its neighborhood or
the whole image. However, the performance of the tradi-
tional non-local means (TNLM) method will be greatly
influenced by similarity window and similarity computa-
tion method. Many novel solutions have been proposed
to address this problem such as the NLM-
Reprojections (NLM-R) method [6], the NLM using
Shape Adaptive Patches (NLM-SAP) [7]. Although these
improved methods perform better than the traditional
NLM, they cannot preserve fringes and minutiaes effec-
tively. In this paper, we propose a novel nonlocal means
filter based on the estimation of the orientation field.
Compared with above state-of-art de-noising methods,
the proposed method is more robust and it can preserve
minutiae better while suppressing noise in the fingerprint
images.
2. Our Method
In the TNLM method, for the considered pixel (m,n) in
the noisy image, the corresponding non-local means
de-noised intensity NL(m,n) in the search window Ω is
calculated as [5]:
(,)
(,)
(,,,)(,)
(,) (,,,)
pq pq
wmnpqvpq
NL m nwmnpq


 (1)
where denotes the intensity of pixel (p,q),
w(m,n,p,q) denotes the similarity of two pixels (m,n) and
(p,q) and it is computed as:
v(p,q)
2,
2
1
(,) (.)
(,,,)
ssa
vmnvpq
h
wmnpq e


 (2)

Local Orientation Field Based Nonlocal Means Method for Fingerprint Image De-Noising 151
where means the decay parameter .and
denote the intensities of similarity windows s
centered at (m,n) and (p,q).
1
h
), q),( nmvs (pvs
a,2denotes the Gaussian
weighted Euclidean distance convolved with a Gaussian
kernel of standard deviation a. As we can see, the TNLM
method utilizes the geometrical configuration in a neigh-
bourhood to determine the pixel similarity, but its igno-
rance of the orientation field will degrade its perform-
ance in restoring the fingerprint image. Considering that
a well estimated orientation field can facilitate repre-
senting geometrical features effectively, we introduce the
orientation field into the traditional nonlocal means to
obtain improved de-noised results.The local orientation
of each block centered at pixel (m, n) is estimated as [1]:

22
(,)2 (,)(,)
22


 
 
WW
mn
Vmnuvuv
xx
WW
um vn y

(3)

∂∂

WW
m+ n+
2222
V(m,n)=(u,v)-(u,v)
yxy
WW
u=m- v=n-
22
(4)


(,)
11
(,)tan
2(,)


Vmn
y
mn Vmn
x (5)
where and denote the gradients of pixel
(m,n),which is calculated by Sobel operator[8].
(,)Vmn
y(,)Vmn
x
(,)

mnis
the least square estimate of the local ridge orientation of
the block W centered at pixel (m,n). Then we adjust the
weigh{( using orientation information
(,)
)} pq ,,wmnp,q

.
2
2
2
2
1
,2),(),(
).(),(
),,,( h
qpnm
h
qpvnmv
eeqpnmw
a
ss 



(6)
where 2 his the decay parameter. It can be seen from (6)
that different from the TNLM method, the proposed
method determines the weight by utilizing both the gray
values of image patches and the local orientation field.
To demonstrate the superiority of the proposed method
in weight calculation, we use the noisy images with
standard deviation σϵ{50,60,70} shown in Figure 1(a)
and compute the distribution of the similarity between
the center pixel and other pixels in each test image. Fig-
ure 1(b) and Figure 1(c) shows the weight distribution
for the two compared methods, where its values go from
one (white) to zero (black). It can be seen from Figure 1
that our method can determine the similarity more effec-
tively than the TNLM method, especially at high noise
corruption.
3. Experiments
In this section, the fingerprint image simulated using
fingerprint generator software released at http://www.ia.c
as.cn/kygz/kycg/rjdj/200910/t20091010_2542737.html
and the real fingerprint image are used as the test images.
For simulation experiments, gaussian white noise with
the standard deviation

ϵ{20,30,40,50} is added to the
simulated fingerprint image. The restoration performance
of the TNLM, the NLM-R, the NLM-SAP and the pro-
posed NLM-LOF is appreciated using peak signal-to-
noise ratio (PSNR) and structural similarity
σ = 50 σ = 60 σ = 70
(a)
σ = 50 σ = 60 σ = 70
(b)
σ = 50 σ = 60 σ = 70
(c)
Figure 1. The distribution of weight similarity between the
center pixel and other pixels in the noisy images. (a). noisy
images with different standard deviations, (b). the weight
distribution for the TNLM method, (c). the weight distribu-
tion for the NLM-LOF.
index [8] (SSIM). In all the experiments, we choose the
search window size and the similarity window size to be
5×5 and 3×3, respectively. The filtering parameter h (the
same for h1 in the NLM-LOF) is fixed to 6*

and 2 is
tuned to obtain the best restoration performance for the
proposed NLM-LOF. Table 1 lists the PSNR and SSIM
values of all the de-noising methods operating on the
corrupted fingerprint image. The observation from Table
1 demonstrates that our method has the best restoration
performance in that it outperforms the compared methods
in terms of the PSNR and SSIM measurement.
h
To visualize such improvement, we illustrate the
de-noised images in Figure 2. As we can see, Figure 2(d)
is more similar to the ground truth than Figure 2(c) and
the edges are significantly protected while the TNLM
(Figure 2(c)) oversmooth the whole image.

Local Orientation Field Based Nonlocal Means Method for Fingerprint Image De-Noising
152
Besides, we test the two methods on a real fingerprint
image shown in Figure 3(a). Figure 3(b) is the zoomed
view of labeled region In Figure 3(a). Much noise still
exists in the image de-noised by the TNLM method (Fig-
ure 3(b)) and the important anatomical details are
blurred. By comparison, the NLM-LOF can suppress
noise effective- ly while preserving the anatomical de-
tails very well as shown in Figure 3(d).
4. Conclusions
We have proposed the local orientation field based
nonlocal means method. Compared with the state-of-art
nonlocal means filter, the proposed method can de-noise
the fingerprint images more effectively because it utilizes
more feature information to represent the structural simi-
larity of pixels in the image. Experiments on simulated
and real fingerprint images demonstrate the effectiveness
of the proposed method in restoring the corrupted finger-
print image in terms of noise reduction and detail pres-
ervation.
Table 1. Comparisons of the PSNR values and SSIM value-
sof the de-noised results on different standards noisy im-
ages.
(a) (b)
(c) (d)
Figure 2. De-noising experiment on a simulated image. a.
the original image, b. noisy image (), c. result with
NLM, d. result with NLM-LOF.
40 
( a) (b)
(c) (d)
Figure 3. Comparisons of the de-noising results for the
TNLM and NLM-LOF operating on a real fingerprint im-
age. a.original image, b. zoomed view of the labeled region,
c. result with TNLM, d.result with NLM-LOF.
5. Acknowledgements
This work was partly supported by the National Natural
Science Foundation of China (Grant No.:30911120497),
the National 973 project (Grant No.: 2011CB933103),
the Project of the National 12th-Five Year Research Pro-
gram of China (Grant No.: 2012BAI13B02) and Project
of National High Technology Research and Development
Program of China（Grant No.:2013AA040206).
REFERENCES
[1] L. Hong, Y. F. Wan and A. Jain, “Fingerprint Image En-
hancement Algorithm and Performance Evaluation,”
IEEE Transactions on Pattern Analysis and Machine In-
telligence, Vol. 20, No. 8, August 1998.
[2] Y. Y. Liang and P. Z. Wen, “Fingerprint Image Denois-
ing using Morphological Amoebas,” International Con-
ferences on Intelligent Computing and Integrated Systems
(ICISS), 2010, pp.197 - 200.
[3] X. F. Liang and T. ASANO, “A Linear Time Algorithm
for Binary Fingerprint Image Denoising Using Distance
Transform,” IEICE TRANS. INF. & SYST., Vol. E89-D,
No.4, April 2006.
[4] Portilla, J. Strela, V. Wainwright and M. J. Simoncelli,
“Image Denoising using Scale Mixtures of Gaussians in
the Wavelet Domain,” IEEE Transactions on Image
Processing, Vol. 12, No. 11, 2003, pp. 1338-1351.
doi:10.1109/TIP.2003.818640
[5] A. Buades, B. Coll and J. Morel, “A Nonlocal Algorithm
for Image Denoising,” IEEE International Conferences
on Computer Vision and Pattern Recognition (CVPR),
Vol. 2, 2005, pp. 60-65.
[6] J. Salmon and Y. Strozecki, “From Patches to Pixels in
Non-Local methods:Weighted-Average Rep-rojection,”
International Conferences On Image Processing (ICIP),
2010, pp. 1929-1932.
[7] C.-A. Deledalle J. Salmon and V. Duval, “Non-Local

Local Orientation Field Based Nonlocal Means Method for Fingerprint Image De-Noising
153
Methods with Shape-Adaptive Patches (NLM- SAP),”
Journal of Mathematical Imaging and Vision (JMIV), Vol.
43, 2012, pp. 103-120. doi:10.1007/s10851-011-0294-y
[8] Z. Wang, A. C. Bovik, H. R. Sheik and E. P. Simoncelli,
“Image Quality Assessment: From Error Visibility to
Structural Similarity,” IEEE Transactions on Image Proc-
essing, Vol. 13, No. 4, Apr. 2004, pp. 600-602.
doi:10.1109/TIP.2003.819861