See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/310953762

Overview of Fingerprint Recognition System

Conference Paper · March 2016

DOI: 10.1109/ICEEOT.2016.7754902

CITATIONS READS

73 30,685

4 authors:

Mouad M.H. Ali Vivek Hilal Mahale

Hodeidah university Dr. Babasaheb Ambedkar Marathwada University
26 PUBLICATIONS   298 CITATIONS    13 PUBLICATIONS   205 CITATIONS   

SEE PROFILE SEE PROFILE

Pravin Yannawar Ashok Gaikwad

Dr. Babasaheb Ambedkar Marathwada University Institute of Management Studies and Information Technology, Aurangabad, (M.S) …
74 PUBLICATIONS   861 CITATIONS    42 PUBLICATIONS   420 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Analysis of Visual Speech using Multiple Camera Angle for Audio Visual Speech Recognition View project

Modi Charactor Recognition View project

All content following this page was uploaded by Mouad M.H. Ali on 11 October 2017.

The user has requested enhancement of the downloaded file.

 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) - 2016

Overview of Fingerprint Recognition System

Mouad .M.H.Ali Vivek H. Mahale Pravin Yannawar A. T. Gaikwad
Research Scholar at Dr. Research Scholar at Dr. Department of CSIT Dr. Institute of Management
Babasaheb Ambedkar Babasaheb Ambedkar Babasaheb Ambedkar Studies and Information
Marathwada University Marathwada University Marathwada University Technology, Aurangabad,
Aurangabad, (M.S), India Aurangabad, (M.S), India Aurangabad, (M.S), India (M.S), India
[email protected] [email protected] [email protected] [email protected]

Abstract— This article is an overview of a current research based characteristics are based on an action taken by a person such
on fingerprint recognition system. In this paper we highlighted as (Voice recognition, keystroke-scan, and signature-scan).
on the previous studies of fingerprint recognition system. This Any biometrics system including two phases first phase is
paper is a brief review in the conceptual and structure of enrollment phase and second is recognition phase. The
fingerprint recognition. The basic fingerprint recognition system
consists of four stages: firstly, the sensor which is used for
recognition phase divided to two things which is verification
enrolment & recognition to capture the biometric data. Secondly, and identification. During the enrollment phase the biometrics
the pre-processing stage which is used to remove unwanted data data are captured and generate digital image then Pre-
and increase the clarity of ridge structure by using enhancement processing apply to digital image for removing unwanted data
technique. Thirdly, feature extraction stage which take the input and apply the post-processing than store this data in database.
from the output of the pre-processing stage to extract the In the case of identification process the fingerprint acquired
fingerprint features. Fourthly, the matching stage is to compare from one person is compared with all the fingerprints which
the acquired feature with the template in the database. Finally, store in database. Also it is known as (1:N) matching. it is used
the database which stores the features for the matching stags. in the process of seeking the criminals.
The aim of this paper is to review various recently work on
fingerprint recognition system and explain fingerprint
In the verification process the person’s fingerprint is
recognition stages step by step and give summaries of fingerprint verified from the database by using matching algorithms. Also
databases with characteristics. it is known as (1:1) Matching. It is the comparison of a
claimant fingerprint against enroll fingerprint, initially the
Keywords: - Fingerprint, Pre-processing, Feature extraction, person enrolls his/her fingerprint into verification system, and
Matching, Databases . the result show whether the fingerprint which take from the
user is matching with the fingerprint store as a template in
I. INTRODUCTION database or not match.
The Enrollment, Identification and Verification process shown
Along of various biometrics techniques, In the past few in the Fig. 1
decades, human-beings have been addicted to various
technologies such as captured photos, scanned signatures, bar
code systems, verification Id & so on. Also, Biometrics is one
of the applications in Image processing which refers to
technologies that used physiological or behavioral
characteristics of human body for the user authentication. The
biometric authentication system based on two modes:
Enrolment and Recognition. In the enrolment mode, the
biometric data is acquired from the sensor and stored in a
database along with the person’s identity for the recognition.
In the recognition mode, the biometric data is re-acquired
from the sensor and compared to the stored data to determine
the user identity.
Biometric recognition based on uniqueness and
permanence. The uniqueness means that there is no similarity
of feature between two different biometrics data. For example,
there are no two humans having the same fingerprint feature
even if they are twins. And when the features of biometrics do Fig.1.Process of Enrollment, identification and verification
not change over the lifetime or aging, it is called permanence. The fingertip surface is a combination of many of ridges and
Biometrics can have physiological or behavioral many of valleys. In case of the ridge which declare as black
characteristics. The physiological characteristics are included lines and the valleys declare as white lines are show in Fig.2.
in the physical part of body such as (fingerprint, palm print, The minutiae points are the points where the ridge structure
iris, face, DNA, hand geometry, retina... etc). The behavioral changes such as bifurcation and end point.

978-1-4673-9939-5/16/$31.00 ©2016 IEEE

 A. Image Capture or Image Acquisition stage

The Image Acquisition stage is the process to obtain

images by different ways. There are two ways to capture
fingerprint image; online and offline. In the online fingerprint
Fig.2. Graphical of ridge and valleys Ridge Ending, Bifurcation and short
Ridge [14] identification the optical fingerprint reader is used to capture
the image of fingerprint. The size of fingerprint image will be
260*300 pixels. The offline fingerprint identification is
II. FINGERPRINT obtained by ink in the area of finger and then put a sheet of
Fingerprints are graphical patterns of ridges and valleys on the white paper on the fingerprint and finally scans the paper to
surface of fingertips, the ridge ending and ridge bifurcation is get a digital image.
called minutiae as shown in fig.3. There are many methods
based on minutiae-based fingerprint representation were B. Image Pre-processing Stage
proposed in [1], [2]. Every person has a unique fingerprint
from any other person. The fingerprint identification is based The pre-processing stage is the process of removing
on two basic assumptions: - Invariance and Singularity unwanted data in the fingerprint image such as noise,
Invariance: means the fingerprint characteristics do not change reflection .etc. The fingerprint image pre-processing is used to
along the life. increase the clarity of ridge structure. There are many steps for
doing this process shown in fig.5,such as Image Segmentation,
Singularity: means the fingerprint is unique and no two
Binarization, Elimination of noise, smoothing and thinning
persons have the same pattern of fingerprint.
which are used to enhance the fingerprint image. In [3], the
Gaussian filter, Short Time Fourier Transform analysis are
adopted to enhance fingerprint image quality. In some cases
the binarized of fingerprint image are contains a some of false
minutiae .In [4]. A detailed pre-processing is mentioned to
remove false minutiae. In fig 6 shows the preprocessing steps.
Input image

Fig.3. different ridge features on Fingerprint image

Normalization
Table I. shows the terms and definitions of fingerprint structure
No Term Definition
1 Termination The location where a ridge comes to an end.
2 Bifurcation The location where a ridge divides into two Orientation Image
separate ridges.
3 Binarization a process to transform the image from 256 levels
to two levels(0,1)refers to (black and white)
respectively Region Mask Generation
4 Thinning The process of reducing the width of each ridge
to one pixel .
5 Termination Concidered as angle between the direction of the
Frequency Image Estimation
Angle ridge and the horizontal .
6 Bifurcation Which Concidered as the angle between the
Angle direction of the valley ending between the
bifurcations and the horizontal. Filtering (Gabor Filter)
7 Matching Score It is the mesure of similarity between the input
and template data
8 False Non The system fail to detect a match between input Enhancement
Matching Ratio and template in database .
Fig.5. main steps of fingerprint Enhancement
The main stages of fingerprint recognition system are shown
in fig.4 Jiao Ruili et. al., [5] they are do an automatic fingerprint
identification system the acquisition and pre-processing
system with a fixed point DSP, TMS320VC5509A and a
fingerprint sensor, MatBF200. And they said that the system is
diminutive and flexible and they are presents a VC5509A
based fingerprint pre-processing system, accomplished
fingerprint image acquisition. The pre-processing system is
accomplished with the properly selected algorithm on a DSP
platform. Comparing the results of the algorithms, appropriate
Fig.4. Fundamental Steps of Fingerprint Recognition System algorithms are selected for fingerprint identification pre-
processing. They are Median Filtering, Directional Filtering
Enhancement, Fixed Threshold Binarization, and Hilditch to perform their algorithm. Yi Chen and Anil K Jain [12]
Thinning. proposed an algorithm based on fingerprint features that
Yun and Cho [6] in this work they adaptive pre-processing means minutiae features and ridges features also Pattern and
method on fingerprint image and extracts five features from it. Pores. Their find the correlation between Fingerprint features
and they used clustering method for analyses image quality, and their distributions in their model. Tachaphetpiboont and
and enhance it by their characteristics. This is what pre- Amornraksa [13] propose a feature extraction method based
processing is performed after distinguishing the fingerprint on FFT for the fingerprint matching. The recognition rate
image quality related to its characteristics. obtained from the proposed method is also evaluated by the k-
NN classifier. The amount of time required for the extraction
and verification is very less in this approach. In fig.7, show the
feature extraction of fingerprint. and table III show some
summary of feature extraction researches.

(a) (b) (c)

Fig.6 preprocessing steps (a) original image (b) enhancement(c) binary image
The Table II shows the some recent research of pre-processing (a) (b)
Fig 7.feature extraction (a) thinning image (b) minutiae
Table II. Summary of fingerprint pre-processing stage
Ref Year Pre-processing Database Table III. Show the Summary of fingerprint feature extraction
[21] 2004 Orintation field :Modal-based method THU Ref Year Feature extraction Database
, region segmention ,orientation filed [29] 1992 Orientation field NIST4
,ridge enhancement [30] 1996 Singularities NIST4
[22] 2006 Hierarchical Discrete wavelet FVC2002 [31] 1998 Ridge structure NIST4
Transformation(DWT) [32] 1999 Singularities and ridge NIST4
[23] 2007 Gabor filters,mask estimation, FVC2002 [33] 2001 Fingercode NIST4
Binarization ,Thinnig [34] 2002 Ridge Distribution NIST4
[24] 2008 Minutiae feature by using CNN ----------- [35] 2003 Relational graph, fingercode NIST4
[25] 2013 Normalization,Ridge segmention , FVC2002 [21] 2004 Minutiae extraction THU
Ridge orintation Core point detection. [22] 2006 Seven Invariant moment, fingercode, FVC2002
[26] 2012 Enhancement using two stage FVC2002 refrences point
determination of reference point and [23] 2007 Ridge ending and ridge bifurcation FVC2002
determination of ROI [24] 2008 Minutiae feature by using CNN -----------
[27] 2007 Gray scale image ,binarization ----------- [25] 2013 ROI,Compute LDP Code (local FVC2002
[28] 2013 Gabor filter and FFT, Normalization, FVC2004 Directional pattern)
localorientation,local frequency, [36] 2014 Fixed length represntion that provide FVC2002/
region mask , filter, Binarization extract aligment between features. FVC2004
[26] 2012 Local and globle Invariant moment FVC2002
C. Feature extraction stage Feature and PCA for feature
selection
The feature extraction process of fingerprint image applied
on the output of pre-processing stage. The process of feature D. Matching stage:-
extraction depends on set of algorithms. A fingerprint feature
The matching stage is the process to compare the
extraction program is to locate, measure and encode ridge
acquired feature with the template in the database. In other
endings and bifurcations in the fingerprint. There are various
words the process of matching stage is to calculate the degree
methods for extracting the features from the fingerprint image.
of similarity between the input test image (for user when he
The famous methods is minutiae extraction algorithm which is
wants to prove his/her identity) and a training image from
find the minutiae points and map their relative placement on
database (the template which created at the time of enrolment).
the fingerprint .There are two types of minutiae points; Ridge
Matching can be done in three methods: hierarchical approach,
ending and Ridge bifurcation [7]. In[8] they are used an
classification approach and Coding approaches. The
advanced method for extract feature from fingerprint which
hierarchical approach is increases matching speed at the cost of
done by extract minutiae directly from original gray-level
accuracy [14].Classification approaches assign a class to each
images without use binarization and thinning and they use
biometric in a database. There are many classification methods
gabor filter methods to extract features from fingerprint [9].
including KNN classifier [15]. Coding approaches which use
Afsar et. al., [10] In their research the extract the minutiae
one matching function to search entire databases.
from fingerprint image after apply the binarized, thinned and
Arun Ross et. al., [16] proposed the hybrid fingerprint
segmented version of a fingerprint image. In this system the
matcher which employs the combination of ridge strengths
fingerprint classification for indexing during fingerprint
and a set of minutiae points.
matching. Zebbiche and Khelifi [11] presented biometric
Johg Ku Kum et. al., [17] presented a study on Hybrid
images as one Region of Interest (ROI). In their method use
fingerprint matching methods. They combining minutiae
Discrete Wavelet Transform and Discrete Fourier Transform
matching and image based fingerprints verification methods
and the matching done by using the shapes of fingerprint such Table V. Some fingerprint databases
as cross(diamond and dispersed) and square . Database Total Subject Image Resolutio Sensor
images / sample Size n dpi type
Swapnali Mahadik et. al.,[18] in their work the Alignment DB1_B 880 110- 8 300x300 500 dpi Optical
based Minutiae Matching algorithm used for matching . in this DB2_B 880 110- 8 256x364 500 dpi capacitive
FVC
case the images are subjected to translation Rotation and 2000
DB3_B 880 110-8 448x478 500 dpi Optical
Scaling to do the matching stage. Anil Jain et. al., [19] in this DB4_B 880 110-8 240x320 ~500dpi
Synthetic
Generator
work the matching stage perform by integrate three fingerprint
DB1 _B 880 110-8 388x374 500 dpi Optical
matching algorithms which is Hough transform, string FVC DB2_B 880 110-8 296x560 569 dpi Optical
distance and 2D dynamic programming based matching using 2002 DB3_B 880 110-8 300x300 500 dpi capacitive
the logistic regression method. DB4_B 880 110-8 288x384 ~500dpi
sFinGe
Aparecido Nilcau Marana and Jain [20] in this work the v2.51
matching is perform by using Ridge Based using the Hough DB1_A 1440 120-12 640x480 500 dpi Optical
DB2_A 1440 120-12 328x480 500 dpi Optical
transform method. In the fig. 8 shows the example of some FVC
thermal
fingerprint matching of two fingerprints. 2004 DB3_A 1440 120-12 300x480 512 dpi
sweeping
sFinGe
DB4_A 1440 120-12 288x384 ~500dpi
v3.0
Electric
DB1 1,800 150-12 96×96 250 dpi
Field
FVC DB2 1,800 150-12 400×560 569 dpi Optical
2006 Thermal
DB3 1,800 150-12 400×500 500 dpi
sweeping
Fig .8.Example of fingerprint matching SFinGev
DB4 1,800 150-12 288×384 ~500 dpi
3.0
polyU 3170 140-22 ~1,200 dpi Optical
The table IV. Show some summary of some research related CASIA 20000 4000-5 328×356 ------ Optical
with fingerprint marching and which matching methods used custom
polyU (HRF) 1480 148-10 320x240 1200 dpi
and in which database are test. built
Table IV. show the Summary of fingerprint matching FingerDOS 3600 360 - 10 260x300 500dpi Optical
Ref Year Matching Database
[37] 1996 Hough transform-based approaches ----------- IV. CONCLUSIONS
[38] 1997 Ridge-based relative pre-alignment -----------
[21] 2004 Minutiae matching THU This paper gave an overview of the fingerprint recognition.
[39] 2005 Global matching of clusters of ---------- We highlighted in details the fingerprint recognition step by
minutiae step. We also referred to the image acquisition stage, image
[22] 2006 Invariant moment fingerCode and FVC2002 pre-processing stage, feature extraction stage and matching
LVQ
stage for recognition purpose in details with some previous
[40] 2006 Global minutiae matching with image ----------
correlation work. In addition to that we introduced some techniques for
[23] 2007 Minutiae matching, vector matching FVC2002 fingerprint recognition and the finally the summary of
,weight modification and local area fingerprint databases with some characteristics.
matching process
[24] 2008 Minutiae matching ,which find the ---------
similartiy between two images and by REFERENCES
calculating the correlation between
these images. [1] N. K. Ratha, K. Karu, S. Chen, and A. K. Jain ,” A real-time matching
[41] 2009 Global matching by evolutionary system for large fingerprint databases ,” IEEE Trans.Pattern
-------- Anal.Mach Intell.,vol.18,no.8.pp 779-813,Aug.1996.
algorithms
[42] 2010 Weighted global matching with --------- [2] A. K. Jain and L.Hong,”Online fingerprint verification,” IEEE
adjustment of scores Trans.Pattern Anal.Mach Intell.,vol.19,no.4.pp 302-341,Apr.1997.
[43] 2012 Orientation image-based relative pre- ----------- [3] Kumar, A., Zhang, D.,” Combining fingerprint, palmprint and hand-
alignment shape for user authentication. In Pattern Recognition, ICPR 2006. 18th
[25] 2013 LDP and SLFNN FVC2002 International Conference on (Vol. 4, pp. 549-552). IEEE. 2006.
[44] 2013 Hierarchical and/or multilevel ----------- [4] Zhao, F., Tang, X. 2007. Preprocessing and post processing for
minutiae matching skeleton-based fingerprint minutiae extraction. Pattern Recognition 40
[27] 2007 Minutiae matching ,RMI and Fuzzy --------- (2007) 1270 – 1281.
operator
[5] Jiao Ruili and Fan Jing, “VC5509A Based Fingerprint Identification
[26] 2012 ELM and R-ELM FVC2002
Preprocessing System,” International Conference on Signal
Processing, pp. 2859 – 2863, 2008.
III. DATABASES
[6] E. K. Yun and S. B. Cho, “Adaptive Fingerprint Image Enhancement
There are many fingerprint databases which are defer from with Fingerprint Image Quality Analysis,” International conference of
other by total images, number of subject, number of sample , Image and Vision Computing, pp. 101–110, 2006.
image size, resolution and type sensor which are captured the [7] Deshpande, A., S., Patil, S., M., Lathi, R.”A Multimodel Biometric
Recognition System based on Fusion of Palmprint Fingerprint and
image of fingerprint the table V. show the some standards Face”. International Journal of Electronics and Computer Science
databases available with some of characteristics of Engineering. ISSN-2277-1956,2012.
it[45,46,47,48].
[8] Zhao, F., Tang, X,”Preprocessing and postprocessing for skeleton- machine”,Neural comput& applic (2013) 22:435-445, DOI
based fingerprint minutiae extraction”.Pattern Recognition, 40(4), 10.1007/s00521-011-0806-0, Springer-Verlag London 2012.
1270-1281,2007. [27] Montesanto,A.Baldassarri,P.Vallesi,G.Tascini,G.,”
[9] Jain, A. K., Prabhakar, S.,Hong,L.”A multichannel approach to Fingerprints Recognition Using Minutiae Extraction:aFuzzy
fingerprint classification”. Pattern Analysis and Machine Intelligence, Approach.”,IEEE Conference Publications,14th International
IEEE Transactions on, 21(4), 348-359. 1999. Conference on Image Analysis and Processing, ICIAP 2007,
[10] F. A. Afsar, M. Arif and M. Hussain, “Fingerprint Identification and Pages: 229 - 234, DOI: 10.1109/ICIAP.2007.4362784, 2007.
Verification System using Minutiae Matching,” National Conference [28] Morteza Zahedi, Ozra Rostami Ghadi ,” Combining Gabor filter and
on Emerging Technologies, pp.141-146, 2004 FFT for fingerprint enhancement based on a regional adaption method
[11] K.Zebbiche and F.Khelifi,“Region-Based Watermarking of and automatic segmentation”,springer verlag london 2013,SIViP,DOI
Biometrics Images: Case Study in Fingerprint Images,” Proceedings of 10.1007/s11760-013-0436-3 ,2013
International Journal of Digital Multimedia Broadcasting, pp. 1-13, [29] Wilson CL, Candela GT, Grother PJ, Watson CI, Wilkinson RA ,”
2008. Massively parallel neural network fingerprint classification system.
[12] Yi Chen and A K Jain, “Beyond Minutiae: A Fingerprint Individuality National Institute of Standards and Technology; NISTIR 4880. 1992
Model with Patteren, Ridge and Pore Features,” International [30] Karu K, Jain A ,” Fingerprint classification” . Patt Recog 29(3):389–
Conference on Biometrics, pp. 523-533, 2009. 404, 1996
[13] S Tachaphetpiboont and T Amornraksa, “Applying FFT Features for [31] Senior A ,”A hidden Markov model fingerprint classifier”. Conference
Fingerprint Matching,” Proceedings of the IEEE Conference on record of the Thirty-First Asilomar Conference on Signals, Systems &
Wireless Pervasive Computing, pp. 1-5, 2006. Computers 1:306–310, 1997
[14] J. You, W.K. Kong, D. Zhang, K.H. Cheung, “On hierarchical [32] Hong L, Jain .” Classification of fingerprint images”. In: Proceedings
palmprint coding with multiple features for personal identification in of the 11th Scandinavian Conference on Image Analysis,
large databases”, IEEE Transactions on Circuits and Systems for Kangerlussuaq, Greenland, June 1999 .
Video Technology 14 (2) (2004) 234–243, 2004 [33] Yao Y, Frasconi P, Pontil M ,” Fingerprint classification with
[15] Gayathri, R. Ramamoorthy, P.”Fingerprint and palmprint Recognition combinations of support vector machines” . In: Proceedings of the 3rd
Approach based on Multiple Feature extraction”. European Journal of International Conference on Audio and Video Based Biometric Person
scientific research. Vol 76, No 4, 2012 . Authentication, Halmstad, Sweden, June 2001
[16] Arun Ross, Anil Jain and James Reisman, “A Hybrid Fingerprint [34] Chang J, Fan K ,” A new model for fingerprint classification by ridge
Matcher,” Proceedings of International Conference on Pattern distribution sequences”. Patt Recog 35(6):1209–1223 , 2002
Recognition, pp .1661-1673, 2003. [35] Yao Y, Marcialis G, Pontil M, Frasconi P, Roli F ,” Combining flat
[17] Jong KU Kin, Seung-Hoon Chae, Sung Jin Lim and Sung Bum Pan, and structured representations for fingerprint classification with
“A Study on the Performance Analysis of Hybrid Fingerprint recursive neural networks and support vector machines” . Patt Recog
Matching Methods,” International Journal of Future Generation 36(2):397–406, 2003
Communication and Networking, pp. 23-28, 2008. [36] Akhil Vij, Anoop Namboodiri,“ Learning Minutiae Neighborhoods: A
[18] Swapnali Mahadik, K Narayanan, D V Bhoir and Darshana Shah, New Binary Representation for Matching Fingerprints”, 2014 IEEE
“Access Control System using Fingerprint Recognition,” International Conference on Computer Vision and Pattern Recognition Workshops
Conference on Advances in Computing, Communication and Control, ,2014.
pp. 306-311, 2009. [37] N.K. Ratha, K. Karu, S. Chen, A.K. Jain, A real-time matching system
[19] A K Jain, S Prabhakar and A Chen, “Combining Multiple Matchers for for large fingerprint databases, IEEE Trans. Pattern Anal. Mach. Intell.
a High Security Fingerprint Verification System,” Pattern Recognition 18 (1996) 793 799–813.
Letters, Elsevier Science Direct, vol. 20, pp. 1371- 1379, 1999. [38] A.K. Jain, L. Hong, R.M. Bolle, On-line fingerprint verification, IEEE
[20] A N Marana and A K Jain, “Ridge-Based Fingerprint Matching using Trans. Pattern Anal. Mach. Intell. 19 (1997) 302–314.
Hough Transform,” Proceedings of the IEEE Brazilliab Symposium on [39] E. Zhu, J. Yin, G. Zhang, Fingerprint matching based on global
Computer Graphica and Image Processing, pp. 112-119, 2005. alignment of multiple reference minutiae, Pattern Recogn. 38 (2005)
[21] Jinwei Gu,”A model-based method for the computation of fingerprints' 1685–1694.
orientation field ”, IEEE Transactions on Image Processing, Volume: [40] D. Wan, J. Zhou, Fingerprint recognition using model-based density
13, No.6, Pages: 821 - 835, DOI: 10.1109/TIP.2003.822608, 2004. map, IEEE Trans. Image Process. 15 (2006) 1690–1696.
[22] JuchengYang; jinWook Shin; BungJun Min; JongBin Park; Dongsun [41] W. Sheng, G. Howells, M. Fairhurst, F. Deravi, K. Harmer, Consensus
Park,” Fingerprint Matching Using Invariant Moment FingerCode and fingerprint matching with genetically optimised approach, Pattern
Learning Vector Quantization Neural Network” , IEEE Conference Recogn. 42 802 (2009) 1399–1407.
Publications on Computational Intelligence and Security, Volume: 1,
[42] R. Kumar, B.R.D. Vikram, Fingerprint matching using multi-
Pages: 735 - 738, DOI: 10.1109/ICCIAS.2006.294231, 2006.
dimensional ann, Eng. Appl. Artif. Intell. 23 (2010) 222–228.
[23] WangYuan,YaoLixiu,ZhouFuqiang,“A Real Time Fingerprint Recogni
[43] X. Jiang, X. You, Y. Yuan, M. Gong, A method using long digital
tion System Based On Novel Fingerprint Matching Strategy”, 8th
straight segments for fingerprint recognition, Neurocomputing 77
International Conference on Electronic Measurement and Instruments.
(2012) 28–35.
ICEMI '07. Pages: 1-81 - 1-85, DOI: 10.1109/ICEMI.2007.4350576 ,
2007. [44] F. Chen, X. Huang, J. Zhou, Hierarchical minutiae matching for
fingerprint and palmprint identification, IEEE Trans. Image Process.
[24] Abrishambaf,R.Demirel,Hasan,Kale,I,”A fully CNN based fingerprint
22 (2013) 4964– 632 4971.
recognition system”, 11th International Workshop on Cellular Neural
Networks and Their Applications. CNNA 2008. IEEE Conference [45] Fingerprint Verification Competition(FVC) 2000,
Publications,Pages: 146 - 149, DOI: 10.1109/CNNA.2008.4588667, http://bias.csr.unibo.it/fvc2000/
2008 . [46] Fingerprint Verification Competition (FVC) 2002,
[25] Kumar,R. Chandra,P. Hanmandlu, M.,”Local directional pattern (LDP) http://bias.csr.unibo.it/fvc2002/
based fingerprint matching using SLFNN”, IEEE Second International [47] Fingerprint Verification Competition (FVC) 2004,
Conference on Image Information Processing (ICIIP), Pages: 493 - http://bias.csr.unibo.it/fvc2004/
498, DOI: 10.1109/ICIIP.2013.6707640, 2013. [48] Fingerprint Verification Competition (FVC) 2006,
[26] Jucheng Yang,Shanjuan Xie,Sook Yoon, Dongsun Park, Zhijun Fang, http://bias.csr.unibo.it/fvc2006/
Shouyuan Yang,”Fingerprint matching based on extreme learning

View publication stats