fingerprint matching using minutiae points

IJCSC Volume 5 • Number 1 March-Sep 2014 pp. 226-236 ISSN-0973-7391

226

Fingerprint Matching Using Minutiae Points

Komal Sondhi Yogesh Bansal CSE&Baddi University CSE/IT&Baddi University [email protected] [email protected]

Abstract: This is a crucial stage as one needs to extract the right features in optimal way. Image or vector of the numbers with specific properties is used for creating template. Fingerprints are rich in details called minutiae, which can be used as identification marks for fingerprint verification. The goal of this thesis is to develop a complete system for fingerprint verification through extracting and matching minutiae. To achieve good minutiae extraction in fingerprints with varying quality, pre-processing in form of image enhancement and binarization is first applied on fingerprints before they are evaluated. Many methods have been combined to build a minutia extractor and a minutia matcher. Minutia-marking with false minutiae removal methods are used in the work. An algorithm has been developed for minutia matching. This algorithm is capable of finding the correspondences between input minutia pattern and the stored template minutia pattern without resorting to exhaustive search. Performance of the developed system is then evaluated on a database with fingerprints from different people. Keywords: Fingerprint Recognition, Minutiae Point, Feature Extraction, Identification, Verification.

I. INTRODUCTION Fingerprints are distinct to each person thanks to unique papillary features and are different even in twins. Fingerprint patterns remain unchanged throughout the entire adult life and are easily produced for identification. If a finger is damaged, other fingers that are previously enrolled into the system can also be used for identification. Fairly small storage space is required for the biometric template, reducing the size of the database required. It is one of the most developed biometrics, with more history, research, and design. Each and every fingerprint including all the fingers are unique, even identical twins have different fingerprints. Sound potential for forensic use as most of the countries have existing fingerprint databases. Relatively inexpensive and offers high levels of accuracy. A fingerprint is a pattern of ridges and furrows located on the tip of each finger. Fingerprints were used for personal identification for many centuries and the matching accuracy is acceptable. In the past, patterns were extracted by creating an inked impression of the fingertip on paper. Today, compact sensors provide digital images of these patterns. The recognition process starts by capturing the finger image by direct contact with a reader device, which can also perform some validation procedures to avoid counterfeit measures (check of temperature and pulse). The uniqueness of a fingerprint can be Determined by the pattern of ridges and furrows as well as by the minutiae points, these are local ridge characteristics that occur at either a ridge bifurcation or a ridge ending. The feature values typically correspond to the position and orientation of certain critical points, known as minutiae points. The matching process involves comparing the two-dimensional minutiae sample and template patterns. Among the main advantages for the use of fingerprints are the higher levels of acceptability and their ease of use, as well the fact that it is a matured technology with several years of proven effectiveness. Also, the fact that its technology is legally accepted and that millions of enrolled fingerprints exist, are important. As disadvantages, it is considered vulnerable to noise and distortion brought on by dirt and twists. Also, since physical contact between the finger and the scanning device is required, the surface can become oily and cloudy after repeated use and reduce the sensitivity. Hygienic considerations must be considered too.

Fingerprint Recognition Fingerprint is a graphical pattern of ridges and valleys on the surface of human finger. It has uniqueness and permanence characteristics because of that it can be among the most reliable human characteristics that can be used in several ways for personal identification. Due to well understood biological and biometric formation properties, it has been used for personal identification, identification of criminals by various forensic departments around the worlds since centuries. Most automatic systems for fingerprint comparison are based on minutiae matching. Minutiae characteristics are local discontinuities in the fingerprint pattern which represent terminations and bifurcations. A ridge termination is defined as the point where ridges end abruptly. A ridge bifurcation is defined as the point where a ridge forks or diverges into branch ridge. These two most prominent scharacteristics ridge termination and ridge bifurcation, define minutiae of fingerprint image. A good quality

IJCSC Volume 5 • Number 1 March

fingerprint image contains about 40 to 100 minutiae.believed that each fingerprint is unique.So fingerprints have being used for ifurrows which are parallel and have sam

Fig. 1 A fingerprint image acquired by an Optical Sensor However, in fingerprint recognition, fingerprints are not distinguished by their ridges and furrows; they are distinguished by Minutia, which are features on the ridges. There is variety of minutia types on fingerprint image as in the below figure but two are mostly swhich is the immediate ending of a ridge and the other is called bifurcation, which is the point on the ridge from which two branches derive.

Fig. 1 Variety of minutia types on fingerprint image Fingerprint identification system has tmatching part.

a

c If we look closely at our fingers and palm friction ridge skin, we will notice that skin forms a pattern of ridges and valleys, as shown in figure 3. As we can see from figure, these ridges are not continuous lines, they might end or diverge. These points where ridges are not continuous are called minutiae points (features) and today the major of fingerprint recognition algorithms use minutiae features to compare similarity or dissimilarity between two fingerprint templates. Fingerprint ridges are completel

Volume 5 • Number 1 March-Sep 2014 pp. 226-236 ISSN-0973-7391

fingerprint image contains about 40 to 100 minutiae. A fingerprint is the feature pattern of onee. Each person has his own fingerprints with the permanidentification and recognition. A fingerprint is composedme width.

Fig. 1 A fingerprint image acquired by an Optical Sensor

fingerprint recognition, fingerprints are not distinguished by their ridges and furrows; they are distinguished by Minutia, which are features on the ridges. There is variety of minutia types on fingerprint image as in the below figure but two are mostly significant and in heavy usage: one is called termination, which is the immediate ending of a ridge and the other is called bifurcation, which is the point on the ridge from

Variety of minutia types on fingerprint image

three part that are image acquiring part, minutia extra

a b

d If we look closely at our fingers and palm friction ridge skin, we will notice that skin forms a pattern of ridges and valleys, as shown in figure 3. As we can see from figure, these ridges are not continuous lines, they might

where ridges are not continuous are called minutiae points (features) and today the major of fingerprint recognition algorithms use minutiae features to compare similarity or dissimilarity between two fingerprint templates. Fingerprint ridges are completely created by the seventh month of an individual fetus

7391

227

e finger and it is nent uniqueness. ed of ridges and

fingerprint recognition, fingerprints are not distinguished by their ridges and furrows; they are distinguished by Minutia, which are features on the ridges. There is variety of minutia types on fingerprint

ignificant and in heavy usage: one is called termination, which is the immediate ending of a ridge and the other is called bifurcation, which is the point on the ridge from

traction part and

If we look closely at our fingers and palm friction ridge skin, we will notice that skin forms a pattern of ridges and valleys, as shown in figure 3. As we can see from figure, these ridges are not continuous lines, they might

where ridges are not continuous are called minutiae points (features) and today the major of fingerprint recognition algorithms use minutiae features to compare similarity or dissimilarity between

y created by the seventh month of an individual fetus


228

development, remain the same for whole lifespan [18], and are the last recognizable characteristics to disappear after death [20]. The form of this ridge patterns is randomly and given that even monozygotic twins have different pattern of fingerprints [19]. Two main layers of skin are: epidermis (outer layer) and dermis (inner layer), where ridges belong to epidermis, meanwhile sweat glands, blood vessels (veins), nerves and other cellular structures are inside the dermis. When ridges are injured or other damage of our finger skin, they will recover and retain original with time, thus the property of permanence and uniqueness makes fingerprint leader to the biometric recognition technologies.

Fig. 3 a) Raw fingerprint image b) Ridge-valley structure of fingerprint image [1]

Fingerprint recognition is defined as the recognition (identification and verification) of individual using fingerprints. Fingerprint Recognition can be done by two methods which are defined as: 1) Fingerprint verification: It verifies an individual and known as one-to-one (1:1) relationship.

2) Fingerprint identification: It identifies an individual and known as one-to-many (1: N) relationship. The verification is much easier and faster because we have the two fingerprints and we just need to compare them [3]. On the other hand, the identification implies more time for extracting the fingerprint because there are needed much more details [3]. Each individual has unique and different fingerprints. Fingerprint classification involving 6 classes with critical points in a fingerprint called core and delta marked as circles and triangles in a Fig. 4 [4].

Fig. 4. Fingerprint Classification

Fingerprint recognition is done in different approaches: Texture-based, Image based approach, Minutiae based approach. But in this paper, fingerprint recognition is done by Fingerprint Matching using Minutiae. In fingerprint terms, minutiae are termed as the points of interest in a fingerprint. The most commonly used


229

minutiae in current fingerprint recognition technologies are ridge endings and bifurcations, because they can be easily detected by only looking at points that surround them (Bifurcation is the location where a ridge divides into two separate ridges)[4].

III. Steps of Fingerprint Matching using Minutiae The stages/steps of the fingerprint recognition are as follows: A. Acquisition In fingerprint recognition, the fingerprint images are acquired by two ways: 1) Online Fingerprint Images (Live Scan): For online fingerprint image acquisition, capacitance or optical fingerprint scanners such as URU 4000, etc [5]. Live scan scanners offer much greater image quality, usually a resolution of 512 dpi, which results in superior reliability during matching in comparison to inked fingerprints .

2) Offline Fingerprint Images (Inked): In the inked method an imprint of an inked finger is first obtained on a paper, which is then scanned [5]. This method usually produces images of very poor quality because of the non-uniform spread of ink and is therefore not exercised in online [5]. B. Pre-processing Fingerprint pre-processing states that some operations are to be performed before extraction of the minutiae. Krishna Kumar et al. proposed different method for this stage are: field orientation, ridge frequency estimation, image segmentation, image enhancement and thinning methods [1]. Manal Abdullah et al. describes different approaches which are: histogram equalization is used for enhancement, locally adaptive binarization implemented for binarization, region of interest is applied for segmentation and thinning [4]. F.A. Afsar et al. performed operations at this stage: block coherence for segmentation, Gabor filter for enhancement, adaptive thresholding for binarization and thinning are used for pre- processing stage [5]. Sangram Banal et al. [8], Manvjeet Kaur et al. [9], and Avinash Pokhriyal et al. [10] proposed C. Minutiae Extraction Minutiae extraction is the process extraction of the feature or minutiae from the fingerprint image. Zain S. Barham implement this stage is done in two steps are thinning is done by parallel thinning algorithm and extraction of minutiae is implemented by Crossing Number (CN) method [6]. Krishna Kumar et al. [1], Manal Abdullah et al. [4], F.A. Afsar et al. [5], Sozan Abdullah Mahmood [7], and Raju RajKumar et al. [12] are implemented by Crossing Number (CN) method which is used for minutiae extraction. Manvjeet Kaur et al. proposed an enhanced thinning is used for elimination of erroneous pixels [9]. Avinash Pokhriyal et al. describe rotation invariant thinning is used for minutiae extraction [10]. Tatsat Naik performed this stage into 2 steps are: thinning, minutiae extraction [14]. Graig T. Diefenderfer implemented the central line thinning method which is dealing with the rotated images without performance degradation [17]. D. Post Processing Fingerprint post-processing is the process which is performed after extraction of minutiae or feature from the fingerprint image. Manal Abdullah et al. [4], Zain S. Barham [6], F.A. Afsar et al. [5], and Raju RajKumar et al. [12] are illustrated distance method for the removal of spurious minutiae. Tatsat Naik et al. proposed remove false minutiae and unify terminations and bifurcations operations are performed at this stage [14]. E .Matching Fingerprint matching is the process which describes matching percentage/score between two fingerprint images. Manal Abdullah et al. [4], Zain S. Barham [6] proposed an alignment based match algorithm for the matching of the fingerprints. F.A. Afsar et al. describe the derivative of Hough transform is done with the help of spatial and oriental-based distance computation for registration of minutiae sets [5]. Sangram Banal described three matching techniques are correlation based matching, minutiae based matching, pattern based matching but in this paper, minutiae based matching is used [8]. Ruturaj M. Dekhane performed the various matching techniques and algorithms are used [11]. They are Cross Correlation Technique, Hungarian Matching algorithm, edit distance and neighbour vector. Tatsat Naik et al. perform operation at this stage: save template, and align and match template [14]. Neeta Murmu et al. proposed alignment based elastic matching algorithm is capable of finding the correspondences between minutiae without resorting to exhaustive research [18]. Shahram


Mohammadi et al. describe a new approach for fingerprint matching which is more robust to shift and rotation of the fingerprints because of its high accuracy [19]. The reference point and reference oridetermined and the features are converted into polar coapproach, it appropriate for the real time applications.

IV. PROPOSED METHOD GUI interface is developed in MATLAB to perform varioStep 1: A fingerprint image is captured from subject (user) by any type of fingerprint sensors. In this step digital gray scaled image is created, and all followed steps are performed on gray level fingerprint image.Step 2: Fingerprint image quality has important impact on performance and in this stage the quality of captured image is assessed and checked if the image fulfils requirements to be accepted or if it is rejected another attempt is required from user. Step 3: In this step the region of interest known as ROI is extracted from fingerprint image, thus it separates fingerprint from background. Step 4: In this stage some of standard image preGabor filtering), masking etc., are applied to enhance contrast between ridges and valleys, smooth, sharpen and remove noise from fingerprint image. Step 5: In this step grey-scale representation (image) is converted into a black and white pixels image or binarized image, where white pixels represent valleys, and black pixels represent ridges.Step 6: When skeletonised image is created from step 6, minutiae extraction is relatively simple step. Line structures are traced until a discontinuity is reached and this point is stored as minutype and angle). Identification of all minutiae points can be made through different methods: investigation, crossing numbers and pattern matching.

Block Diagram of Fingerprint Recognition

Fig.5. Block Diagram of Fingerprint Recognition System 1. Biometric sensor: First block this world and acquires all necessary data. characteristics. 2. Pre-processing: Second block perfoinput. In the following block, essential operations are to be performed before extraction of the minutiae.

��

��

��


Mohammadi et al. describe a new approach for fingerprint matching which is more robust to shift and rotation of the fingerprints because of its high accuracy [19]. The reference point and reference oridetermined and the features are converted into polar co-ordinates [19]. Due to high speed and accuracy of this approach, it appropriate for the real time applications.

PROPOSED METHOD GUI interface is developed in MATLAB to perform various operations.

A fingerprint image is captured from subject (user) by any type of fingerprint sensors. In this step digital gray scaled image is created, and all followed steps are performed on gray level fingerprint image.

age quality has important impact on performance and in this stage the quality of captured image is assessed and checked if the image fulfils requirements to be accepted or if it is rejected another attempt

region of interest known as ROI is extracted from fingerprint image, thus it separates

In this stage some of standard image pre-processing routines such as normalization, filtering (like are applied to enhance contrast between ridges and valleys, smooth, sharpen and

scale representation (image) is converted into a black and white pixels image or pixels represent valleys, and black pixels represent ridges.

When skeletonised image is created from step 6, minutiae extraction is relatively simple step. Line structures are traced until a discontinuity is reached and this point is stored as minutia point (minutia position, type and angle). Identification of all minutiae points can be made through different methods: investigation, crossing numbers and pattern matching.

Block Diagram of Fingerprint Recognition

Block Diagram of Fingerprint Recognition System

is also known as sensor, acts as an interface between system Usually it’s a picture acquisition system but can change

performs needed pre-processing- removes artifacts from sensor, characteristics are extracted. Fingerprint pre-processing states that some

operations are to be performed before extraction of the minutiae.

��

��

��

��

��

��

��

Test

Test

7391

230

Mohammadi et al. describe a new approach for fingerprint matching which is more robust to shift and rotation of the fingerprints because of its high accuracy [19]. The reference point and reference orientation are

ordinates [19]. Due to high speed and accuracy of this

A fingerprint image is captured from subject (user) by any type of fingerprint sensors. In this step digital gray scaled image is created, and all followed steps are performed on gray level fingerprint image.

age quality has important impact on performance and in this stage the quality of captured image is assessed and checked if the image fulfils requirements to be accepted or if it is rejected another attempt

region of interest known as ROI is extracted from fingerprint image, thus it separates

processing routines such as normalization, filtering (like are applied to enhance contrast between ridges and valleys, smooth, sharpen and

scale representation (image) is converted into a black and white pixels image or

When skeletonised image is created from step 6, minutiae extraction is relatively simple step. Line tia point (minutia position,

type and angle). Identification of all minutiae points can be made through different methods: neighbourhood

system and real change as per desired

sensor, enhances processing states that some

� ��

��

��

��


3. Feature extractor: This is a crucial vector of the numbers with specific properties 4. Template generator: Template is synthesismeasurements those are not required forfile and for protecting identity of enrolee 5. Stored template: While the enrolment 6. Matcher: And while matching processmatching it with existing one, estimatingevaluates template with input. This thenprocess which describes matching percentage/score between two fingerprint images.

V. EXPERIMENTAL In the following figures, result of all the intermediate steps of the proposed algorithm is highlighted: 1. After starting the project the GUI Interface of Fingerprint Recognition Systemscreen of the proposed system. We can run the proposed system write anydatabase.

Fig .6.1. GUI Interface of Fingerprint Recognition System

2. After clicking on "Select Fingerprint" the image clicking on Open button. Selected image is then converted to grayscale for further processing.


stage as one needs to extract the right features in optimalproperties is used for creating template.

synthesis of related features extracted from source. Elementsfor comparison algorithms are banished in templates for reducing

enrolee.

enrolment takes place, template gets stored in database or on card.

process is performed, acquired template gets passed on to individualestimating distance between these two using the algorithm. Matching

then becomes the output for specified purpose. Fingerprint matching is the process which describes matching percentage/score between two fingerprint images.

XPERIMENTAL RESULTS of all the intermediate steps of the proposed algorithm is highlighted:

GUI Interface of Fingerprint Recognition System. Fig 5.1 shows the starting screen of the proposed system. We can run the proposed system write any test person name to save it in the

GUI Interface of Fingerprint Recognition System

Select Fingerprint" it display the location of Fingerprint images from where we can select Open button. Selected image is then converted to grayscale for further processing.

7391

231

optimal way. Image or

Elements of biometric reducing size of

card.

individual that is Matching program

Fingerprint matching is the

of all the intermediate steps of the proposed algorithm is highlighted:

. Fig 5.1 shows the starting test person name to save it in the

it display the location of Fingerprint images from where we can select Open button. Selected image is then converted to grayscale for further processing.


Fig. 6.2. Select fingerprint Image for Pre

3. Now grayscale image need further enhancements. So click on "Extract Features". Extract Features is a four step process, i.e. image enhancement, making mask, finding minutiae, filtering false minutiae. Output will come as shown in figure 5.3

Fig.6.3. Image Enhancement and Feature Extraction


elect fingerprint Image for Pre-processing

3. Now grayscale image need further enhancements. So click on "Extract Features". Extract Features is a four process, i.e. image enhancement, making mask, finding minutiae, filtering false minutiae. Output will come

Image Enhancement and Feature Extraction

7391

232

3. Now grayscale image need further enhancements. So click on "Extract Features". Extract Features is a four process, i.e. image enhancement, making mask, finding minutiae, filtering false minutiae. Output will come


4. In this system we need to build a database from which we can search and compare selected image and give results. Enter name of person (whose thumb impression template is extracted in previous step) and click on "Save to Database".

Fig 6.4: Saving Fin 5. It's time to search and validate the person who is trying to login in our security system. For this we need to repeat step II and III first. And then click on "Search From Database". Here extracted template is compared wieach template (saved in database in previous steps). If match found it shows template comparison chart and matching score of searched person.

Fig. 6.5. Matching current Fingerprint template from Database and Calculating score


4. In this system we need to build a database from which we can search and compare selected image and give results. Enter name of person (whose thumb impression template is extracted in previous step) and click on

.4: Saving Fingerprint Template to database

5. It's time to search and validate the person who is trying to login in our security system. For this we need to repeat step II and III first. And then click on "Search From Database". Here extracted template is compared wieach template (saved in database in previous steps). If match found it shows template comparison chart and

Matching current Fingerprint template from Database and Calculating score

7391

233

4. In this system we need to build a database from which we can search and compare selected image and give results. Enter name of person (whose thumb impression template is extracted in previous step) and click on

5. It's time to search and validate the person who is trying to login in our security system. For this we need to repeat step II and III first. And then click on "Search From Database". Here extracted template is compared with each template (saved in database in previous steps). If match found it shows template comparison chart and

Matching current Fingerprint template from Database and Calculating score


6. Graphical representation of fingerprint shows that how matching score varies from one fingerprint to other. Here line with cross(x) ending represent current image taken from sensors. Line ending with dot(.) represents fingerprint template fetched from database.

Fig. 6.6. Graphical representation for score calculation

VI .Conclusions: The conclusion from the proposed method for fingerprint recognition is that the proposed method summarizes all the steps involved in the Fingerprint Recognition.means that the authentication and verification is provided.it means that the authentication and verification must not provided to individual.


representation of fingerprint shows that how matching score varies from one fingerprint to other. Here line with cross(x) ending represent current image taken from sensors. Line ending with dot(.) represents fingerprint template fetched from database.

Graphical representation for score calculation

The conclusion from the proposed method for fingerprint recognition is that the proposed method summarizes all the steps involved in the Fingerprint Recognition. If the matching percentage score more than 0.48 then it means that the authentication and verification is provided. If the matching percentage scores less than 0.48 then it means that the authentication and verification must not provided to individual.

7391

234

representation of fingerprint shows that how matching score varies from one fingerprint to other. Here line with cross(x) ending represent current image taken from sensors. Line ending with dot(.) represents

The conclusion from the proposed method for fingerprint recognition is that the proposed method summarizes percentage score more than 0.48 then it

If the matching percentage scores less than 0.48 then


235

Future Work: A similar technique can be designed by using Fingerprint recognition with another method which will replace the proposed algorithm with a better algorithm which will provide more enhanced and accurate results. Advanced technique can be used to produce better results. The development of latent fingerprints by use of chemical methods is one of the processes that crime scene investigators and forensic scientists utilize in criminal cases.

ACKNOWLEDGMENT I am thankful to my Guide my parents, husband and especially to my loving son Nikunj Malhotra whose blessings and continuous support gave me enough strength from time to time and helped me at every possible step. Special thanks to my husband who always support my innovative ideas.Finally, I am thankful to all whosoever have contributed in this thesis work.

REFERENCES

[1] Krishna Kumar, Basant Kumar, Dharmendra Kumar and Rachna Shah, Fingerprint Recognition using Minutiae Extraction, International Conference on ICT-Initiatives, Policies & Governance, Dehradun, India, 28-29 Nov 2011. [2] Davide Maltoni, Dario Maio, Anil K. Jain, Salil Prabhakar, Handbook of Fingerprint Recognition, 2nd Edition, Springer Press. 2009 2nd ed. 2009, XVI, 496p. [3] I. Iancu, N. Constantinescu, M. Colhon, Fingerprints Identification using a Fuzzy Logic System, Int. J. of Computers, Communications & Control, ISSN 1841-9836, E-ISSN 1841-9844, Vol. V (2010), No. 4, pp. 525-531. [4] Manal Abdullah, Mona Alkhozae and Mashaiel Alsowaiel, “Fingerprint Matching Approach Based on Bifurcation Minutiae”, Journal of Information and Communication Technologies, Volume 2, Issue 5, May 2012. pp.33-40. [5] F.A. Afsar, M. Arif and M. Hussain, Fingerprint Identification and Verification System using Minutiae Matching, National Conference on Emerging Technologies 2004. pp. 144-146. [6] Zain S. Barham, Fingerprint Recognition Using MATLAB, Graduation Project. [7] Sozan Abdullah Mahmood, Fingerprint identification Based on Skeleton Minutiae extraction, ICGST AIML-11 Conference, Dubai, UAE, pp. 12-14 April 2011. [8] Sangram Bana1 and Dr. Davinder Kaur2, Fingerprint Recognition using Image Segmentation, International Journal of Advanced Engineering Sciences and Technologies Vol No. 5, Issue No. 1, 012 – 023. [9] Manvjeet Kaur, Mukhwinder Singh, Akshay Girdhar, and Parvinder S. Sandhu, Fingerprint Verification System using Minutiae Extraction Technique, World Academy of Science, Engineering and Technology Vol:2,Issue 10. pp.10-20. [10] Avinash Pokhriyal, Sushma Lehri, MERIT: Minutiae Extraction using Rotation Invariant Thinning, International Journal of Engineering Science and Technology Vol. 2(7), 2010, 3225-3235. [11] Raju Rajkumar , K Hemachandran, A Secondary Fingerprint Enhancement and Minutiae Extraction, Signal & Image Processing : An International Journal (SIPIJ) Vol.3, No.2, April 2012. [12] Khalid Saeed, Marek Tabe˛Dzki, Mariusz Rybnik, Macin Adamski, K3M: A Universal Algorithm for Image Skeltonization and Review of Thinning Technique, Int. J. Appl. Math. Computer. Sci., 2010, Vol. 20, No. 2, 317–335. [13] Lin Hong, Student Member, IEEE, Yifei Wan, and Anil Jain, Fellow, IEEE, Fingerprint Image Enhancement: Algorithm and Performance Evaluation, IEEE Transactions on Pattern Analysis and Machine Intelligence, VOL. 20, NO. 8, AUGUST 1998. [14] Tatsat Naik, Om Sri Satyasai, Study of Fingerprint Recognition System”, B.Tech. (Project), National Institute of Technology, Rourkela. [15] Neeta Murmu, Abha Otti, Fingerprint Recognition, National Institute of Technology, Rourkela. [16] Hui Xu, Yifan Qu, Yan Zhang, Feng Zhao, FPGA Based Parallel Thinning for Binary Fingerprint Image, IEEE, 2009. [17] Flynn, P., Jain, A., & Ross, A. 2008. Handbook of Biometrics. Number ISBN-13: 978-0-387- 71040-2. Springer-Verlag. [18] Pankanti, S., Prabhakar, S., & Jain, A. aug 2002. On the individuality of fingerprints. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24(8), 1010 – 1025. [19] A. Jain, A. Ross, S. Pankanti, Biometrics: A Tool for Information Security. IEEE Transactions on Information Forensics and Security. Vol 1, pp 125-143 June 2006


236

[20] Anil K. Jain, A.Ross, and S. Prabhakar. An introduction to biometric recognition. IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, no. 1, pages 4–19, January 2004. [21] W. Bicz, Z. Gurnienny, and M. Pluta. Ultrasound sensor for fingerprint recognition. In Proc of SPIE, Vol. 2634. Optoelectronic and electronic sensors, pages 104-111, June 1995. [22] B. Moayar and K.S. Fu. An syntactic approach to fingerprint pattern recognition. Pattern [24] Maltoni, D., Maio, D., Jain, A. K. A., & Prabhakar, S. 2009. Handbook of Fingerprint Recognition. Number ISBN: 978-1-84882-253-5. Springer-Verlag, 2nd edition. [25] Babler, W. J. 1991. Embryologic development of epidermal ridges and their configurations. Birth Defects Original Article Series, 27(2), 95–112. [26] K. KARU and A. K. Jain, "Fingerprint Classification," Pattern recognition, Vol.29, No. 3, pp. 389-404, 1996. [27]R. Brunelli and D. Falavigna, “Person Identification Using Multiple Cues”, IEEE Trans. PAMI, vol. 17, no. 10, pp. 955-966, 1995. [28]J. Kittler, M. Hatef, R.P.W. Duin, and J. Matas, “On Combining Classifiers”, IEEE Trans. PAMI, vol. 20, no. 3, pp. 226-239, 1998. [29] L. Hong and A.K. Jain, “Integrating Faces and Fingerprints for Personal Identification”, IEEE Trans. PAMI, vol. 20, no. 12, pp. 1295-1307, 1998. [30]S. Ben-Yacoub, Y. Abdeljaoued, and E. Mayoraz, “Fusion of Face and Speech Data for Person Identity Verification”, IEEE Trans. Neural Networks, vol. 10, no. 5, pp. 1065-1075, 1999. [31]A. Ross and A.K. Jain, “Information Fusion in Biometrics”, Pattern Recognition Letters, vol. 24, no. 13, pp. 2115-2125, 2003. [32]S.Vasuhi. V.Vaidehi, N.T.Naresh Babu, Teena Mary Treesa. An Efficient Multi-modal Biometric Person Authentication System Using Fuzzy Logic. IEEE 978-1-61284-260-8/10. 2010 [33]Pankanti, S., Prabhakar, S., & Jain, A. aug 2002. On the individuality of fingerprints. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24(8), 1010 – 1025. [34]Busch, C. January 29th 2009. IMT 4621-Biometrics Course: "Biometric Systems" - script. Number Version 1.0. NISLab. [35] Ritu ,Minutiae Based Fingerprint Recogntion International Journal Of Engineering And Computer Science ISSN: 2319-7242 Volume 2 Issue 4 April, 2013 Page No. 1166-1171 [36] Shahram Mohammadi, Ali Frajzadeh, A Matching Algorithm of Minutiae for Real Time Fingerprint Identification System, World Academy of Science, Engineering and Technology, 2009. World Academy of Science, Engineering and Technology Vol:13 Issue 12, 2009 pp.12-29. [37] Chen, Y., Vinck, H., Gligoroski, D., & Knapskog, S. J. 2011. An overview of the informationtheoretic perspective on biometric systems. Norsk informasjonssikkerhetskonferanse - NISK, 4(10), 31–42.

fingerprint matching using minutiae points

Documents