INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
LATENT FINGERPRINT RECOGNITION AND MATCHING USING STATISTICAL TEXTURE ANALYSIS M.CHARAN KUMAR1, K.PHALGUNA RAO 2, ¹ M.Tech 2nd year, Dept. of CSE, ASIT, Gudur, India ² Professor, Dept. of CSE, ASIT, Gudur, India cherry.abu@gmail.com; 2 kprao21@gmail.com;
1
insisted on: distortion, dry, and wet fingerprints.
Abstract: Latent’s are the partial fingerprints that are usually smudgy, with small area and containing large distortion. Due to this characteristic, latent’s have a significantly smaller number of minutiae points compared to full (rolled or plain) fingerprints. The small number of minutiae and noise of latents make it extremely difficult to automatically match latent’s their mated full prints that are stored in law enforcement databases, although a number of methods used for fingerprint recognition to extract accurate results but is not up to level. The proposed fingerprint recognition and matching using statistical analysis gives efficient scheme of fingerprint recognition for biometric identification of individuals. Three statistical features are extracted to represent in mathematical model. They are (1) an entropy coefficient, for intensity histogram of the image, (2) a correlation coefficient, for operation between the original and filter image by using wiener filter, and (3) an energy coefficient, obtaining image in 5-level wavelet decomposition obtained after 5th level decomposition. The approach can be easily used to provide accurate recognition results.
Distortion of fingerprints seriously affects the accuracy of matching. There are two main reasons contributed to the fingerprint distortion. First, the acquisition
of
a
fingerprint
is
a
three-
dimensional/two-dimensional warping process. The fingerprint captured with different contact centers usually results in different warping mode. Second, distortion will be introduced to fingerprint by the no orthogonal pressure people exert on the sensor. How to cope with these nonlinear distortions in the matching process is a challenging task. Several fingerprint matching approaches have been proposed in the literature. These include methods based on point pattern matching, transform features and structural matching. Many fingerprint recognition algorithms are based on minutiae matching since it is widely
believed that
the minutiae are most
discriminating and reliable features. Rather al. Index Terms: - fingerprint recognition, entropy,
addressed a method based on point pattern matching.
correlation, wavelet energy.
The generalized Hough transform (GHT) is used to recover the pose transformation between two
1. INTRODUCTION SIGNIFICANT
impressions. Jain et al. proposed a novel later bank
improvements
recognition have been
in
fingerprint
based fingerprint feature representation method.
achieved in terms of
Jingled.
algorithms, but there are still many challenging tasks.
Addressed a method which relies on a
similarity measure defined between local structural
One of them is matching of nonlinear distorted
features, to align the two pat- terns and calculate a
finger-prints. According to Fingerprint Verification
matching score between two minutiae lists. Fantail.
Competition 2004 (FVC2004), they are particularly
Applied a set of geometric masks to record part of the
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
178
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
rich information of the ridge structure. What et al.
not always well defined and, therefore, cannot be
Addressed a method using groups of minutiae to
correctly detected. A significant number of spurious
define local structural features. The matching is
minutiae may be created as a result. In order to
performed based on the pairs of corresponding
ensure that the performance of the minutiae
structural features that are identified between two
extraction algorithm will be robust with respect to the
fingerprint impressions. However, these methods do
quality of input fingerprint images, an enhancement
not solve the problem of nonlinear distortions.
algorithm which can improve the clarity of the ridge
Recently, some algorithms have been presented to
structures is necessary. However, for poor fingerprint
deal with the nonlinear distortion in fingerprints
image, some spurious minutiae may still exist after
explicitly in order
to improve the matching
fingerprint enhancement and post processing. It is
performance. Proposed a method to measure the
necessary to propose a method to deal with the
forces and torques on the scanner directly. This
spurious minutiae.
prevents capture with the aid of specialized hardware when excessive force is applied to the scanner Doraietal. Proposed a method to detect and estimate distortion occurring in fingerprint videos, but those two mentioned methods do not work with the collected fingerprint images. Mao and Maltonietal. Proposed a plastic distortion model to cope with the nonlinear deformations characterizing finger- print images taken from on-line acquisition sensors. This model helps to understand the distortion process. However, it is hard to automatically and reliably estimate the parameter due to the insufficiency and uncertainty of the information. Doggie Leeetal. Addressed a minutiae-based fingerprints matching
Fig. 1. Feature set of a live-scan fingerprint image. (a)
algorithm using distance normalization and local
Original fingerprint image. (b) Thinned ridge image with minutiae and sample points of (a).
alignment to deal with the problem of the nonlinear distortion.
However,
rich
information
of
the A method to judge whether an extracted minutia is a
ridge/valley structure is not used, and the matching
true one has been proposed in this paper. According
performance is moderate.
to our work, the distance between true minutiae is However, in reality, approximately 10% [20] of
generally greater than threshold (three). While near
acquired fingerprint images are of poor quality due to
the spurious minutiae, there are usually other
variations
ridge
spurious minutiae. On the other hand, spurious
configuration, skin conditions, acquisition devices,
minutiae are usually detected at the border of
and non-cooperative attitude of subjects, etc. The
fingerprint image. Examples of spurious minutiae in
ridge structures in poor-quality fingerprint images are
poor quality fingerprint images are shown in Fig. 2.
in
impression
conditions,
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
179
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
Fingerprint
ISBN: 378 - 26 - 138420 - 5
recognition
(also
known
as
Dactyloscopy) is the process of comparing known fingerprint against another or template fingerprint to determine if the impressions are from the same finger or not. It includes two sub-domains: one is fingerprint verification
and
the
other
is
finger
identification. Verification specify an individual fingerprint by comparing only one fingerprint template stored in the database, while identification specify comparing all the fingerprints stored in the database. Verification is one to one matching and Fig. 2. Examples of spurious minutiae in poor quality
identification is one to N (number of fingerprint
ďŹ ngerprint images. The images have been cropped and
templates
scaled for view. (a) Original image. (b) Enhanced image of
available
in
database)
matching.
Verification is a fast process as compared to
(a), (c) original image, (d) enhanced image of (c). Many
identification.
spurious minutiae were detected in the process of minutiae extraction. Near the spurious minutiae, there are usually other spurious minutiae as indicated in ellipses, and spurious minutiae are usually detected at the border of ďŹ ngerprint image as shown in rectangles.
2. EXISTING SYSTEM A. Fingerprint Recognition Fig.2. Fingerprint Recognition System
The existing algorithm uses a robust alignment
Fig.2 shows the basic fingerprint recognition system.
algorithm (descriptor-based Hough transform) to
First of all we take a fingerprint image. After taking
align fingerprints and measures similarity between
an input image we can apply fingerprint segmentation
fingerprints by considering both minutiae and
technique. Segmentation is separation of the input
orientation field information. To be consistent with
data into foreground (object of interest) and
the common practice in latent matching (i.e., only
background
minutiae are marked by latent examiners), the
ridges) from the background. This is very useful for
marked minutiae, it can be easily used in law
recovering false feature extraction. In some cases, a
enforcement applications. Experimental results on
correct segmentation is very difficult, especially in
two different latent databases show that the proposed two
well
Before
to separate the fingerprint regions (presence of
Since the proposed algorithm relies only on manually
outperforms
information).
extracting the feature of a fingerprint it is important
orientation field is reconstructed from minutiae.
algorithm
(irrelevant
poor quality fingerprint image or noisy images.
optimized
Orientation
commercial fingerprint matchers.
field plays an
important role in
fingerprint recognition system. Orientation field
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
180
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
consist of four major steps (1) pre processing
techniques first of all we find minutiae points on
fingerprint image (2) determining the primary ridges
which we have to do mapping. However, there are
of fingerprint block (3) estimating block direction by
some difficulties when using this approach. It is
projective distance variance of such a ridge (4)
difficult to identify the minutiae points accurately
correcting the estimated orientation field. Image
when the fingerprint is of low quality.
enhancement is use to improve significantly the
• Pattern-based (or image-based) matching:
image quality by applying some image enhancement
Pattern based technique compare the basic fingerprint
technique. The main purpose of such procedure is to
patterns (arch, whorl, and loop) between a previously
enhance the image by improving the clarity of ridge
stored template and a candidate fingerprint. This
structure or increasing the consistency of the fridge
requires that the images be aligned in the same
orientation. Fingerprint classification is used to check
orientation. In a pattern-based algorithm, the template
the fingerprint pattern type. After classification of
contains the type, size, and orientation of patterns
fingerprint. We can apply fingerprint ridge thinning
within the aligned fingerprint image.
which is also called block filtering; it is used to
The candidate fingerprint image is graphically
reduce the thickness of all ridges lines to a single
compared with the template to determine the degree
pixel width. Thinning does not change the location
to which they match.
and orientation of minutiae points compared to original fingerprint which ensures accurate estimation
3. PROPOSED SYSTEM
of minutiae points. Then we can extract minutiae
A. entropy
points and generate data matrix. Finally we can use
Image entropy is an extent which is used to explain
minutiae matching to compare the input fingerprint
the business of an image, i.e. the amount of
data with the template data and give the result.
information which must be implicit for by a compression algorithm. Low entropy Images, such as
B. Fingerprint Matching Techniques
those include a lot of black sky, have very little
There are many Fingerprint Matching Techniques.
difference and large runs of Pixels with the same or
Most widely used matching techniques are these:
parallel DN values. An Image that is entirely flat will have entropy of Zero. Therefore, they can be
• Correlation-based matching:
compressed to a relatively small size. On the other
In correlation based matching the two fingerprint
hand, high
images are matched through corresponding pixels
Entropy images such as an image of heavily formed
which is computed for different alignments and
areas on the moon have a great deal of
rotations. The main disadvantage of correlation based
Thing from one pixel to the next and accordingly
matching is its computational complexity.
cannot be compressed as much as low entropy images. Image entropy as used in this paper is
• Minutiae-based matching:
calculated with the same formula used by the Galileo
This is the most popular and widely used technique,
Imaging Team Entropy
for
fingerprint
comparison.
In
:
minutiae-based
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
181
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
In the above expression, P is the probability 
That the difference between two adjacent pixels
Wiener Filtering:
The Wiener filtering is optimal in conditions of the
Is equal to i, and Log2i is the base 2 algorithm.
mean square error (MSE). In other words, it
Entropy successfully bounds the performance of The strongest lossless compression feasible, which
minimizes the generally mean square error in the
can be realized in theory by using the
development of inverse to remove and noise
Distinctive set or in perform using Huffman.
smoothing. The Wiener filtering is a linear inference of the new image. The advance is based on a stochastic frame. The orthogonality principle implies
B. Correlation
that the Wiener filter in Fourier domain. To complete
Digital Image connection (correlation) and Tracking (DIC/DDIT) is an optical method that employs
the
Wiener
filter
in
perform
we
have
to
tracking & image check techniques for accurate 2-D
approximation the power spectra of the original image. For noise is remove the power spectrum is
and 3-D measurements of change in images. This is
equal to the variation of the noise. To estimate the
often used to measure deformation (engineering),
power range of the original image many methods can
displacement, strain, and visual flow, but it is widely
be used. A through estimate is the period gram
applied in many areas of science and engineering
estimate of the power spectral density (PSD).
calculations. The image is first subjected to a 2-D wiener filter using a 3*3 mask. By using wiener filter to remove the redundant noise or un-wanted pixels.
C. Energy
Digital image correlation (DIC) techniques have been
For calculating the energy coefficient, the image is subjected to a wavelet decomposition using the
increasing in status, especially in micro- and neon-
Daubechies wavelet for up to 5 levels. The wavelet
scale mechanical testing applications due to its relative ease of implementation and use. Advances in
decomposition involves the image with a low-pass
computer technology and digital cameras have been
filter for generating the approximation coefficients
the enabling technologies for this method and while
and a high pass filter for generating the detail
white-light optics has been the leading approach, DIC
coefficients, followed by a down-sampling. The data
can be and has been extensive to almost any imaging
image for each level is taken as the approximation
technology.
image for the previous level. Another related use is in image transforms: for example, the DCT transform
The cross correlation coefficient is defined by
(basis of the JPEG compression method) transforms a
we
blocks of pixels (8x8 image) into a matrix of
represent as r, then we have
transformed coefficients; for distinctive images, it results that, while the original 8x8 image has its energy regularly distributed among the 64 pixels, the
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
182
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
changed image has its energy determined in the lower-upper "pixels”, The decomposition operation generates the approximation coefficientsA5 and Where n is the number of variables, and Xi
detailed coefficients B5,B4,B3,B2,B1 as shown in
And Y is the values of the ith variable, at points X
below.
and Y correspondingly. i The Manhattan Distance is
Ea=∑ (A5)/∑ (B5+ B5+B4+B3+B2+B1)
the distance between two points considered along axes at right angles. The name alludes to the grid
The final feature vector is taken as the complex
explain of the streets of Manhattan, which cause the
formed of the above three components viz.
straight path a car could take between two points in
F= {Cc, En, Ea}
the city. For the 8-puzzle if xi(s) and y(s) are the x
Classification is done by mapping the feature vectors
and y coordinates of tile i in state s, and if upper line
of a training set and a testing set into appropriate
(xi) and upper-line (yii) are the x and y coordinates of
feature spaces and calculating differences using
tile i in the goal state, the heuristic is:
Manhattan distance.
ALGORITHM
FOR
CALCULATING
STATISTICAL TEXTURE FEATURES Input: Query image for which statistical features has
I
been computed. Output: feature vector 1. Calculate Entropy for query image (En) using -sum
Figure 3: Wavelet decomposition of an image
(p.*log2 (p)) formula E. Manhattan Distance
2. Apply wiener filter for query image and then
The distance between two points in a grid base on a
calculate correlation coefficient (CC) for query image
firmly horizontal and/or vertical path (that is, along
and filtered image
the grid lines), as distinct to the diagonal or "as the
3. Apply 5 level decomposition for input query image
crow flies" distance. The Manhattan detachment is
and calculate energy for coefficients (Ea)
the plain sum of the horizontal and vertical works;
4. Calculate feature vector F for query image by
whereas the diagonal span might be computed by
using En, Ea, and CC.
apply the Pythagorean Theorem. The formula for this
Then compare feature vector F of query image with
distance between a point X=(X1, X2, etc.) and a point
the database image and if features are equal then the
Y= (Y1, Y2, etc.) is:
image is matched.
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
183
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
0.420820.
4. EXPERIMENTAL RESULTS The proposed algorithm has been participated in FVC2004. In FVC2004, databases are more difficult than in FVC2000/FVC2002 ones. In FVC2004, the organizers have particularly insisted on: distortion, dry, and wet fingerprints. Especially in fingerprints database DB1 and DB3 of FVC2004, the distortion between some fingerprints from the same finger is large. Our work is to solve the problem of distorted fingerprint matching, so the evaluation of the proposed algorithm is mainly focused on DB1 and DB3 of FVC2004. The proposed algorithm is also compared with the one described by Luo et al. and the
one
proposed
by
Bazen
et
al Fig.5. Experimental results of the proposed algorithm on 103_2.tif and 103_4.tif in FVC2004 DB3. The images have been scaled for view. (a) 103_2.tif. (b) Enhanced image of 103_2. (c) 103_4.tif. (d) Enhanced image of 103_4. The similarity of these two fingerprints is 0.484 111.
5. CONCLUSION This paper has proposed a quick and efficient technique of fingerprint recognition using a set of texture statistical based features. The features are derived from a correlation coefficient, an entropy coefficient and an energy coefficient. The features can be calculated by using fingerprint miniature points. Moreover such texture based by using color finger print images. The fingerprint images may be
Fig.4. Experimental results of the proposed algorithm on
divided in to separation of red, green and blue
102_3.tif and 102_5.tif in FVC2004 DB1. The images have been cropped and scaled for view. (a) 102_3.tif. (b)
components. And output part combine true color
Enhanced image of 102_3. (c)102_5.tif. (d) Enhanced
components. Future work would involve combining
image of 102_5. The similarity of these two fingerprints is
color and shape based techniques to study whether these can be used to improve recognition rates.
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
184
www.iaetsd.in
INTERNATIONAL CONFERENCE ON CURRENT INNOVATIONS IN ENGINEERING AND TECHNOLOGY
ISBN: 378 - 26 - 138420 - 5
6. REFERENCES
IEEE Transactions on Image Processing, 9, 2000,
[1]. A. Lanitis, “A Survey of the Effects of Aging on
pp. 846-853.
Biometric
Identity
Verification”,
DOI:10.1504/IJBM.2010.030415 [2]. A. K. Jain, A. Ross and S. Prabhkar, “An Introduction
to
Biometric
Recognition”,
AUTHORS
IEEE K.Phalguna Rao, completed M.Tech information technology from Andhra University presently Pursuing PhD. Life member of ISTE. He is working as Professor in the Dept of CSE Published several papers in the International Journals and International and national conferences. Attended several International and national workshops. Research Interest areas are Data Base Systems, Network Security, cloud Computing, Bioinformatics.
Transactions on Circuits and Systems for Video Technology, special issue on Image and Video – Based Biometrics, 14, 2004, pp. 4-20. [3]. A. K. Jain, A. Ross and S. Pankanti, “Biometrics: A Tool for Information Security”, IEEE Transactions on Information Forensics and Security. 1, 2000. [4]. A. K. Jain and A. Ross, “Fingerprint Matching Using Minutiae and Texture Features”, Proceeding of International
Conference on
Image Processing
(ICIP), 2001, pp. 282-285. [5]. A. K. Jain, L. Hong, S. Pankanti and R. Bolle, “An
Identity-Authentication
System
using
Fingerprints”, Proceeding of the IEEE. 85, 1997, pp. M.Charan Kumar received sree kalahasthi institute of technology degree in computer science engineering from the Jawaharlal Nehru technology university Anantapur, in 2010, and received the Audisankara institute of technology M.Tech degree in computer science engineering from the Jawaharlal Nehru technology Ananthapur in 2014, respectively. He published one International journal and participated four national conferences and participate One International conference. He worked as communication faculty for 3 years in Kerala and Karnataka.
1365-1388. [6]. D. Maltoni, D. Maio, A. K. Jain and S. Prabhkar, Handbook of Fingerprint Recognition. [7]. S. Chikkerur, S. Pankanti, A. Jea and R. Bolle, “Fingerprint Representation using Localized Texture Features”, The 18th
International Conference on
Pattern Recognition, 2006. [8]. A. A. A. Yousiff, M. U. Chowdhury, S. Ray and H. Y. Nafaa, “Fingerprint Recognition System using Hybrid Matching Techniques”, 6th IEEE/ACIS International
Conference
on
Computer
and
Information Science, 2007, pp. 234-240. [9]. O. Zhengu, J. Feng, F. Su, A. Cai, “Fingerprint Matching
with
Rotation-Descriptor
Texture
Features”,
The 8th International Conference on
Pattern Recognition, 2006, pp. 417-420. [10]. A. K. Jain, S. Prabhkar, L. Hong and S. Pankanti, “Filterbank-Based Fingerprint Matching”,
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT
185
www.iaetsd.in