Académique Documents
Professionnel Documents
Culture Documents
\
|
|
|
.
xi x ( )
yi y ( )
u i u ( )
(
(
(
=TM *
(5)
where (x,y,u) is the parameters of the reference minutia, and TM is (6) :
TM =
cos u
sin u
0
sin u
cos u
0
0
0
1
|
\
|
|
|
.
(6)
The new coordinate system is originated at minutia F and the new x-axis is coincident with the direction of minutia F.
No scaling effect is taken into account by assuming two fingerprints from the same finger have nearly the same size.
Lins method uses the rotation angle calculated from all the sparsely sampled ridge points. This method use the rotation
angle calculated earlier by densely tracing a short ridge start from the minutia with length D. Since we already got the
minutia direction at the minutia extraction stage, obviously this method diminishes the redundant calculation but still
holds the accuracy. A transformation is carried out to directly line up one fingerprint image to another according to the
discrepancy of the reference minutia pair. It still requires a transform to the polar coordinate system for each image at
the next minutia match stage. This approach is to transform each according to its own reference minutia and then do
match in a unified x-y coordinate. As a result, less computation workload is achieved through this method.
5.2 Match Stage
The matching algorithm for the aligned minutia patterns needs to be elastic since the strict match requiring that all
parameters (x, y,u) are the similar for two identical minutia tend to be impossible due to the slight deformations and
inexact quantization of minutia. Our approach to elastically match minutia is achieved by placing a bounding box
around each template minutia. If the minutia to be matched is within the rectangle box and the direction discrepancy
between them is very small, then the two minutia are considered as a matched minutia pair. Each minutia in the
template image either has no matched minutia or has only one corresponding minutia. The final match ratio for two
fingerprints is the number of total matched pair over the number of minutia of the template fingerprint. The score is
I nt ernat i onal Journal of Appl i cat i on or I nnovat i on i n E ngi neeri ng & M anagement (I JAI E M )
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 1, Issue 4, December 2012 ISSN 2319 - 4847
Volume 1, Issue 4, December 2012 Page 46
100*ratio and ranges from 0 to 100. If the score is larger than a pre-specified threshold, the two fingerprints are from
the same finger. However, the elastic match algorithm has large computation complexity and is vulnerable to spurious
minutia.
6. EXPERIMENTATION AND RESULTS
A fingerprint database from the FVC2000 (Fingerprint Verification Competition 2000) is used to check the experiment
performance. The program tests all the images without any fine tuning for the database. The experiments show the
program can differentiate imposturous minutia pairs from genuine minutia pairs in a certain assurance level.
Furthermore, good experiment designs can surely get better the accuracy as declared [10]. Further studies on good
designs of training and testing are expected to improve the result. Here is the diagram for Correct Score and Incorrect
Score distribution as shown in figure 9.
Figure 9 Distribution of Correct Scores and Incorrect Scores Red line: Incorrect Score Green line: Correct Scores
It can be seen from the above figure that their exist two partially overlapped distributions. The Red curve whose peaks
are mainly located at the left part means the average incorrect match score is 25. The green curve whose peaks are
mainly located on the right side of red curve means the average correct match score is 35. This indicates the algorithm
is capable of differentiate fingerprints at a good correct rate by setting an appropriate threshold value
Figure 10 FRR curve Blue dot line: FRR curve Red dot line: FAR curve
The above diagram shows the FRR (false rejection ratio) and FAR (false acceptance ratio) curves. At the equal error
rate 25%, the separating score 33 will falsely reject 25% genuine minutia pairs and falsely accept 25% imposturous
minutia pairs and has 75% verification rate. The elevated incorrect acceptance and false rejection are due to some
fingerprint images with bad quality and the vulnerable minutia match algorithm.
7. CONCLUSION
This paper has used many methods to build a minutia extractor and a minutia matcher. The grouping of numerous
methods comes from a wide investigation into this paper. Some novel changes like segmentation using Morphological
operations, minutia marking with particular considering the triple branch counting, minutia unification by
decomposing a branch into three terminations, and matching in the unified x-y coordinate system after a two-step
transformation are used in this paper, which are not accounted in other literatures. The program coding with MATLAB
going through all the stages of the fingerprint recognition is put together. It is supportive to understand the procedures
of fingerprint recognition and demonstrate the key issues of fingerprint recognition.
I nt ernat i onal Journal of Appl i cat i on or I nnovat i on i n E ngi neeri ng & M anagement (I JAI E M )
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 1, Issue 4, December 2012 ISSN 2319 - 4847
Volume 1, Issue 4, December 2012 Page 47
REFERENCES
[1] A. Bonnaccorsi, On the Relationship between Firm Size and Export Intensity, Journal of International
Business Studies, XXIII (4), pp. 605-635, 1992. (journal style)
[2] R. Caves, Multinational Enterprise and Economic Analysis, Cambridge University Press, Cambridge, 1982.
(book style)
[3] M. Clerc, The Swarm and the Queen: Towards a Deterministic and Adaptive Particle Swarm Optimization, In
Proceedings of the IEEE Congress on Evolutionary Computation (CEC), pp. 1951-1957, 1999. (conference style)
[4] H.H. Crokell, Specialization and International Competitiveness, in Managing the Multinational Subsidiary, H.
Etemad and L. S, Sulude (eds.), Croom-Helm, London, 1986. (book chapter style)
[5] K. Deb, S. Agrawal, A. Pratab, T. Meyarivan, A Fast Elitist Non-dominated Sorting Genetic Algorithms for
Multiobjective Optimization: NSGA II, KanGAL report 200001, Indian Institute of Technology, Kanpur, India,
2000. (technical report style)
[6] J. Geralds, "Sega Ends Production of Dreamcast," vnunet.com, para. 2, Jan. 31, 2001. [Online]. Available:
http://nl1.vnunet.com/news/1116995. [Accessed: Sept. 12, 2004]. (General Internet site)
AUTHOR
G. Srinivas Reddy received his M.Tech(CSE). with distinction from Jawaharlal Nehru Technological
University, Hyderabad, A.P., India., and is now persuing his PhD. He has been in the academic fiel for
about 10 years with good number of research publications in various domains of computing sciences.
He is presently Assistant Professor at Mahatma Gandhi Institute of Technology, Hyderabad, A.P,
INDIA. His major research area include Computational Physics, Digital Image Processing, Evolutionary
AlgorithmsComputer networks and Security.
Professor T.Venkat Narayana Rao, received B.E in Computer Technology and Engineering from
Nagpur University, Nagpur, India, M.B.A (Systems), holds a M.Tech in Computer Science from
Jawaharlal Nehru Technological University, Hyderabad, A.P., India and a Research Scholar in JNTU. He
has 21 years of vast experience in Computer Science and Engineering areas pertaining to academics and
industry related I.T issues. He is presently Professor, Department of Computer Science and Engineering,
Guru Nanak Institutions Technical Campus, Ibrahimpatnam, R.R.Dist., A.P, INDIA. He is nominated as Editor and
Reviewer to 27 International journals relating to Computer Science and Information Technology. He is currently
working on research areas that include Digital Image Processing, Digital Watermarking, Data Mining, Network
Security and other Emerging areas of Information Technology. He can be reached at tvnrbobby@yahoo.com.
Dr K Venkateswara Reddy is a principal of MLRITM, Hyderabad, received his M.Tech and PhD from
JNTU and Osmania University. He checquered a dynamic career in reputed engineering colleges as a
professor, Head and Vice-principal and is found to be disciplinary and dynamic personality in academic
and administrative spheres. He bagged several national and international journals to his credit in 20 years
length of his service. He is life member of ISTE. Presently he is working in Cloud Computing, Network Security,
MANET and other emerging fields of computer science.