International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)

Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com Volume 1, Issue 2, July August 2012 ISSN 2278-6856

Fingerprint Image Enhancement, Thinning and Matching

Dinesh Kumar Misra1, Dr.S.P. Tripathi2 and Ashutosh Singh3
1

PhD Research Scholar, Teerthanker Mahaveer University, College of Engineering, Moradabad, Uttar Pradesh, India

Professor and HoD , Computer Science and Engineering, IET, Gautam Budha Technical University, Sitapur Road, Lucknow, Uttar Pradesh, India
3

Ashutosh Singh, Integral University, Department of Computer Science & Engineering, Lucknow, Uttar Pradesh, India

Abstract: Fingerprint image enhancement method is based

on the intrinsic characteristics of fingerprint patterns in the Fourier domain rather than spatial domain. Since signal components of fingerprints ridges are localized in the Fourier domain. So to enhance the localized signal components and attenuate the other noise component, fingerprint filters is designed in Fourier domain one to enhance ridge direction and other for ridge direction enhancement. Fingerprint matching is the process used to determine whether two sets of fingerprint ridge detail come from the same finger. If the two finger print image is given, the system first extract orientation field and then minutiae features and establishes alignment of two image using algorithm. There exist many algorithms that do fingerprint matching in many different ways. Some methods involve matching minutiae points between the two images, while others look for similarities in the bigger structure of the fingerprint. In this Paper, we propose a method for fingerprint enhancement in Fourier domain and matching based on minutiae matching. However, unlike conventional minutiae matching algorithms, this algorithm also takes into account region and line structures that exist between minutiae pairs. This allows for more structural information of the fingerprint to be accounted for, thus resulting in stronger certainty of matching minutiae. Also, since most of the region analysis is pre-processed, it does not make the algorithm slower.

Keywords: Fingerprint, Minutiae, Minutiae matching, Thinning, Scanning, Edge Enhancement, Region Coloring

1. INTRODUCTION
The subject of fingerprint image enhancement and processing for matching has been examined and many methods are proposed. Most of the methods have several steps, out of that one step is to detect fingerprint ridge direction and other step is to use the direction to enhance the image [2, 3, 5, 6]. Two of the fundamentally important conclusions that have risen from research are: (i) a person's fingerprint is natural structure and is not of changing nature (ii) everyone in this world has his own Volume 1, Issue 2 July-August 2012

fingerprint with the permanent uniqueness. Even the fingerprints in twins are not the same. In practice two humans with the same fingerprint have never been found. A fingerprint contains narrow ridges separated by narrow valleys and these ridges flows almost parallel to each other. The ridges are the dark area of the fingerprint and the valleys are the white area that exists between the ridges [9,12,15]. However in the research on finger print verification, we can distinguish it with the help of minutiae, which are the some abnormal points on ridges. There are two types of termination of minutiae, immediate ending of ridges or a point from where edges ends abruptly called termination and the point on ridge from where ridge split into two or more branches is known as bifurcation as shown in Fig.1. The most commonly used minutiae in current fingerprint matching techniques are ridge endings and bifurcations because they can be easily detected by only looking at points that surround them. Henry Faulds , Francis Galton and Edward Henry and among others had established scientific basis for using fingerprints as a method of personal identification in late 19th century. Since then the finger matching was mostly used by law enforcement agencies worldwide to establish the identity of suspect/victims based on partial prints or latent and to identify repeat offenders based on prints of all their fingers. But these techniques are finding many other applications like identity management, access control, attendance and time management etc. Due to rising concern on about security and frauds many Government and commercial organizations have substantially increased their own deployment of finger based matching and recognition system in several no forensic applications including physical and logical access control , ATM transaction ,border control and consumer device services. Fingerprint is dominant biometric trait in this application compared to other common traits such as face, iris and voice and new Page 17

International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)

Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com Volume 1, Issue 2, July August 2012 ISSN 2278-6856
emerging traits including gait, ear and palm vein. points in another image then the points are said matched. Still Finger print matching is difficult pattern recognition problem due to large intra-class variations like variation in finger print image of same finger and inter class variations like similarity between finger print images from different fingers. It is the idea of this paper to filter and rectify the above constraint.

3. IMPLEMENTATION PROCESS
Finger print image extraction is first step in this implementation process. This is mainly done to improve the image quality and make it clearer for further operations. Often Finger print image from various sources lack sufficient contrast and clarity. Hence enhancement by way image extraction is performed to improve accuracy of matching .It increases contrast between ridges and furrows and connect the some of the false broken points of ridges due to insufficient amount of ink or poor quality of sensing devices. It can be done by utilizing Histogram Equalization. Histogram equalization [12] is a technique of improving the global contrast of an image by adjusting the intensity distribution on a histogram. This allows areas of lower local contrast to gain a higher contrast without affecting the global contrast. Histogram equalization accomplishes this by effectively spreading out most frequent intensity values. The original histogram of fingerprint image has bimodal type (in Fig.2.a), the histogram after equalization occupies all the ranges from 0 to 255 and the visualization effect is enhanced as shown in Fig.2.b The result of histogram equalization is shown for one of the case of fingerprint image in fig.3.

(a) (b) Figure 1 Minutiae Features In this paper Section 2 describes the Minutiae matching method. Section 3 explains implementation process. Section 4 deals testing procedure. Section 5 describes output results as net outcome of proposed method and section 6 at the end future work.

2. MINUTIAE MATCHING METHOD

Fingerprint minutiae matching scheme [4,9,13,14] can be classified in three groups: 2.1 Correlation Based Matching In this process two finger print images are superimposed and correlation between corresponding pixels is computed for different alignment e.g. displacement and rotation. 2.2 Minutiae Based Matching In this process of matching minutiae are extracted from two fingerprints and stored as set of points in two dimensional planes. It consists of finding the alignment between template and the input minutiae sets that result in the maximum number of minutiae pairings. 2.3 Pattern or Image based matching Pattern based matching use algorithms to compare the basic fingerprint patterns like arch, whorl or loop between a previously stored template and candidate fingerprint. For this purpose image is required to be aligned in same orientation. In matching process algorithms finds a central point on the fingerprint image and centers on the image. In pattern based algorithm, the template contains the type, size and orientation of pattern within the aligned fingerprint image. The candidate fingerprint image is graphically compared with the template to determine the degree to which the match. Fingerprint matching technique uses one of the above techniques but most of the cases minutiae matching is utilized. Matching of minutiae is described above. Other technique of minutiae matching is minutiae distance relative to other minutiae around it. If multiple points in one image have similar distances between them, multiple Volume 1, Issue 2 July-August 2012

Figure 2 (a) Original Histogram (b) Histogram after Equalization

Figure 3 (a) Original Image (b) Enhanced image after Histogram Equalization Page 18

International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)

Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com Volume 1, Issue 2, July August 2012 ISSN 2278-6856
3.1 Thinning Thinning [1, 15] was done using the Zhang-Suen algorithm as described below, A Fast Parallel Algorithm for Thinning Digital Patterns. A 3x3 window is moved down throughout the image and calculations are carried out on each pixel to decide whether it needs to be in the image or not. To the right is a description of the window and the classification given to the pixels that surround the centre pixel. The algorithm runs two sub-iterations continuously until the image reaches a stable state. Table1. 3x3 windows to verify need of pixel in image. 3.2 Scanning a Fingerprint Some of the algorithms require a linear scan of the fingerprint image. Scanning is achieved by moving a fixed size window across the picture in a grid-like pattern as shown in fig.5. This can be seen in the image to the right. However, it is possible that areas of interest do not lie squarely in the one of the windows. To account for this the window is then shifted just vertically, just horizontally, and then vertically and horizontally by half the window size and the grid scan is completed again. Therefore, it takes four scans of the image to do the linear scan. This is not a problem because it is used for the preprocessing of a fingerprint image (which only occurs once) and is done in a linear manner.

Pseudo Code for Zhang Suen Thinning: Let A(P) be the number of 01 patters in the order set P2 P9 Let B(P) be the number of non-zero neighbors of P Do until image is stable (i.e. no changes made) Sub-iteration 1: Delete P from image if: a) 2 = B(P) = 6 b) A(P) = 1 c) P2* P4* P6= 1 d) P4*P6*P8=1 Sub iteration 2: a) and b) above c) P2*P4*P8 =1 d) P2*P4*P6 =1 This processes effectively thins the image, however, it sometimes creates undesirably artifacts. In the example of a Zhang-Suen thinned fingerprint there are gaps between edges as well as regions of small area that need to be removed for proper regional analysis as shown in Fig.4. Example of Zhang-Suen Thinned fingerprint:

Figure 5 Scanning of finger print Image 3.3 Edge Enhancement Regions are defined by the fingerprint edges that bound them. However, because of the nature of the fingerprint and current scanning techniques, ridge detail can be missing from the scanned fingerprint. Furthermore, the thinning algorithm can also eliminate some of the edge detail. Most missing edges take the form of gaps in an edge and are usually easily identified by a human. Still problem occurred in computer to recognize them. In the course of the project one of the edge enhancement techniques utilized, which caught some of the simple gaps, however, did not fill in the bigger or more complex ones. Pseudo Code for Edge Enhancement: Scan Image as explained in previous section: For each window: Find all the endpoints in the window For each endpoint pair Look at the line that goes through the points If the line is "strong" Draw the line between the points A line is said to be strong if many points on the line are already in or near points in the existing edge detail. If the line is strong then it is most likely that the ridge was supposed to span the gap and therefore can be drawn in. Note that because the image has been thinned, it is easy to find endpoints in the image. Endpoints are merely pixels that only have one neighboring pixel. Page 19

Figure 4 Input image

Thinned Image

Volume 1, Issue 2 July-August 2012

International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)

Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com Volume 1, Issue 2, July August 2012 ISSN 2278-6856
were used. Two separate minutiae pairs were used and the corresponding minutiae pairs were found on each of the 4 scans as shown in fig.7 and Fig.8.

3.4 Region Coloring Once the edge enhancement process completed and edges have been properly added to the image, the region coloring [11] process started. The region coloring is similar to taking the image into Microsoft Paint and using the color fill tool on all the valleys of the fingerprint, however, the code does it in a little more efficient way. The image is scanned and colors are associated with white space in the image. While the image is being colored in each pixel looks at the pixels around it to determine what color it should be and color equivalences are set up. Once again image is being scanned, replacing all the colors in the equivalence set with just one of the colors from them. Therefore, each pixel in a region has the same color number associated with it. Example of Region coloring:

5. RESULT
Four input Image 1,2,3 and 4 are taken as input for region coloring, then spurious region removal, if present any by using algorithm written .The results are shown below as output Image 5,6,7 and 8 respectively. Input Fingerprints:

Image1

Image2

Figure 6 (a) Input Image

(b) Output Image Image3 Image4 Figure 7 Four input Image (1, 2, 3, and 4) The pre-processing algorithms were run on each of the 4 different scans of the same finger to obtain the output fingerprints:

3.5. Spurious Region Removal As an artifact of the thinning process small regions are created where there should be no region. Because the matching process relies on the region pre-processing to be accurate these regions must be removed. Pse udo Code for Re gi on Re moval : For each window in scan: For each region encased in the window that is sufficiently small Remove the border between the erroneous region and the region it borders with least. This will make it so that regions that are small are spilled into a surrounding region that it most likely was supposed to belong to.

Image 5

Image 6

4. TESTING PROCEDURE
Once pre-processing is completed, the image is used for the matching process. In matching process, first we had to show that the region data was a good indication of matching minutiae. That is we need to show that the amount of regions between two minutiae is consistent across many different scans of the same fingerprint. To test our hypothesis 4 different scans of the same finger Volume 1, Issue 2 July-August 2012

Image 7

Image 8 Page 20

International Journal of Emerging Trends & Technology in Computer Science (IJETTCS)

Web Site: www.ijettcs.org Email: editor@ijettcs.org, editorijettcs@gmail.com Volume 1, Issue 2, July August 2012 ISSN 2278-6856
feature- feature extraction process, IEICE transactions, Vol.J72-D-II, N0.5, pp 724-732, 1989. [8] A.K.Jain, S Prahbakar, S.Hong,, L Pankanti, Filter Bank based Finger print Matching, IEEE transaction on Image Processing,Vol.9,No.5,pp.846859, May,2000, DOI :10.1109/83.841531 [9] Salil Prabhakar, Fingerprint classification and matching using filter bank, Ph.D Thesis, 2001. [10] Eu Zhu, Jianping Yin,Guomin Zhang, Fingerprint matching based on global alignment of multiple reference minutiae, Pattern Recognition 38,pp16851694,2005. [11] J. Feng, Combining Minutiae Descriptors for Fingerprint matching, Pattern recognition, pp.342352, Jan.2008. [12] S. Bana and Dr. D. Kaur, Fingerprint recognition using image segmentation, IJEAST, Vol. No.5,Issue No.1,pp.012-023, 2008. [13] Manvjeet Kaur, Mukhwinder Singh, Akshay Giridhar and Parvinder S Sandhu , Finger print Verification System using Minutiae Extraction Technique, World Academy of Science , Engineering and Technology,46 , 2008. [14] A.K.Jain, J Feng and JainFpMatching, IEEE 0018/9162, pp.36-45, 2010. K Nandakumar, Computer Society,

Figure 8 Output Image 5,6,7,8 (corresponding output image of input image1, 2, 3, 4 respectively)

6. CONCLUSION AND FUTURE WORK

Future work on this project would include the creating of a matching algorithm that uses the regional data created in this pre-processing system. The efficient matching algorithm have to be developed in theory and in code so that our goal of getting faster and more accurate matched image than with pre-existing software. Also, more work can be done on the edge enhancing algorithm as it does not properly detect missing edges that are supposed to be curved. It can be accomplished by edge orientation, edge enhancement using energy minimization principle.

ACKNOWLEDGEMENT
Authors are highly thankful to Teerthankar Mahaveer University (TMU) , Moradabad, U.P., India for all kind of support and co-operation to pursue research work under able Professor Dr. S.P.Tripathi of Gautam Budhha Technical University (GBTU), Lucknow, U.P. India.

REFERENCES
[1] L.Lam, S.W.Lee, and C.Y. Suen, Thinning Methodology-A Comprehensive Survey, IEEE Transaction on Pattern Analysis and machine intellgence,vol.14,no.9,1992. [2] Toshio Kamei and Masanori Mizoguchi ITRL, NEC Corporation, Japan: Image Filter Design For Fingerprint Enhancement- Proc. ISCV, 95, pp109114, 1995. [3] L. Hong, A. K. Jain, S. Pankanti and R. Bolle, Finger print Enhancement, Proc. First IEEE WACV, pp.202-207, Sarasota, 1996. [4] N.K Ratha, K.Karu,S.Chen, A.K.Jain, A Real-time matching system for large fingerprint database, IEEE transaction on Pattern Analysis and Machine Intelligence Vol..18, No.8,pp.799-813,1996 [5] Hong Y. Wan, A.K.Jain, Fingerprint Image enhancement Algorithm and performance Evaluation, IEEE Trans., Pattern Analysis & Matching,Intell.20,pp.777-789,1998. [6] Lin Hong, Wan Yi-fei and A. Jain, Finger print image Enhancement: Algorithm and Performance Evaluation, IEEE transaction on Pattern Analysis and Matching Intellgence, Vol.20, no.8, pp777-789, 1998. [7] K. Asai, Y. Hoshino and K. Kiji, Automated fingerprint Identification by minutiae-network

[15] C Saraswat and Amit Kumar, An Efficient Automatic Attendance System using Fingerprint Verification Technique, IJCSE, Vol.02, No.2, pp.264-269, 2010. Dinesh Kumar Misra has received B.Tech (ET) from IETE, New Delhi, M.Tech.(CSE) from AAIDU, Allahabad, U.P., India, MBA (HR) from IGNOU, New Delhi and Perusing Ph.D in CSE form College of Engineering, TMU, Moradabad, U.P., India on Digital Image processing. He has published 5 International and 3 National papers. Presently he is working as Scientist/Engineer in Department of Space, ISRO, Lucknow U.P., India since 1993. Dr. S.P. Tripathi, Professor and Head in CSE Department, IET, GBTU, Lucknow, U.P., India. He is Ph .D in CSE from Lucknow University, Lucknow, U.P., India and able Professor to supervise more than 8 Ph.D students. He has published more than 25 research paper. He has keen interest in research in the field of Data structure, Fuzzy Logic and Data Base Management. Ashutosh Singh, B.Tech in CSE from Integral University, Lucknow, U.P., India is Final year student and working on the above cited work.

Volume 1, Issue 2 July-August 2012

Page 21