Fingerprint Identification Application

1. INTRODUCTION
1.1. PREAMBLE
Recognition of persons on the basis of biometric features is an emerging phenomenon in our society. It has received increasing attention in recent years due to the need for security in a wide range of applications, such as replacement of the personal identification number (PIN) in banking and retail business, security of transactions across computer networks, high-security wireless access, televoting, and admission to restricted areas. For wide application and user-acceptance of fingerprint recognition, improvement of the recognition performance is still necessary. New

algorithms may reduce the error rates to levels that are acceptable for application of biometric authentication, and enable the use of low-cost sensors that can be integrated easily in wireless hardware or smart cards. Next, users will accept biometrics as a part of modern society if they have experienced the benefits of reliable and high-quality biometric systems.

1.2. IMPORTANCE OF Fingerprint Identification

Fingerprints are easily accessible, recognition requires minimal effort on the part of the user, it does not capture information other than strictly necessary for the recognition process (such as race, health, etc.), and provides relatively good performance. Several problems, with their associated algorithms and systems, can be defined in the context of fingerprint recognition, being verification, identification, and classification. The term recognition is used in a general sense and encompasses all three kinds of tasks.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

Verification (or authentication) systems use fingerprint technology to verify the claimed identity of a person. Such systems receive two inputs: the claimed identity of the person requesting authentication (usually a username or smart card) and the live-scanned fingerprint of that person. The claimed identity is used to retrieve a reference fingerprint stored in a database and is matched (compared) against the currently offered fingerprint (the test fingerprint). This results in a measure of similarity, on which the verification decision is based. Identification systems identify a person based on a fingerprint. Such systems receive only one input, namely the live-scanned query fingerprint. A database is searched for a matching fingerprint, which is also referred to as one-to-many matching. A person is identified if a matching fingerprint is found in the database. The system assigns the identity that corresponds to the matching fingerprint to the person that requests identification. On the other hand, if no matching fingerprint is found in the database, the person is rejected. For both verification and identification systems, enrollment is an important step. This is the process of taking reference fingerprints of all users and storing these in the database for comparison. The task of a Classification system is to determine which class (or group) the input fingerprint belongs to. These systems also receive only a single fingerprint as input. A well-known set of categories is formed by the Henry classes.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

1.3. ROLE OF IMAGE PROCESSING IN FINGERPRINT IDENTIFICATION

Digital image processing is the use of computer algorithms to perform image processing on digital images. As a subcategory or field of digital signal processing, digital image processing has many advantages over analog image processing. It allows a much wider range of algorithms to be applied to the input data and can avoid problems such as the build-up of noise and signal distortion during processing. Since images are defined over two dimensions (perhaps more) digital image processing may be modeled in the form of multidimensional systems. Digital image processing allows the use of much more complex algorithms, and hence, can offer both more sophisticated performance at simple tasks, and the implementation of methods which would be impossible by analog means. Some of the technologies used by digital image processing are: Feature extraction Pattern recognition

The goal of manipulation can be divided into three categories: Image Processing (image in -> image out) Image Analysis (image in -> measurements out) Image Understanding (image in -> high-level description out)

The most requirements for image processing of images is that the images be available in digitized form, that is, arrays of finite length binary words. For digitization, the given Image is sampled on a discrete grid and each sample or pixel is quantized using a finite number of bits. The digitized image is processed by a computer. To display a digital image, it is first converted into analog signal, which is scanned onto a display. Image processing is the study of any algorithm that takes an image as input and returns an image as output. This includes some processing like:

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application Display image and printing, image editing and manipulation,

4 image

enhancement, feature detection, image compression. Image and Video Processing enables you to acquire, process, and analyze images and video for algorithm development and system design.

1.4. PROJECT GOAL

The goal of this project is to develop a fingerprint identification application. The application is used to find whether a matching fingerprint image is present in the database of fingerprint images.

Fingerprint recognition is one of the most popular and successful methods used for person identification, which takes advantage of the fact that the fingerprint has some unique characteristics called minutiae; which are points where a curve track finishes, intersect with other track or branches off. A critical step in studying the statistics of fingerprint minutiae is to reliably extract minutiae from the fingerprint images. However, fingerprint images are rarely of perfect quality. They may be degraded and corrupted due to variations in skin and impression conditions. Thus, image enhancement techniques are employed prior to minutiae extraction to obtain a more reliable estimation of minutiae locations. Then the extracted minutiae are compared with stored minutiae features of other images and verified to find match exist or not. This application is mainly developed for helping police department in the identification of criminals. The most commonly found evidence on crime scene is fingerprint, so this application will be helpful for police identifying criminal on spot instead of taking fingerprints to laboratory and identifying it.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

1.5. PROJECT DESCRIPTION

Fingerprint identification application is an Image Processing project. In this project, the developed application compares acquired fingerprint image with database of fingerprint image and verify matching image exist or not. The steps involved in this application are: Image Acquisition Image Enhancement Binarization Of Fingerprint Image: Fingerprint Ridge Thinning Minutiae Extraction Minutiae Matching

In the first step we acquire fingerprint image using camera. The captured image is the input in the application to find whether a matching fingerprint exist in the database or not. The database will be consisting of collected fingerprint images, its features and details of the person related to it. The capture image is preprocessed to enhance is its quality. After enhancing the image is converted to binary image. Next to extract the features binarized image is reduced to one pixel width. Then in the next step we extract the minutiae features from the image and a matching process is performed with other images in the database.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

1.6. REQUIREMENT SPECIFICATION

1.6.1. HARDWARE REQUIREMENTS
Processor RAM Hard Disk : : : Intel P-IV system 1 GB RAM 120GB

1.6.2. SOFTWARE REQUIREMENTS

Operating System : Tool Programming : : Windows 7 Eclipse IDE with OpenCV plug-in and javaCV plugin java

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

2. LITERATURE SURVEY
2.1. INTRODUCTION
Biometric identification is one of the most amazing technological innovation of the recent history and fingerprint identification being the most promising form of it and most widely used. Out of a number of possible ways to match fingerprints, minutiae based matching is perhaps the most widely studied and have yielded better results in the past as compared to the other methods. Fingerprint identification is based upon unique and invariant features of fingerprints. Fingerprints are graphical flow like ridges present in human fingers which are formed during embryonic development, caused by ridges underneath the skin. According to FBI, the odds of two people sharing the same fingerprints are one in 64,000,000,000. Fingerprints differ even for ten fingers of the same person.

2.2. Fingerprint Patterns

In the biometric process of finger scanning, a ridge is a curved line in a finger image. Some ridges are continuous curves, and others terminate specific points called ridge endings. Sometimes, two ridges come together at a point called a bifurcation [3]. Ridge endings and bifurcations are known as minutiae.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application Fig 2.1

Fig 2.2

2.3. Advantages:
Some of the advantages high of fingerprint low identification for fraud are: and high high

distinctiveness,

permanence,

potential

performance with medium collectivity and acceptability. It also has certain drawbacks like need for training, finger and hand impairment, worn ridges etc acting as a barrier to universality.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

The method of identification is suitable for workstation access control , physical access control, Information system control etc.

2.4. Preprocessing Image

Extraction of minutiae features before matching needs a series of processes, including orientation computation, image segmentation, image enhancement, ridge extraction and shinning, minutiae extraction and filtering etc. before the matching can be done.

2.4.1.

Orientation Computation

The orientation field of a fingerprint image represents the directionality of ridges. Fingerprint image typically divided into number of non-overlapping blocks and an orientation representative of the ridges in the block is assigned to the block based on grayscale gradients in the block. Theblock size depends on the inter-ridge distance, i.e. it should include at least one ridge and one valley in a block. The block orientation can be determined from the pixel gradients by averaging or voting (optimization).

2.4.2.

Image segmentations
of partitioning

In computer vision, image segmentation is the process

a digital image into multiple segments. The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

10

2.4.3.

Image Enhancement

Image enhancement is the improvement of digital image quality (wanted e.g. for visual inspection or for machine analysis), without knowledge about the source of degradation. If the source of degradation is known, one calls the process image restoration. Both are iconical processes, viz. input and output are images.

2.5. Minutiae MATCHING

An earlier popular minutiae based technique was introduced by Bebis et al. [1] using the delay triangulation method. Jain et. Al [2]. Used ridge patterns in fingerprint matching. They used ridge information to help with alignment. For a pair of template and query minutiae, the template minutiae was rotated and translate taking the coordinates of this pair as origin and axes along and perpendicular to its direction. However the computational cost involved with method was still high. They first built a minutia-simplex that contains a pair of minutiae as well as their associated textures, with its transformationvariant and invariant relative features employed for the comprehensive similarity measurement and parameter estimation, respectively. By the second step, they used the ridge-based nearest neighborhood among minutiae to represent the ridge-based relative features among minutiae. Finally, they modeled the relationship between transformation and the comprehensive similarity between two fingerprints in terms of histogram for initial parameter estimation.

2.5.1.

Graph based fingerprint matching

Graph based fingerprint matching algorithm was presented by Isener et. Al [3] . This method however, is time consuming and complicated as complex algorithms like graph isomorphism has to be adopted in the system. An improvement was presented by Hrechak et.al[4]

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

11

2.5.2. Correlation filters to the fingerprint identification

Correlation filters have added features like built in shift invariance, closed form expressions and trade off discrimination for distortion tolerance .The one-to-one correlation of fingerprints on a large set of data yields poor results for fingerprint matching because of the elastic distortions between two fingerprints of the same finger . The distortions can be significant enough that the correlation cannot recognize elastic-distorted versions of the same fingerprint and cannot discriminate between a matching fingerprint and a non-matching fingerprint of the same class.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

12

3. METHODOLOGY
3.1. Image Acquisition
The fingerprint image can obtained by capturing fingerprint image on camera or phone.

Fig 3.1 Original Image

3.2. Image Enhancement

The performance of minutiae extraction heavily algorithms relies on and the other input

fingerprint

recognition

techniques

fingerprint image quality. In an ideal fingerprint image, ridges and valleys alternate and flow in a locally constant direction. The goal of an enhancement algorithm is to improve the clarity of the ridge structures in the recoverable regions and mark the unrecoverable regions as too noisy for further processing. For image Enhancement we have used Linear Contrast Stretching and histogram equalization techniques

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

13

Fig 3.2 Enhanced Image

3.3. BINARIZATION OF FINGERPRINT IMAGE

Binarization is a process that converts a grey level image into a binary image and in a binary image each pixel value is either 0 or 1(255). Most minutiae extraction algorithms operate on binary images where there are only two levels of interest: the black pixels that represent ridges, and the white pixels that represent valleys. This improves the contrast between the ridges and valleys in a fingerprint image, and consequently facilitates the extraction of minutiae. We have implemented adaptive binarization method and in this method there is a threshold value and below this all pixels are 0 and above this all pixels are 255 i.e. 1.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

14

Fig 3.3 Binarized Image

3.4. FINGERPRINT RIDGE THINNING:

Thinning is the process applied over binarized image, from previous step, by thinning certain pattern shapes until it is represented by 1-pixel wide lines. Fingerprint thinning is usually implemented via morphological operations such as erosion and dilation to reduce the width of ridges to a single pixel while preserving the extent and connectivity of the original shape.

Fig 3.4 Thinned Image

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

15

4. MINUTIAE EXTRACTION
The image obtained after binarization and thinning is ready to extract the features. If all the white pixels are 1 and black pixels are 0 then the width of the rigid lines of fingerprint is represented by only one zero pixel. In the image each pixel is surrounded by eight pixels and called neighbor pixel. In any point of a rigid line the summation of the neighbor pixels must be 6. If the rigid line is terminated then the summation will be changed and that will be 7. On the other hand in a point of bifurcation the summation will be 5 . To develop this algorithm we have to consider 3x3 window and the window will scan the whole image where the center pixel is black or 0. After passing the image through the algorithm we will get a new image where each bifurcation and termination is represented by a dot of a white pixel.

Fig 4.1 Fingerprint Minutiae feature The following algorithm and the Fig 4.2 representing the whole process.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

16

Fig 4.2: (a) 3x3 Window for searching minutiae (b) rigid line with Pc=6 (c) bifurcation with Pc=5 (d) termination with Pc= 7

After implementing the algorithm in Eclipse platform using javaCV library which is wrapper for openCV library the following image is obtained. Each dot in the image represents either a bifurcation or a termination of a rigid line. The image data provide the coordinate of all bifurcating or terminating points of the input fingerprint image. This paved the way for the recognition of the image as these are the required features of an fingerprint image.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

17

(a)

(b)

Fig 4.3 (a): thinned image (b): Extracted features

5. Minutiae Matching 5.1. Matching Based on distance

The coordinate values are obtained for minutiae points. The distance between the minutiae points are calculated and stored. The coordinates and distance of minutiae point of database image are also generated and matching is found on comparing minutiae points on coordinate value and distance.

5.2. Correlation Matching

After finding the matching for coordinates and distance between with them, the minutiae are verified by overlapping the two set of minutiae and again comparing the overlapped image with the template minutiae to find whether difference exist between images. If there is no difference in the image the fingerprint is said to be matched otherwise the fingerprints are non matching

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application Flow Chart of System

18

The Images are matched with each and every images in the database until a matching is found or matched with all images in database if there does not exist a matching image.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

19

6. RESULT AND ANALYSIS

6.1.INTRODUCTION

Several techniques are there for matching fingerprints Minutiae points. Computation of these minutiae points requires several tasks like calculating distance between points, finding angle between ridges, finding match for images with different orientation. Since the images of fingerprint is often poor quality the preprocessing of the images highly challenging to obtain clear image fingerprint which tend to loss features or obtain spurious minutiae. In the process of minutiae extraction many spurious minutiae gets extracted dealing with this problem is another challenging task The project developed is for clear fingerprint images of same size and orientation. With the clear and identical images the matching works accurately.

6.2. FINGERPRINT MATCHING RESULTS

Test case I : Image of low quality The image got enhanced only 10%, thinning of image and minutiae extracted was less accurate Test case II: Image of good quality The image got enhanced much better. Thinning of image was accurate. Minutiae extracted was 75% accurate. Test case III: Matching Similar Images The images matched are similar but less varying in size. The match result was only 50% accurate

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application Test case IV: Matching Identical Images

20

The images matched are identical and the result of match was 90% accurate Test case V: Finding Matching Image in the database 1 . The query image was identical to one of the image in the database and result obtained is matched image. 2. The query image was not present in the database. The result obtained was no match found.

7. CONCLUSION

The project Fingerprint Identification Application is developed for finding fingerprint match between two images. The application works well for identical images. The methods used in the project for processing fingerprint images are Image Enhancement, Binarization, Thinning,Minutiae extract using 3x3 window image for convolution, Minutiae matching on distance between features. The application works well for images of good quality and same orientation and size.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

21

8. FUTURE ENHANCEMENT
The proposed system works well on the images of good quality and minutiae matching are done on distance based method and correlation based method. The method used for minutiae extraction generates spurious minutiae. The application can be made to work on images of low quality by improving the image and accuracy on minutiae extraction can be made much accurate to eliminate spurious minutiae, minutiae matching techniques can be made finding angle between points. The fingerprint images captured may often vary in their orientation so application can be made match identical images in different orientation.

PES Institute of Technology

Department of MCA

2012-2013

Fingerprint Identification Application

22

9. BIBLOGRAPHY
[1] Bebis, G., Deaconu, T., Georgiopaulos, M., 1999. Fingerprint Identification using Delaunay Triangulation. IEEE Transactions on Information Intelligence and Systems, 452459. [2] Jain A, Hong L, Bolle R. On-line fingerprint verification. IEEE Transactions on Pattern Analysis and Machine Intelligence 1997;19:30214. [3] D.K. Isenor, S.G. Zaky, Fingerprint identification using graph matching, Pattern Recognition 19 (2) (1986) 113122. [4] A.K. Hrechak, J.A. McHugh, Automated fingerprint recognition using structural matching, Pattern Recognition 23 (1990) 893904.
BOOKS: Digital Image Processing Computer Vision For Visual Effects Authors: Rafael C. Gonzales and Richard E. Woods Richard J. RADKE

ONLINE RESOURCES: www.google.com http://stackoverflow.com www.en.wikipedia.org

PES Institute of Technology

Department of MCA

2012-2013