Fingerprint Feature Extraction using Scanning Window Analysis

Abstract

In the course of recent years, the authors have attempted to separate the features of fingerprint as it is the most widely used biometric identification system in various applications such as, security and authentication devices, forensic identification, and fingerprint scanner in various electronic devices. It is the demand of the coming era to coordinate such innovation for the simplicity of the openness. Precise fingerprint recognition presupposes vigorous element extraction which is frequently hampered by noisy information. In this paper, to acquire the area and sort of all minutiae i.e., the discontinuities in the ridges and bifurcation of the fingerprint, an efficient and simple way is proposed using scanning window analysis (SWA)

Index Terms—Fingerprint Recognition, AFIS, Adaptive Thresholding, SWA

I. INTRODUCTION

FINGERPRINTS have been broadly utilized as a biometric trademark by criminological sciences. Because of the constancy and uniqueness of fingerprints, it is the most generally utilized among all the biometric methods known today [1]. It is the demand of the coming era to coordinate such innovation for the simplicity of the openness. Late advances in automated fingerprint identification systems (AFIS), have brought about an expanded organization of AFIS in wide applications, for example, e-commerce, user authentication in laptops and cell phones, and security systems. There are many challenges while obtaining the fingerprints information as fingerprints are graphical patterns of ridges and valleys, and for obtaining fingerprints information, feature extraction is a very important level of the process

Fingerprint contains complex patterns of stripes, called ridges. There exists some crevice between the ridges, called valleys. In a fingerprint, the dull lines of the image are known as the ridges and the white zone between the ridges is called valleys. A ridge can spread further in two ways, it is possible that it closes or bifurcates into two ridges [2]. The spot where ridge finishes is called end or ridge end and where it bifurcates is called bifurcation. Minutiae comprise of these two fundamental sorts, ridge end and bifurcation [3]. These two sorts of minutiae are considered as the essential minutiae focus between the ridges called valleys

The fingerprint pattern comprises of interceding ridges and valleys separated equidistantly. According to Maltoni et al

[4], fingerprints are consistently portrayed by elements at three levels: ridge flow and pattern type, ridge endings and bifurcations, and pores and incipient ridges. Minutiae which is the most broadly utilized feature is normally characterized as the ridge ending and the ridge bifurcation [5]. Different systems in light of the minutiae-based fingerprint representation were proposed [6], [7]

For the processing of fingerprint images, two stages are of crucial significance for the accomplishment of biometric recognition namely, image enhancement and feature extraction

To elaborate, the fingerprint identification technique generally follows three steps [1], [8]: _ Pre-processing, with a specific end goal to wipe out excess data

_ Feature Extraction, where ridges, bifurcation or any other features of fingerprints are extracted

_ Template Matching, where the features obtained are matched in order to achieve the percentage of similarity

The assignment of fingerprint enhancement is to check the quality impairments and to recreate the real fingerprint design as consistent with the first as could be allowed. Normally, the methodologies in view of low resolution features use Gabor filters or wavelets (e.g., [9]–[11]) and strategies fitting in with the methodologies in view of high resolution features use a region-growing algorithm [12] and scoring method [13]

Fingerprint recognition is widely used in various applications

UIDAI project was initiated by Government of India to issue a 12-digit unique identification number called Aadhar to each resident. Its objective is to collect the biometric and demographic data of residents. Nowadays, several laptop computers and cellphones are equipped with fingerprint scanners

Scientific way to understand child’s potential and personality, dermatoglyphics is used which refers to fingerprint patterns

All law implementation offices overall routinely gather fingerprints of caught hoodlums to track their criminal history

In this paper, the authors have presented an incorporated methodology for fingerprint feature extraction utilizing scanning window analysis. Extraction of features from fingerprints is a testing issue. The proposed algorithm depends on the regular succession of steps utilized as a part of fingerprint recognition

However, every stride has been particularly planned and streamlined to handle fingerprint images with a decent tradeoff in the middle of exactness and pace

II. THE PROPOSED ALGORITHM

In this section, the proposed algorithm is discussed when all is said in done, and after that we are portraying the two noteworthy parts of system one by one, in the following parts

Figure 2 shows a review of the feature extraction methodology, initially a grayscale picture was taken and it was gotten as an input image. After reading the image, the first pre-processing part is implemented and then the cropped region is feed forward for the feature extraction

Pre-processing is an imperative stride for Fingerprint Recognition System (FRS). It raises the quality and produces an image in which minutiae can be recognized effectively. The last consequence of FRS likewise relies on upon this stride

Minutiae discovery and highlight extraction step includes refining of the diminished image, distinguishing the minutiae focuses and after that extricating feature from an image [14]

The steps used in fingerprint feature extraction are as, _ Pre-processing _ Thinning/Morphological Operations _ Scanning Window Analysis The majority of the above steps are clarified in subtle element beneath. The above steps when performed successively, they create images of good quality, which offers in recognizing some assistance with trueing minutiae focuses precisely. Furthermore, these strides result in a precise FRS

A. Pre-processing

In pre-processing, the dark scale image is changed into a binary image. The essential principle of changing over an image into binary is to decide an edge threshold, afterward the pixels whose worth are more than the limit are changed over to white pixels, and the pixels whose quality are under or equivalent to the edge threshold are changed over to dark pixels. Conventionally, edge threshold has been chosen utilizing Otsu strategy [15]. For more genuine result, rather than retribution on the limit of the whole image, the edge threshold estimation of a little window (10_10) of the image are figured out. Thusly the whole image is converted into binary by means of adaptive threshold as shown in Figure 1

It is discovered tentatively that this technique creates a more gainful result. Image cropping is used to make the analytical extremely useful in analysing a fingerprint image. It is a subset of an image or a data set analyze for a specific reason [16], the obtained cropped image is shown in Figure 3

B. Morphological Operations

All the holes are filled and the edges are smoothed in dilation. A structuring element has been used for dilation is line with 70_. The proportion of the structuring element is 3 _ 3. It is instigated on the image sequentially, and if any one of the branches coincides with white pixel, the central pixel is switched over to white. Otherwise the central pixel will be black. In thinning operation, after we get the dilated image, the accompanying undertaking is to thin the image to only one pixel line. It is tender to create algorithms for minutiae discovery in diminished image. In the event that the width of the ridge is more than one pixel component, thus it is extremely hard to create algorithms for minutiae identification

So, in the proposed algorithm, thinning is accomplished by making image to width of only one pixel line. Figure 5 shows the obtained results after thinning operation

C. Scanning Window Analysis

After setting out the thinned image to simply single pixel, SWA is used to elicit the characteristics. Equally, all the lines are abbreviated to just one pixel, a 3_3 window can be used to extract out the ridges and bifurcation information. Figure 6 shows the methodology used in SWA. By using 3_3 window, thinned image is scanned from top to bottom and left to right

If the center pixel is black then it will decide whether there is any ridges or bifurcation. 6a shows center pixel black and only two pixels are in scanning window. So it is clear that only two pixels in scanning window results in ridges end. 6b consist of only three pixels and that is why it is a continuous line. If there is a pixel count higher or equal to four, it has to be a bifurcation. By utilizing this scheme all over the thinned image, ridges and bifurcation information can be obtained extracted from a fingerprint. This minutiae information can be further used for recognition purpose

III. EXPERIMENTAL RESULTS

In this section, the experimental results of the proposed algorithm for fingerprint feature extraction are presented. The system said to be robust if it is able to extract the fingerprint features from the input grayscale image correctly. The result shown in Figure 4 are the one obtained by implementing the proposed algorithm in licensed software MATLABR

From the result obtained by applying the discussed algorithm, it is conspicuous that the minutiae extracted from fingerprint are more sensitive to noise. Blue imprint in result speak to the bifurcation where as the red imprint demonstrates the ridges end. Proposed method gives better result for less noisy and non-merged valleys. As this is a easy yet proficient method for extricating features, it can be widely used in local application where very little hazard includes with respect to security

IV. CONCLUSION

Feature extraction of fingerprint using scanning window analysis have been presented and exploited in an integrated approach towards image enhancement methodology and minutiae extraction. Pre-processing steps are involved in the algorithm to remove the spurs which makes results more suitable for extracting features. As SWA works on the principle of scanning thinned image which reduced to only one line pixel, spurs can result into false extraction of fingerprint’s features

Here, the proposed method works proficiently even for the degraded images. The proposed technique can be applied directly to the original grayscale images. The accuracy of the algorithm is above 80% which can be implemented easily over a system and gives reliable results that can be used for various fingerprint identification based applications

ACKNOWLEDGMENT

Any accomplishment requires the elbow grease of many people. Authors would like to offer their sincere thanks to all of them. Authors would like to express their gratitude towards the reviewers of this paper for the valuable comments and suggestions, to all those researchers whose research work published in different journals and proceedings has been used as a reference in this paper and all people who directly or indirectly helped in this work. Authors would like to thank A. D. Patel Institute of Technology for assistance, counsel, and providing platform where the simulation work can be performed

REFERENCES

[1] A. Jain, R. Bolle, and S. Pankanti, Biometrics: Personal Identification

in Networked Society. Kluwer Academic Publishers, 1999.

[2] C. Gottschlich, “Curved-region-based ridge frequency estimation and

curved gabor filters for fingerprint image enhancement,” IEEE Transactions

on Image Processing, vol. 21, no. 4, pp. 2220–2227, 2012.

[3] H. Fronthaler, K. Kollreider, and J. Bigun, “Local features for enhancement

and minutiae extraction in fingerprints,” IEEE Transactions on

Image Processing, vol. 17, no. 3, pp. 354–363, 2008.

[4] D. Maltoni, D. Maio, A. Jain, and S. Prabhakar, Handbook of Fingerprint

Recognition. Springer-Verlag, 2nd ed. ed., 2009.

[5] J. Gu, J. Zhou, and C. Yang, “Fingerprint recognition by combining

global structure and local cues,” IEEE Transactions on Image Processing,

vol. 15, no. 7, pp. 1952–1964, 2006.

[6] N. K. Ratha, “A real-time matching system for large fingerprint

databases,” IEEE Transactions on Pattern Analysis and Machine Intelligence,

vol. 18, no. 8, pp. 799–813, 1996.

[7] A. Jain, L. Hong, and R. Bolle, “On-Line Fingerprint Verification,” IEEE

Transactions on Pattern Analysis and Machine Intelligence, vol. 19,

no. 4, pp. 302–314, 1997.

[8] R. Sanchez-Reillo and A. Gonzalez-Marcas, “Access control system with

hand geometry verification and smart cards,” Aerospace and Electronic

Systems Magazine, IEEE, vol. 15, no. 45, pp. 45–48, 2000.

[9] X. Y. Jing and D. Zhang, “A face and palmprint recognition approach

based on discriminant DCT feature extraction,” IEEE Transactions on

Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 34, no. 6,

pp. 2405–2415, 2004.

[10] T. Connie, A. T. B. Jin, M. G. K. Ong, and D. N. C. Ling, “An automated

palmprint recognition system,” Image and Vision Computing, vol. 23,

no. 5, pp. 501–515, 2005.

[11] L. Hong, W. Yifei, and A. Jain, “Fingerprint image enhancement:

algorithm and performance evaluation,” IEEE Transactions on Pattern

Analysis and Machine Intelligence, vol. 20, no. 8, pp. 777–789, 1998.

[12] A. K. Jain and J. Feng, “Latent palmprint matching,” IEEE Transactions

on Pattern Analysis and Machine Intelligence, vol. 31, no. 6, pp. 1032–

1047, 2009.

[13] J. Li and G. Shi, “A Novel Palmprint Feature Processing Method Based

on Skeleton Image,” 2008 IEEE International Conference on Signal

Image Technology and Internet Based Systems, pp. 221–228, 2008.

[14] A. K. Jain, S. Prabhakar, and L. Hong, “A Multichannel approach to

fingerprint classification,” IEEE Transactions on Pattern Analysis and

Machine Intelligence, vol. 21, no. 4, pp. 348–359, 1999.

[15] O. Nina, B. Morse, and W. Barrett, “A recursive otsu thresholding

method for scanned document binarization,” 2011 IEEE Workshop on

Applications of Computer Vision, WACV 2011, pp. 307–314, 2011.

[16] S. J. Xie, D. S. Park, J. C. Yang, and S. Yoon, “ROI-based Fingerprint

Quality Estimation,” International Conference on Management of e-

Commerce and e-Government, pp. 460–464, 2009.

[...]