www.ijecs.

in
International Journal Of Engineering And Computer Science ISSN:2319-7242
Volume 3 Issue 1 January, 2014 Page No.3804-3812

Literature Survey On Fingerprint Recognition Using Level 3 Feature

Extraction Method
Chandra Prakash Singh1, Susheel Jain2, Anurag Jain3
1
M.Tech., RITS Bhopal/ RGPV Bhopal, India,
[email protected]
2
Asst.Prof. Department of CSE, RITS Bhopal/ RGPV Bhopal, India,
[email protected]
3
Prof. Department of CSE, RITS Bhopal/ RGPV Bhopal, India,
[email protected]

ABSTRACT : To design Level 3 fingerprint feature extraction method and match using SIFT algorithm. First of all
fingerprint of good quality are acquired by using optical scanner. Normalization of image is done using Gaussian blurring
and sliding window contrast adjustment. Pores are extracted and estimated. These estimated pores, are used to match from
template database to stored database using SIFT algorithm. Scale Invariant Features Transform (SIFT) is an algorithm in
computer vision to detect and describe local features in images. The features are invariant to image scaling and rotation. They
are well localized in both the spatial and frequency domains. The features are highly distinctive, which allows a single feature
to be correctly matched with high probability against a large database of features, providing a basis for object and scene
recognition.

Keywords - Fingerprint recognition, pores, SIFT recently employed for automated fingerprint recognition, in
technique, pores matching which the pores are usually extracted by using a
computationally expensive skeletonization method or a unitary
INTRODUCTION scale isotropic pore model. In this paper, however, author
Fingerprint recognition is a complex pattern recognition shows that real pores are not always isotropic. To accurately
problem. It is difficult to design accurate algorithms capable of and robustly extract pores, they propose an adaptive
extracting salient features and matching them in a robust way, anisotropic pore model, whose parameters are adjusted
especially in poor quality fingerprint images and when low-cost adaptively according to the fingerprint ridge direction and
acquisition devices with small area are adopted. There is a period. The fingerprint image is partitioned into blocks and a
popular misconception that automatic fingerprint recognition is a local pore model is determined for each block. With the local
fully solved problem since it was one of the first applications of pore model, a matched filter is used to extract the pores within
machine pattern recognition. On the contrary, fingerprint each block. Experiments on a high resolution (1200dpi)
recognition is still a challenging and important pattern fingerprint dataset are performed and the results demonstrate
recognition problem that the proposed pore model and pore extraction method can
locate pores more accurately and robustly in comparison with
LITERATURE SURVEY other state-of- the-art pore extractors.
This chapter presents the work done by other
researcher related to fingerprint verification system, pores 2.) Moheb R. et al. [7] proposed an approach to image
extraction and matching system. In this chapter description extraction and accurate skin detection from web pages. This
about all reference papers are summarized.
paper proposes a system to extract images from web pages and
1.) Qijun Zhao et al. [6] proposed an adaptive pore then detect the skin color regions of these images. As part of
model for fingerprint pore extraction. Sweat pores have been the proposed system, using BandObject control, they build a

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3805
 .

Tool bar named “Filter Tool Bar (FTB)” by modifying the minutia unification by decomposing a branch into three
Pavel Zolnikov implementation. In the proposed system, they terminations, and matching in the unified x-y coordinate
introduce three new methods for extracting images from the system after a two-step transformation are used in the work.
web pages (after loading the web page by using the proposed
4.) Hoi Le et al. [9] proposed online fingerprint identification
FTB, before loading the web page physically from the local
with a fast and distortion tolerant hashing method. National ID
host, and before loading the web page from any server). These
card, electronic commerce, and access to computer networks
methods overcome the drawback of the regular expressions
are some scenarios where reliable identification is a must.
method for extracting images suggested by Ilan Assayag. The
Existing authentication systems relying on knowledge-based
second part of the proposed system is concerned with the
approaches like passwords or token-based such as magnetic
detection of the skin color regions of the extracted images. So,
cards and passports contain serious security risks due to the
they studied two famous skin color detection techniques. The
vulnerability to engineering-social attacks and the easiness of
first technique is based on the RGB color space and the second
sharing or compromising passwords and PINs. Biometrics
technique is based on YUV and YIQ color spaces. They
such as fingerprint, face, eye retina, and voice offer a more
modified the second technique to overcome the failure of
reliable means for authentication. However, due to large
detecting complex image‟s background by using the saturation
biometric database and complicated biometric measures, it is
parameter to obtain an accurate skin detection results. The
difficult to design both an accurate and fast biometric
performance evaluation of the efficiency of the proposed
recognition. Particularly, fast fingerprint indexing is one of the
system in extracting images before and after loading the web
most challenging problems faced in fingerprint authentication
page from local host or any server in terms of the number of
system. In this paper, they present a specific contribution by
extracted images is presented. Finally, the results of comparing
introducing a new robust indexing scheme that is able not only
the two skin detection techniques in terms of the number of
to fasten the fingerprint recognition process but also improve
pixels detected are presented.
the accuracy of the system.
3.) Manvjeet Kaur et al. [8] proposed a fingerprint verification
5.) Ratha et al. [30] proposed an adaptive flow orientation
system using minutiae extraction technique. Most fingerprint
based segmentation or binarization algorithm. In this approach
recognition techniques are based on minutiae matching and
the orientation field is computed to obtain the ridge directions
have been well studied. However, this technology still suffers
at each point in the image. To segment the ridges, a 16x16
from problems associated with the handling of poor quality
window oriented along the ridge direction is considered
impressions. One problem besetting fingerprint matching is
around each pixel. The projection sum along the ridge
distortion. Distortion changes both geometric position and
direction is computed. The centers of the ridges appear as peak
orientation, and leads to difficulties in establishing a match
points in the projection. The ridge skeleton thus obtained is
among multiple impressions acquired from the same finger tip.
smoothened by morphological operation. Finally minutiae are
Marking all the minutiae accurately as well as rejecting false
detected by locating end points and bifurcations in the thinned
minutiae is another issue still under research. Our work has
binary image.
combined many methods to build a minutia extractor and a
minutia matcher. The combination of multiple methods comes 6.) Anil Jain et al. [10] proposed a Pores and Ridges:
from a wide investigation into research papers. Also some novel Fingerprint Matching Using Level 3 Features. Fingerprint
changes like segmentation using morphological operations, friction ridge details are generally described in a hierarchical
improved thinning, false minutiae removal methods, minutia order at three levels, namely, Level 1 (pattern), Level 2
marking with special considering the triple branch counting,

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3806
 .

(minutiae points) and Level 3 (pores and ridge shape). Although 8.) Umut Uludaga et al. [14] proposed a Biometric template
high resolution sensors (∼1000dpi) have become commercially selection and update: a case study in fingerprints. Sweat pores
available and have made it possible to reliably extract Level 3 have been recently employed for automated fingerprint
features, most Automated Fingerprint Identification Systems recognition, in which the pores are usually extracted by using
(AFIS) employ only Level 1 and Level 2 features. As a result, a computationally expensive skeletonization method or a
increasing the scan resolution does not provide any matching unitary scale isotropic pore model. In this paper, however, real
performance improvement [17]. They develop a matcher that pores are not always isotropic. To accurately and robustly
utilizes Level 3 features, including pores and ridge contours, for extract pores, they propose an adaptive anisotropic pore
1000dpi fingerprint matching. Level 3 features are model, whose parameters are adjusted adaptively according to
automatically extracted using wavelet transform and Gabor the fingerprint ridge direction and period. The fingerprint
filters and are locally matched using the ICP algorithm. Our image is partitioned into blocks and a local pore model is
experiments on a median-sized database show that Level 3 determined for each block. With the local pore model, a
features carry significant discriminatory information. EER matched filter is used to extract the pores within each block.
values are reduced (relatively ∼20%) when Level 3 features are Experiments on a high resolution (1200dpi) fingerprint dataset
employed in combination with Level 1 and 2 features. are performed and the results demonstrate that the proposed
pore model and pore extraction method can locate pores more
7.) Mayank Vatsa et al. [11] proposed an combining pores and
accurately and robustly in comparison with other state-of-the-
ridges with minutiae for improved fingerprint verification. This
art pore extractors.
paper presents a fast fingerprint verification algorithm using
level-2 minutiae and level-3 pore and ridge features. The 9.) Coetzee and Botha [31] proposed a binarization technique
proposed algorithm uses a two-stage process to register based on the use of edges extracted using Marr-Hilderith
fingerprint images. In the first stage, Taylor series based image operator. The resulting edge image is used in conjunction with
transformation is used to perform coarse registration, while in the original gray scale image to obtain the binarized image.
the second stage, thin plate spline transformation is used for fine This is based on the recursive approach of line following and
registration. A fast feature extraction algorithm is proposed line thinning. Two adaptive windows, the edge window and
using the Mumford–Shah functional curve evolution to the gray-scale window are used in each step of the recursive
efficiently segment contours and extracts the intricate level-3 process. To begin with, the pixel with the lowest gray-scale
pore and ridge features. Further, Delaunay triangulation based value is chosen and a window is centered on it. The boundary
fusion algorithm is proposed to combine level-2 and level-3 of the window is then examined to determine the next position
information that provides structural stability and robustness to of the window. The window is successively position to trace
small changes caused due to extraneous noise or non-linear the ridge boundary and the recursive process terminates when
deformation during image capture. They defines eight all the ridge pixels have been followed to their respective ends.
quantitative measures using level-2 and level-3 topological
10.) Ruud M. Bolle et al. [33] proposed the evaluation
characteristics to form a feature super vector. A 2n-support
techniques for biometrics-based authentication systems (FRR).
vector machine performs the final classification of genuine or
Biometrics-based authentication is becoming popular because
impostor cases using the feature super vectors. Experimental
of increasing ease-of-use and reliability. Performance
results and statistical evaluation show that the feature super
evaluation of such systems is an important issue. They
vector yields discriminatory information and higher accuracy
endeavor to address two aspects of performance evaluation
compared to existing recognition and fusion algorithms.
that have been conventionally neglected. First, the “difficulty”

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3807
 .

of the data that is used in a study influences the evaluation thresholds to detect the strong edge and the weak edge, and the
results. They propose some measures to characterize the data weak edge will be include in the output image only when the
set so that the performance of a given system on different data weak edge is connected to the strong edge. The Sobel Operator
sets can be compared. Second, conventional studies often have has a good performance on the images with gray gradient and
reported the false reject and false accept rates in the form of high noise, but the location of edges is not very accurate, the
match score distributions. However, no confidence intervals are edges of the image have more than one pixel. The Binary
computed for these distributions, hence no indication of the Image Edge Detection Algorithm is simple, but it can detect
significance of the estimates is given. In this paper, they the edge of the image accurately, and the processed images are
compare the parametric and nonparametric (bootstrap) methods not need to be thinned, it particularly adapts to process various
for measuring confidence intervals. They give special attention binary images with no noise. So each algorithm has its
to false reject rate estimates. advantages and disadvantages, and the suitable algorithm
should be selected according to the characters of the images
11.) Wang Yuan et al. [36] proposed a real time fingerprint
been detected, then it can performance perfectly.
recognition system based on novel fingerprint matching
strategy. In this paper they present a real time fingerprint 13.) Shunshan li et al. [38] proposed the Image Enhancement
recognition system based on a novel fingerprint minutiae Method for Fingerprint Recognition System. In this paper
matching algorithm. The system is developed to be applicable fingerprint image enhancement method, a refined Gabor filter,
to today's embedded systems for fingerprint authentication, in is presented. This enhancement method can connect the ridge
which small area sensors are employed. The system is breaks, ensures the maximal gray values located at the ridge
comprised of fingerprint enhancement and quality control, center and has the ability to compensate for the nonlinear
fingerprint feature extraction, fingerprint matching using a deformations. it includes ridge orientation estimation, a Gabor
novel matching algorithm, and connection with other filter processing and a refined Gabor filter processing. The
identification system. Here they describe their way to design a first Gabor filter reduces the noise, provides more accurate
more reliable and fast fingerprint recognition system which is distance between the two ridges for the next filter and gets a
based on today's embedded systems in which small area rough ridge orientation map while the refined Gabor filter with
fingerprint sensors are used. Experiment on FVC database show the adjustment parameters significantly enhances the ridge,
our system has a better performance than compared. And for the connects the ridge breaks and ensures the maximal gray values
image enhancement and matching techniques they use high of the image being located at the ridge center. In addition, the
efficiency, it can also give a real time identification result with algorithm has the ability to compensate for the nonlinear
high reliability. deformations. Furthermore, this method does not result in any
spurious ridge structure, which avoids undesired side effects
12.) Wei Cui et al. [37] proposed the research of edge detection
for the subsequent processing and provides a reliable
algorithm for fingerprint images. This paper introduces some
fingerprint image processing for Fingerprint Recognition
edge detection operators and compares their characteristics and
System. In a word, a refined Gabor filter is applied in
performances. At last the experiment show that each algorithm
fingerprint image processing, then a good quality fingerprint
has its advantages and disadvantages, and the suitable algorithm
image is achieved, and the performance of Fingerprint
should be selected according the characteristic of the images
Recognition System has been improved.
detected, so that it can perform perfectly. The Canny Operator
is not susceptible to the noise interference; it can detect the real 14.) S. Mil'shtein et al. [39] proposed a fingerprint recognition
weak edge. The advantage is that it uses two different algorithm for partial and full fingerprints. In this study, they

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3808
 .

propose two new algorithms. The first algorithm, called the the field of biometrics as it provides better results. In this
Spaced Frequency Transformation Algorithm (SFTA), is based paper, they propose normalized cross-correlation technique for
on taking the Fast Fourier Transform of the images. The second fingerprint matching to minimize error rate as well as reduce
algorithm, called the Line Scan Algorithm (LSA), was the computational effort than the minutiae matching method.
developed to compare partial fingerprints and reduce the time The EER (Equal Error Rate) obtained from result till now with
taken to compare full fingerprints. A combination of SFTA and minutiae matching method is 3%, while that obtained for the
LSA provides a very efficient recognition technique. The most method proposed in this paper is approx 2% for all types of
notable advantages of these algorithms are the high accuracy in fingerprints in combined form.
the case of partial fingerprints. At this time, the major drawback
17.) Asker M. Bazen et al. [42] proposed a correlation-based
of developed algorithms is lack of pre-classification of
fingerprint verification system. In this paper, a correlation-
examined fingers. Thus, they use minutiae classification scheme
based fingerprint verification system is presented. Unlike the
to reduce the reference base for given tested finger. When the
traditional minutiae-based systems, this system directly uses
reference base had shrunk, they apply the LSA and SFTA.
the richer gray-scale information of the fingerprints. The
15.) Another paper proposed a novel approaches for minutiae correlation-based fingerprint verification system first selects
filtering in fingerprint images. Existing structural approaches appropriate templates in the primary fingerprint, uses template
for minutiae filtering use heuristics and adhoc rules to eliminate matching to locate them in the secondary print, and compares
such false positives, where as gray level approach is based on the template positions of both fingerprints. Unlike minutiae-
using raw pixel values and a super-vised classifier such as based systems, the correlation-based fingerprint verification
neural networks. They proposed two new techniques for system is capable of dealing with bad-quality images from
minutiae verification based on non-trivial gray level features. which no minutiae can be extracted reliably and with
The proposed features intuitively represent the structural fingerprints that suffer from non-uniform shape distortions.
properties of the minutiae neighborhood leading to better Experiments have shown that the performance of this system
classification. They use directionally selective steerable wedge at the moment is comparable to the performance of many other
filters to differentiate between minutiae and non-minutiae fingerprint verification systems.
neighborhoods with reasonable accuracy. They also propose a
18.) David G. Lowe [43] proposed an approach to distinctive
second technique based on Gabor expansions that result in even
image features from scale-invariant keypoints. This paper
better discrimination. They present an objective evaluation of
presents a method for extracting distinctive invariant features
both the algorithms. Apart from minutiae verification, the
from images that can be used to perform reliable matching
feature description can also be used for minutiae detection and
between different views of an object or scene. The features are
minutiae quality assessment.
invariant to image scale and rotation, and are shown to provide
16.) Deepak Kumar Karna et al. [41] proposed normalized robust matching across a substantial range of affine distortion,
cross-correlation based fingerprint matching. To perform change in 3D viewpoint, addition of noise, and change in
fingerprint matching based on the number of corresponding illumination. The features are highly distinctive, in the sense
minutia pairings, has been in use for quite some time. But this that a single feature can be correctly matched with high
technique is not very efficient for recognizing the low quality probability against a large database of features from many
fingerprints. To overcome this problem, some researchers images. This paper also describes an approach to using these
suggest the correlation technique which provides better result. features for object recognition. The recognition proceeds by
Use of correlation-based methods is increasing day-by-day in matching individual features to a database of features from

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3809
 .

known objects using a fast nearest-neighbor algorithm,

followed by a Hough transformation to identify clusters REFERENCES
1. Schneier, Bruce. Applied Cryptography. New York: John
belonging to a single object, and finally performing verification
Wiley & Sons, 1996.
through least-squares solution for consistent pores parameters. 2. M. Ray, P. Meenen, and R. Adhami, “A novel approach to
This approach to recognition can robustly identify objects fingerprint pore, extraction.” Southeastern Symposium
among clutter and occlusion while achieving near real-time on System Theory, page no. 282–286, 2005.
3. McGraw, Gary and Greg Morrisett., “Attacking Malicious
performance.
Code: A Report to the Infosec Research Council.” IEEE
Software. September/October 2000.
I. CONCLUSION
This chapter presents the work done by other researcher 4. The Implementation of Electronic Voting in the UK
research summary. 2002.
related to fingerprint verification system, pores extraction and “http://www.dca.gov.uk/elections/e-voting/pdf/e-
matching system. In this chapter description about all reference summary.pdf.” 21.01.2007.
papers are summarized. This paper presents a brief survey of 5. D. Maio, D. Maltoni, R. Cappelli, J.L. Wayman, and A.K.
Jain. FVC2000: Fingerprint Verification Competition.
fingerprint level 3 features extraction and matching approach
IEEE Transactions on Pattern Analysis and Machine
which is a novel approach, its characteristics, design issues and Intelligence, 24(3):402–412, 2002.
applications. It also describes an overview of Level 1 and level 6. Qijun Zhao, Lei Zhang, David Zhang, Nan Luo,
2 features, in the literature and their functionalities. Along with “Adaptive Pore Model for Fingerprint Pore Extraction.”
Proc. IEEE, 978-1-4244-2175-6/08, 2008.
that, it has through discussion of SIFT algorithm. Finally, it
7. Moheb R. Girgis, Tarek M. Mahmoud, and Tarek Abd-El-
presents an novel approach for level 3 feature extraction and Hafeez, “An Approach to Image Extraction and Accurate
matching algorithm. Since the technology is going to its zenith, Skin Detection from Web Pages.” World academy of
the way of its journey is not smooth and many loopholes are Science, Engineering and Technology, page no. 27, 2007.

there.
8. Manvjeet Kaur, Mukhwinder Singh, Akshay Girdhar, and
Parvinder S. Sandhu, “Fingerprint Verification System
The proposed work is an attempt to overcome some weakness using Minutiae Extraction Technique.” World academy of
regarding security concern of the system. The experimental Science, Engineering and Technology, page no. 46, 2008.
results demonstrate that the proposed approach and its 9. Hoi Le, The Duy Bui, “Online fingerprint identification
with a fast and distortion tolerant hashing.” Journal of
associated pore extraction method can detect pores more
Information Assurance and Security 4 page no. 117-123,
accurately and robustly, and can help to improve the 2009.
verification accuracy of pore based fingerprint recognition 10. Anil Jain, Yi Chen, and Meltem Demirkus, “Pores and
systems. There are many method exists to make it unextractable Ridges: Fingerprint Matching Using Level 3 Features.”
Pattern recognition letters, page no. 2221-2224, 2004.
by adversaries, like one is to use multi-biometric traits under a
11. Mayank Vatsa, Richa Singh, Afzel Noore, Sanjay K.
single process, but it need extra sensors setup for each kind of Singh, “Combining pores and ridges with minutiae for
traits, the proposed technique gives an extra edge to such improved fingerprint verification.” Elsevier, Signal
systems which use single type of sensor and give more Processing 89, page no. 2676–2685, 2009.
12. Qijun Zhao, Lei Zhang, David Zhang, Nan Luo,
security.
“Adaptive Pore Model for Fingerprint Pore Extraction.”
This approach will give the technology new amplitude in IEEE, 978-1-4244-2175, 2008.
order to provide a secure way of authentication, in which the
13. A.K. Jain, R. Bolle, S. Pankanti (Eds.), “Biometrics:
pores are logically extracted. The proposed algorithm performs
Personal Identification in Networked Society”, Kluwer
better than existing recognition algorithms and fusion
algorithms. Along with other advantages, in all biometric Academic Publishers, Dordrecht, 1999.
systems fingerprint based systems are more efficient than other 14. Umut Uludaga, Arun Rossb, Anil Jain, “Biometric
multimodal system, so it minimizes FAR and FRR. template selection and update: a case study in

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3810
 .

fingerprints.” U. Uludag et al. / Pattern Recognition Fingerprint Recognition.” in Proc. IEEE 1991
„Elsavier‟, 37 page no. 1533 – 1542, 2004. International Symposium on CAS, Singapore, page no.
15. Anil K. Jain and David Maltoni., “Handbook of Fingerprint 2625-2628, 1991.
Recognition.” Springer Verlag New York, Inc., Secaucus, 30. N. K. Ratha, K. Karu, S. Chen, and A. K. Jain, “A real-
NJ, USA, 2003. time matching system for large fingerprint databases.”
16. K. Kryszczuk, P. Morier, and A. Dryga jlo., “Study of the Transactions on Pattern Analysis and Machine
Distinctiveness of Level 2 and Level 3 Features in Intelligence, 18(8): page no. 799–813, 1996.
Fragmentary Fingerprint Comparison.” In Proc. Of 31. L. Coetzee and E. C. Botha, “Fingerprint recognition in
Biometric Authentication Workshop, page no. 124–133, low quality images.” Pattern Recognition, 26(10), 1993.
May 2004. 32. D. Marr and E. C. Hilderith, “Theory of edge detection.”
17. K. Kryszczuk, A. Drygajlo, and P. Morier, “Extraction of Proceedings of the Royal Society, pages 187–217, 2004.
Level 2 and Level 3 features for fragmentary fingerprints.” 33. L. O‟Gormann and J.V.Nickerson, “An approach to
Proc. of the 2nd COST275 Workshop, Vigo, Spain, page fingerprint filter design.” Pattern Recognition, 22(1): page
no. 83-88, 2004. no. 29–38, 1989.
18. D. Maio, D. Maltoni, A. K. Jain, and S. Prabhakar., 34. Greenberg S., Aladjem M., Kogan D., and Dimitrov I.
“Handbook of Fingerprint Recognition.” Springer Verlag, “Fingerprint image enhancement using filtering
2003. techniques.” In International Conference on Pattern
19. http://www.itl.nist.gov/iad/894.03/fing/summary.html, Recognition, volume 3, page no 326–329, 2000.
NIST Fingerprint Data Exchange Workshop, 1998. 35. Ruud M. Bolle, Sharath Pankanti and Nalini K. Ratha,
20. S. Pankanti, S. Prabhakar, and A. K. Jain, “On the “Evaluation techniques for biometrics-based
Individuality of Fingerprints.” IEEE Trans. PAMI, Vol. 24, authentication systems (FRR).” IBM Thomas J. Watson
page no. 1010-1025, 2002. Research Center.
21. J.D. Stosz and L.A. Alyea, “Automated system for 36. Wang Yuan, Yao Lixiu, Zhou Fuqiang, “A real time
fingerprint authentication using pores and ridge structure.” fingerprint recognition system based on novel fingerprint
Proc. of the SPIE Automatic Systems for the Identification matching strategy.” The eighth international conference
and Inspection of Humans, Volume 2277, page no. 210- on electronic measurement and instruments, ICEMI 2007.
223, 1994. 37. Wei Cui, Guoliang Wu, Rongjin Hua, and Hao Yang,
22. P.J. Besl and N.D. McKay, “A method for registration of 3- “The Research of Edge Detection Algorithm for
D shapes.” IEEE Trans. PAMI, Vol. 14, page no. 239-256, Fingerprint Images.” IEEE‟ 2008.
1992. 38. Shunshan li, Min Wei, Haiying Tang, Tiange Zhuang and
23. A. Tsai, A. Yezzi Jr., A. Willsky, “Curve evolution Michael H. Buonocore, “Image Enhancement Method for
implementation of the Mumford–Shah functional for image Fingerprint Recognition System.”, Proceedings of the
segmentation, de-noising, interpolation, and 2005 IEEE, Engineering in Medicine and Biology 27th
magnification.” IEEE Transactions on Image Processing 10 Annual Conference, Shanghai, China, September 1-4,
(8) page no. 1169–1186, 2001. page no. 3386-3389, 2005.
24. T. Chan, L. Vese, “Active contours without edges.” IEEE 39. S. Mil'shtein, A. Pillai, A. Shendye, C. Liessner, and M.
Transactions on Image Processing, 10 (2) page no. 266– Baier, “Fingerprint Recognition Algorithms for Partial
277, 2001. and Full Fingerprints.” IEEE 2008.
25. A.R. Roddy and J.D. Stosz, “Fingerprint features–statistical 40. Arun Ross, Umut Uludag, Anil Jain, “Biometric template
analysis and system performance estimates” Proc. IEEE, selection and update: a case study in Fingerprints.”
vol. 85, no. 9, page no. 1390-1421, 1997. Pattern Recognition Society. Published by Elsevier Ltd.,
26. http://www.fmrib.ox.ac.uk/~steve/susan/thinning/node2.ht 2003.
ml 41. Deepak Kumar Karna, Suneeta Agarwal, Shankar Nikam,
27. Q. Zhang and K. Huang, “Fingerprint classification based “Normalized Cross-correlation based Fingerprint
on extraction and analysis of singularities and pseudo Matching.” Fifth International Conference on Computer
ridges.” 2002. Graphics, Imaging and Visualization, IEEE 2008.
28. http://www.owlnet.rice.edu/~elec301/Projects00/roshankg/ 42. Asker M. Bazen, Gerben T.B. Verwaaijen, Sabih H.
elec301.htm Gerez, “A Correlation-Based Fingerprint Verification
29. A. Luk, S.H. Leung, “A Two Level Classifier For System.” Workshop on Circuits, Systems and Signal

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3811
 .

Processing, Veldhoven, The Netherlands, November 2000.

43. David G. Lowe, “Distinctive Image Features from Scale-
Invariant Key points.” International Journal of Computer
Vision, 2004.
44. Working draft of CDEFFS: the ANSI/NIST committee to
define an extended fingerprint feature set, 2008. Available
at “http://fingerprint.nist.gov/standard/cdeffs/index.html”.
45. Lin Zhang, Lei Zhang, David Zhang, Hailong Zhu, “Online
finger-knuckle-print verification for personal
authentication.” Pattern recognition, Elsevier, 2010.
46. verification.” IEEE Transactions on Pattern Analysis and
Machine Intelligence, page no. 302–314, 1997.
47. FVC2002. http://bias.csr.unibo.it/fvc2002/.
48. P. Mell and T. Grance, “Draft nist working definition of
cloud computing,” Referenced on June. 3rd, 2009 Online
at http://csrc.nist.gov/ groups/SNS/cloud-
computing/index.html, 2009.

BOOKS
1 Schneier, Bruce. Applied Cryptography. New York:
John Wiley & Sons, 1996.
2 M. Ray, P. Meenen, and R. Adhami, “A novel approach to
fingerprint pore, extraction.” Southeastern Symposium on
System Theory, page no. 282–286, 2005.
3 McGraw, Gary and Greg Morrisett., “Attacking Malicious
Code: A Report to the Infosec Research Council.” IEEE
Software. September/October 2000.

ABOUT AUTHERS

Chandra Prakash Singh, is a scholar of M.Tech, (Computer

Science Engineering), at R.I.T.S. Bhopal, under R.G.P.V.
Bhopal, M.P.,India.

Susheel Jain, Assistant Professor in Computer science

department of R.I.T.S., Bhopal, M.P. He has done his M.Tech.
in Software Engineering From Gautam Buddh Technical
University, Lucknow, India.

Anurag Jain, H.O.D. of Computer science department of

R.I.T.S. Bhopal, M.P. He has done his M.Tech, in Computer
Science and Engineering, From Barkatullah University, Bhopal,
India

Chandra Prakash Singh1IJECS Volume 3 Issue 1 January, 2014 Page No.3805-3812 Page 3812