FINGERPRINT BASED ATTENDANCE SYSTEM

Transcription

1 FINGERPRINT BASED ATTENDANCE SYSTEM PROF. MEGHA.A.PATIL Assistant Professor Department of Electronics and Communication Engineering BLDEA s V P.Dr P.G.Halakatti college of Engineering and Technology Vijayapur Karnataka, India Shweta_agp@yahoo.co.in Abstract Managing staff attendance during working days has become a difficult challenge. The ability to compute the attendance percentage becomes a major task as manual computation produces errors, and also wastes a lot of time. For the stated reason, an efficient attendance management system using biometrics is designed. This system takes attendance electronically with the help of a finger print device and the records of the attendance are stored in a database. Attendance is marked after staff identification.for student identification, a biometric (fingerprint) identification based system is used. This process however, eliminates the need for stationary materials and personnel for the keeping of records. Eighty candidates were used to test the system and success rate of 94% was recorded. The manual attendance system average execution time for eighty students was seconds while it was 3.79 seconds for the automatic attendance management system using biometrics. The results showed improved performance over manual attendance management system. Attendance is marked after staff identification. (Keywords: fingerprints, attendance, enrollment, authentication, identification) I INTRODUCTION In an increasingly digital world, reliable personal authentication has become an important human computer interface activity. National security, e-commerce, and access to computer networks are some examples where establishing a person s identity is vital. Existing security measures rely on knowledge-based approaches like passwords or token-based approaches such as swipe cards and passports to control access to physical and virtual spaces. Though ubiquitous, such methods are not very secure. Tokens such as badges and access cards may be shared or stolen. Passwords and PIN numbers may be stolen electronically. Furthermore, they cannot differentiate between authorized user and a person having access to the tokens or knowledge. Biometrics such as fingerprint, face and voice print offers means of reliable personal authentication that can address these problems and is gaining citizen and government acceptance. 1.1 Biometrics Biometrics is the science of verifying the identity of an individual through physiological measurements or behavioral traits[1][2]. Since biometric identifiers are associated permanently with the user they are more reliable than token or knowledge based authentication methods. Biometrics offers several advantages over traditional security measures. These include a. Non-repudiation:[1] With token and password based approaches, the perpetrator can always deny committing the crime pleading that his/her password or ID was stolen or compromised even when confronted with an electronic audit trail. There is no way in which his claim can be verified effectively. This is known as the problem of deniability or of repudiation. However, biometrics is indefinitely associated with a user and hence it cannot be lent or stolen making such repudiation infeasible. b. Accuracy and Security: [1]Password based systems are prone to dictionary and brute force attacks. Furthermore, such systems are as vulnerable as their weakest password. On the other hand, biometric authentication requires the physical presence of the user and therefore cannot be circumvented through a dictionary or brute force style attack. Biometrics has also been shown to possess a higher bit strength compared to password based systems and is therefore inherently secure. c. Screening: In screening applications[2], we are interested in preventing the users from assuming multiple identities (e.g. a terrorist using multiple passports to enter a foreign 3 country). This requires that we ensure a person has not already enrolled under another assumed identity before adding his new record into the database. Such screening is not possible using traditional authentication mechanisms and biometrics provides the only available solution. The various biometric modalities can be broadly categorized as Physical biometrics: This involves some form of physical measurement and includes modalities such as face, fingerprints, iris-scans, hand geometry etc. Behavioral biometrics: These are usually temporal in nature and involve measuring the way in which a user performs certain tasks. This includes modalities such as speech, signature, gait, keystroke dynamics etc. 902

2 Chemical biometrics: This is still a nascent field and involves measuring chemical cues such as odor and the chemical composition of human perspiration. It is also instructive to compare the relative merits and demerits of biometric and password/cryptographic key based systems. Table 1.1 provides a summary of them. Depending on the application, biometrics can be used for identification or for verification. In verification, the biometric is used to validate the claim made by the individual. The biometric of the user is compared with the biometric of the claimed individual in the database. The claim is rejected or accepted based on the match. (In essence, the system tries to answer the question, Am I whom I claim to be? ). In identification, the system recognizes an individual by comparing his biometrics with every record in the database. Table1.1: Comparison of Biometric and Password/Key based authentication[12]. Biometrics Authentication Password/Key based authentication Based on physiological Based on something that the measurements or behavioral use has or knows traits Authenticates the user Authenticates the password/key Is permanently associated with the user Can be lent, lost or stolen Biometric templates have Have zero uncertainty high uncertainty Utilizes probabilistic matching 1.2 Biometrics and Pattern Recognition Requires exact match for authentication As recently as a decade ago, biometrics did not exist as a separate field. It has evolved through interaction and confluence of several fields. Fingerprint recognition[3] emerged from the application of pattern recognition to forensics. Speaker verification evolved out of the signal processing community. Face detection and recognition was largely researched by the computer vision community. While biometrics is primarily considered as application of pattern recognition techniques, it has several outstanding differences from conventional classification problems as enumerated below: 1. In a conventional pattern classification problem such as Optical Character Recognition (OCR) recognition, the number of patterns to classify is small (A-Z) compared to the number of samples available for each class. However in case of biometric recognition, the number of classes is as large as the set of individuals in the database. Moreover, it is very common that only a single template is registered per user. 2. The primary task in biometric recognition is that of choosing a proper feature representation. Once the features are carefully chosen, the act of performing verification is fairly straightforward and commonly employs simple metrics such as Euclidean distance. Hence the most challenging aspects of biometric identification involve signal and image processing for feature extraction. 3. Since biometric templates represent personally identifiable information of individuals, security and privacy of the data is of particular importance unlike other applications of pattern recognition. 4. Modalities such as fingerprints, where the template is expressed as an unordered point set (minutiae) do not fall under the category of traditional multivariate/vectorial features commonly used in pattern recognition. 1.3 Fingerprints as Biometric Fingerprints were accepted formally[1] as valid personal identifier in the early twentieth century and have since then become a de-facto authentication technique in law-enforcement agencies worldwide. The FBI currently maintains more than 400 million fingerprint records on file. Fingerprints have several advantages over other biometrics, such as the following: 1. High universality: A large majority of the human population has legible fingerprints and can therefore be easily authenticated. This exceeds the extent of the population who possess passports, ID cards or any other form of tokens. 2. High distinctiveness: Even identical twins who share the same DNA have been shown to have different fingerprints, since the ridge structure on the finger is not encoded in the genes of an individual. Thus, fingerprints represent a stronger authentication mechanism than DNA. Furthermore, there has been no evidence of identical fingerprints in more than a century of forensic practice. There are also mathematical models that justify the high distinctiveness of fingerprint patterns. 3. High permanence: The ridge patterns on the surface of the finger are formed in the womb and remain invariant until death except in the case of severe burns or deep physical injuries. 4. Easy collectability: The process of collecting fingerprints has become very easy with the advent of online sensors. These sensors are capable of capturing high resolution images of the finger surface within a matter of seconds. This process requires minimal or no user training and can be collected easily from co-operative or non co-operative users. In contrast, other accurate modalities like iris recognition require very co-operative users and have considerable learning curve in using the identification system. 903

3 5. High performance: Fingerprints remain one of the most accurate biometric modalities available to date with jointly optimal FAR (false accept rate) and FRR false reject rate). Forensic systems are currently capable of achieving FAR of less than Wide acceptability: While a minority of the user population is reluctant to give their fingerprints due to the association with criminal and forensic fingerprint databases, it is by far the most widely used modality for biometric authentication. A fingerprint is the feature pattern of one finger (Figure 1.1). It is believed with strong evidences that each fingerprint is unique. Each person has his own fingerprints with the permanent uniqueness. So fingerprints have being used for identification and forensic investigation for a long time. Fig 1.1 A fingerprint image acquired by an Optical Sensor A fingerprint is composed of many ridges and furrows. These ridges and furrows present good similarities in each small local window, like parallelism and average width. However, shown by intensive research on fingerprint recognition, fingerprints are not distinguished by their ridges and furrows, but by Minutia, which are some abnormal points on the ridges (Figure 1.2). Among the variety of minutia types reported in literatures, two are mostly significant and in heavy usage: one is called termination, which is the immediate ending of a ridge; the other is called bifurcation, which is the point on the ridge from which two branches derive. business and government organizations. Because biometric identifiers cannot be easily misplaced, forged, or shared, they are considered more reliable for person recognition than traditional token- or knowledge-based methods. The objectives of biometric recognition are user convenience, better security (e.g., difficult to forge access), and higher efficiency. The tremendous success of fingerprint based recognition technology in law enforcement applications, decreasing cost of fingerprint sensing devices, increasing availability of inexpensive computing power, and growing identity fraud/theft have all ushered in an era of fingerprintbased person recognition applications in commercial, civilian, and financial domains. There is a popular misconception in the pattern recognition and image processing academic community that automatic fingerprint recognition is a fully solved problem in as much as it was one of the first applications of machine pattern recognition almost fifty years ago. On the contrary, fingerprint recognition is still a challenging and important pattern recognition problem. 1.4 History of Fingerprints Human fingerprints have been discovered on a large number of archaeological artifacts and historical items. Although these findings provide evidence to show that ancient people were aware of the individuality of fingerprints, such awareness does not appear to have any scientific basis (Lee and Gaensslen (2001) and Moenssens (1971)). It was not until the late sixteenth century that the modern scientific fingerprint technique was first initiated (see Cummins and Midlo (1961), Galton (1892), and Lee and Gaensslen (2001)). [2][3]. Fig 1.2 Minutia.[2] (Valley is also referred as Furrow, Termination also called Ending, and Bifurcation is also called Branch) Fingerprinting has been around for a long period of time. Police departments have been using fingerprinting to identify criminals. The advancement in technology has allowed for the digitizing of fingerprints. There are devices that emulate the methods of the police by matching minutiae the ridges and swirls on the bottom of a person s finger. Is this person authorized to enter this facility? Is this individual entitled to access privileged information? Is the given service being administered exclusively to the enrolled users? Answers to questions such as these are valuable to Fig 1.3 Archeological finger prints Fig 1.3 gives examples of archaeological fingerprint carvings and historic fingerprint impressions: a) Neolithic carvings b) standing stone c) a Chinese clay seal (300 B.C.) d) an impression on a Palestinian lam(400 A.D.) Fingerprint recognition problem can be grouped into two subdomains: one is fingerprint verification and the other is fingerprint identification (Figure 1.1.2). In addition, different from the manual approach for fingerprint recognition by experts, the fingerprint recognition here is referred as AFRS (Automatic Fingerprint Recognition System), which is program-based. 904

4 Fig 1.4 Verification vs. Identification Fingerprint verification is to verify the authenticity of one person by his fingerprint. The user provides his fingerprint together with his identity information like his ID number. The fingerprint verification system retrieves the fingerprint template according to the ID number and matches the template with the real-time acquired fingerprint from the user. Usually it is the underlying design principle of AFAS (Automatic Fingerprint Authentication System). Fingerprint identification is to specify one person s identity by his fingerprint(s). Without knowledge of the person s identity, the fingerprint identification system tries to match his fingerprint(s) with those in the whole fingerprint database. It is especially useful for criminal investigation cases. And it is the design principle of AFIS (Automatic Fingerprint Identification System). However, all fingerprint recognition problems, either verification or identification, are ultimately based on a welldefined representation of a fingerprint. As long as the representation of fingerprints remains the uniqueness and keeps simple, the fingerprint matching, either for the 1-to-1 verification case or 1-to-m identification case, is straightforward and easy. Two representation forms for fingerprints separate the two approaches for fingerprint recognition. The first approach, which is minutia-based, represents the fingerprint by its local features, like terminations and bifurcations. This approach has been intensively studied, also is the backbone of the current available fingerprint recognition products. We concentrate on this approach in our project. The second approach, which uses image-based methods [6][7], tries to do matching based on the global features of a whole fingerprint image. It is an advanced and newly emerging method for fingerprint recognition. And it is useful to solve some intractable problems of the first approach. But my project does not aim at this method, so further study in this direction is not expanded in my thesis. 1.5 Biometric Systems A biometric system[1] is essentially a pattern recognition system that recognizes a person by determining the authenticity of a specific physiological and/or behavioral characteristic possessed by that person. An important issue in designing a practical biometric system is to determine how an individual is recognized. Depending on the application context, a biometric system may be called either a verification system or an identification system: A verification system authenticates a person s identity by comparing the captured biometric characteristic with her own biometric template(s) pre-stored in the system. It conducts one-to-one comparison to determine whether the identity claimed by the individual is true. A verification system either rejects or accepts the submitted claim of identity (Am I whom I claim I am?). An identification system recognizes an individual by searching the entire template database for a match. It conducts one-to-many comparisons to establish the identity of the individual. In an identification system, the system establishes a subject s identity (or fails if the subject is not enrolled in the system database) without the subject having to claim an identity (Who am I?). The term authentication is also frequently used in the biometric field, sometimes as a synonym for verification; actually, in the information technology language, authenticating a user means to let the system know the user identity regardless of the mode (verification or identification). Throughout this book we use the generic term recognition where we are not interested in distinguishing between verification and identification. The block diagrams of a verification system and an identification system are depicted in Figure 1.5; user enrollment, which is common to both tasks is also graphically illustrated. The enrollment module is responsible for registering individuals in the biometric system database (system DB). During the enrollment phase, the biometric characteristic of an individual is first scanned by a biometric reader to produce a raw digital representation of the characteristic. A quality check is generally performed to ensure that the acquired sample can be reliably processed by successive stages. In order to facilitate matching, the raw digital representation is usually further processed by a feature extractor to generate a compact but expressive representation, called a template. Depending on the application, the template may be stored in the central database of the biometric system or be recorded on a magnetic card or smartcard issued to the individual. The verification task is responsible for verifying individuals at the point of access. During the operation phase, the user s name or PIN (Personal Identification Number) is entered through a keyboard (or a keypad); the biometric reader captures the characteristic of the individual to be recognized and converts it to a digital format, which is further processed by the feature extractor to produce a compact digital representation. The resulting representation is fed to the feature matcher, which compares it against the template of a single user (retrieved from the system DB based on the user s PIN). In the identification task, no PIN is provided and the system compares the representation of the input biometric against the templates of all the users in the system database; the output is either the identity of an enrolled user or an alert message such as user not identified. 905

5 Because identification in large databases is computationally expensive, classification and indexing techniques are often deployed to limit the number of templates that have to be matched against the input. These applications may be divided into the following groups: i) applications such as banking, electronic commerce, and access control, in which biometrics will replace or enforce the current token- or knowledge-based techniques and ii) applications such as welfare and immigration in which neither the token-based nor the knowledge-based techniques are currently being used. Two approaches for Fingerprint recognition Two representation forms for fingerprints separate the two approaches[4] for fingerprint recognition. The first approach, which is minutia-based, represents the fingerprint by its local features, like terminations and bifurcations. This approach has been intensively studied, also is the backbone of the current available fingerprint recognition products. I also concentrate on this approach in my honors project. The second approach, which uses image-based methods, tries to do matching based on the global features of a whole fingerprint image. It is an advanced and newly emerging method for fingerprint recognition. And it is useful to solve some intractable problems of the first approach. But my project does not aim at this method, so further study in this direction is not expanded in my thesis. 1.7 Applications of Fingerprint Recognition Systems Fingerprint recognition is a rapidly evolving technology that has been widely used in forensics such as criminal recognition and prison security, and has a very strong potential to be widely adopted in a broad range of civilian applications[5] Forensic Government Commercial Corpse identification, Criminal Investigation, Terrorist Identification, Parenthood Determination, Missing Children,etc National ID card, Correctional Facility, Driver s License Social Security, Welfare Disbursement, Border Control, Passport Control,etc Computer Network Logon, Electronic Data Security, E-Commerce, Internet Access, ATM, Credit Card, Physical Access Control, Cellular Phones, Personal Digital Assistant, Medical Records Management, Distance Learning, etc Table1.2 Most of the fingerprint recognition applications are divided here into three categories. Traditionally, forensic applications have used manual biometrics, government applications have used token-based systems, and commercial applications have used knowledgebased systems. Fingerprint recognition systems are now being increasingly used for all these sectors. Note that over one billion dollars in welfare benefits are annually claimed by double dipping welfare recipients in the United States alone. These applications may be divided into the following groups: i) applications such as banking, electronic commerce, and access control, in which biometrics will replace or enforce the current token- or knowledge-based techniques and ii) applications such as welfare and immigration in which neither the token-based nor the knowledge-based techniques are currently being used. Information system/computer network security, such as user authentication and access to databases via remote login, is one of the most important application areas for fingerprint recognition. It is expected that more and more information systems/computer networks will be secured with fingerprints with the rapid expansion of the Internet. Applications such as medical information systems, distance learning and e- publishing are already benefiting from deployment of such systems. Electronic commerce and electronic banking are also important and emerging application areas of biometrics due to the rapid progress in electronic transactions. These applications include electronic fund transfers, ATM security, check cashing, credit card security, smartcard security, on-line transactions, and so on. Currently, there are several large fingerprint security projects under development in these areas, including credit card security (MasterCard) and smartcard security (IBM and American Express). The physical access control market is currently dominated by token-based technology. However, it is increasingly shifting to fingerprintbased biometric techniques. The introduction of fingerprintbased biometrics in government benefits distribution programs such as welfare disbursement has already resulted in substantial savings in deterring multiple claimants. In addition, customs and immigration initiatives such as the INS Passenger Accelerated Service System (INSPASS) which permits faster immigration procedures based on hand geometry will greatly increase operational efficiency. Fingerprint-based national ID (Aadhar) systems provide a unique ID to the citizens and integrate different government services. Fingerprint-based voter and driver registration provides registration facilities for voters and drivers. Fingerprint-based time/attendance monitoring systems can be used to prevent any abuses of the current token based/ manual systems. Fingerprint-based recognition systems will replace passwords and tokens in a large number of applications. Their use will increasingly reduce identity theft and fraud and protect privacy. As 906

6 fingerprint technology matures, there will be increasing interaction among market, technology, and applications. The emerging interaction is expected to be influenced by the added value of the technology, the sensitivities of the user population, and the credibility of the service provider. It is too early to predict where and how fingerprint technology would evolve and be mated with which applications, but it is certain that fingerprint-based recognition will have a profound influence on the way we will conduct our daily business. II LITERATURE SURVEY In the field of fingerprint identification, different types of work have been done so far. We had gone through various research papers, the work done till today and the methods used in each work are shown under this section Fast Fourier Transform and Gabor Filters The paper [18] uses a combination of two algorithms, the Fast Fourier Transform and gabor Filters to enhance and reconstruct the image s information. The system consists of eight steps: Acquisition, Noise reduction and enhancement with gabor filters. Enhancement with Fast Fourier Transform, Binarization, Thinning, Minutia detection and recognition. This is used to enhance and reconstruct the information of the finger print image as well as to extract two fundamental types of minutiae, ending points and bifurcations. Finally the extracted features are used to perform the fingerprint recognition. In this method the image is divided into small processing blocks and then fourier transform is performed. Minutiae-Based Algorithms Using CLAHE Histogram equalization is a general process used to enhance the contrast of images by transforming its intensity values. As a secondary result, it can amplify the noise producing worse results than the original image for certain fingerprints. Therefore, instead of using the histogram equalization which affects the whole image,[17] uses CLAHE (contrast limited adaptive histogram equalization) which is applied to enhance the contrast of small tiles and to combine the neighboring tiles in an image by using bilinear interpolation, which eliminates the artificially induced boundaries. In addition, the 'Clip Limit' factor is applied to avoid over-saturation of the image specifically in homogeneous areas that present high peaks in the histogram of certain image tiles due to many pixels falling inside the same gray level range. Additionally, a combination of filters in both domains, spatial and Fourier is used to obtain a proper enhanced image. Segmentation Algorithm [20] Proposed an algorithm for segmentation that employs feature dots, which are then used to obtain a close segmentation curve. The authors claim that their method surpasses directional field and orientation based methods Segmentation is one of the first and most integral preprocessing steps for any fingerprint verification and it determines the result of fingerprint analysis and recognition. Segmentation refers to the separation of finer print area from the image background. A good segmentation method should have the following characteristics: 1. It should be insensitive to image contrast. 2.It should detect the smudged or noisy regions. 3.It should be independent of the image quality. Thinning Algorithm The paper [19] uses a modified thinning algorithm is that can be used to thin any symbol, Characters and also fingerprint images regardless of their shape and orientation. Usually in fingerprint images, Thinning seen as a preprocess for minutiae extraction. The Proposed algorithm identifies the unrecoverable corrupted areas in the fingerprint and does not thin them; this is an important advantage of the proposed method because such corrupted areas are extremely harmful to the extraction of minutiae points. Moreover, this advantage helps remove the spurious minutiae points which are harmful to fingerprint matching. III REQUIREMENTS ANALYSIS Software requirements Operating System - Windows XP/7 Tool MATLAB R2010b Visual basic 2008 SQL server Hardware Requirements PC with Processor - Pentium 4 or Higher PC RAM 2 GB or Higher Hard Disk Drive 40GB or Higher Fingerprint scanner IV PROPOSED SYSTEM 4.1 System Overview The proposed system provides solution to lecture attendance problems through the use of attendance management software that is interfaced to a fingerprint device. The staff bio-data (Matriculation number, Name, Gender and Date of Birth) and the fingerprint are enrolled first into the database. The fingerprint is captured using a fingerprint scanner device. For attendance, the staff places his/ her finger over the fingerprint device and the staff s matriculation number is sent to the database as having attended that particular working day. At the end of every month, reports are generated and sent to mail ids of all the staff. A simple architecture is shown below. Fingerprint input Fingerprint input Biometric sensor Biometric sensor Feature Extraction Feature Extraction Matching Database 907

7 Fig 4.1 General Architecture of a Biometric System 4.2 System Level Design An Automated Fingerprint Attendance System (AFAS) is a highly specialized system that records staff attendance by comparing a single fingerprint image with the fingerprint images previously stored in a database. The Automated Fingerprint Identification system (AFIS) is the principle behind the AFAS. The major factors in designing a fingerprint attendance system include: choosing the hardware and software components and integrating both to work together, defining the system working mode (verification or identification), dealing with poor quality images and other programming language exception, and defining administration and optimization policy [5],[9]. Staff attendance system framework is divided into three parts: Hardware design, Software design, Attendance Management Approach and Report Generation. A fingerprint recognition system constitutes of fingerprint acquiring device, minutia extractor and minutia matcher [Figure 4.2]. Fig 4.3 Fingerprint Device. Software The software architecture consists of: the database and the application program:- Database: The database consists of tables that stores records implemented in Microsoft SQL Server database. However, this can be migrated to any other relational database of choice. SQL Server is fast and easy, it can store a very large record and requires little configuration. Application Program: The application program used is MATLAB. V FINGERPRINT IMAGE PREPROCESSING Fig 4.2 Simplified Fingerprint Recognition System For fingerprint acquisition, optical or semi-conduct sensors are widely used. They have high efficiency and acceptable accuracy except for some cases that the user s finger is too dirty or dry. However, the testing database for my project is from the available fingerprints provided by FVC2002 (Fingerprint Verification Competition 2002). So no acquisition stage is implemented. The minutia extractor and minutia matcher modules are explained in detail in the next part for algorithm design and other subsequent sections. Hardware The hardware to be used can be divided into two categories fingerprint scanner which captures the image and a personal computer which: houses the database, runs the comparison algorithm and simulates the application function. The fingerprint scanner is connected to the computer via its USB interface. Basically this work does not involve the development of hardware. Using the Secugen Fingerprint Reader, the GrFinger Software Development Kit (SDK) toolbox provided by the Griaule (will explain the detail) can be used as an interface between the fingerprint reader and the attendance software. 5.1 Fingerprint Image Enhancement Fingerprint Image enhancement[16][17] is to make the image clearer for easy further operations. Since the fingerprint images acquired from sensors or other medias are not assured with perfect quality, those enhancement methods, for increasing the contrast between ridges and furrows and for connecting the false broken points of ridges due to insufficient amount of ink, are very useful for keep a higher accuracy to fingerprint recognition. Two Methods are adopted in my fingerprint recognition system: the first one is Histogram Equalization; the next one is Fourier Transform Histogram Equalization Histogram equalization[17] is to expand the pixel value distribution of an image so as to increase the perceptional information. The original histogram of a fingerprint image has the bimodal type [Figure 5.1], the histogram after the histogram equalization occupies all the range from 0 to 255 and the visualization effect is enhanced [Figure 5.2]. Figure the Original histogram of a fingerprint image Figure Histogram after the Histogram Equalization 908

8 The right side of the following figure [Figure 5.3] is the output after the histogram equalization. Fig 5.3 Histogram Enhancement.Original Image (Left). Enhanced image (Right) Fingerprint Enhancement by Fourier Transform We divide the image into small processing block s (32 by 32 pixels) and perform the Fourier transform[16] according to: F(u,v)= + )} For u = 0, 1, 2,..., 31 and v = 0, 1, 2,..., 31. In order to enhance a specific block by its dominant frequencies, we multiply the FFT of the block by its magnitude a set of times. Where the magnitude of the original FFT = abs(f(u,v)) = F(u,v). Get the enhanced block according to ˆk} (2) where F -1 (F(u,v)) is done by F(u,v)= )} (3) for x = 0, 1, 2,..., 31 and y = 0, 1, 2,..., 31. The k in formula (2) is an experimentally determined constant, which we choose k=0.45 to calculate. While having a higher "k" improves the appearance of the ridges, filling up small holes in ridges, having too high a "k" can result in false joining of ridges. Thus a termination might become a bifurcation. Figure 5.4 presents the image after FFT enhancement. Fig 5.4 Fingerprint enhancements by FFT Enhanced image (left), Original image (right) + The enhanced image after FFT has the improvements to connect some falsely broken points on ridges and to remove some spurious connections between ridges. The shown image at the left side of figure 5.4 is also processed with histogram equalization after the FFT transform. The side effect of each block is obvious but it has no harm to the further operations because I find the image after consecutive binarization operation is pretty good as long as the side effect is not too severe. 5.2 Fingerprint Image Binarization Fingerprint Image Binarization[16] is to transform the 8-bit Gray fingerprint image to a 1-bit image with 0-value for ridges and 1-value for furrows. After the operation, ridges in the fingerprint are highlighted with black color while furrows are white. A locally adaptive binarization method is performed to binarize the fingerprint image. Such a named method comes from the mechanism of transforming a pixel value to 1 if the value is larger than the mean intensity value of the current block (16x16) to which the pixel belongs [Figure 5.5]. Fig 5.5 The Fingerprint image after adaptive binarization, Binarized image(left), Enhanced gray image(right) 5.3 Fingerprint Image Segmentation In general, only a Region of Interest (ROI) is useful to be recognized for each fingerprint image. The image area without effective ridges and furrows is first discarded since it only holds background information. Then the bound of the remaining effective area is sketched out since the minutia in the bound region is confusing with those spurious minutias that are generated when the ridges are out of the sensor. To extract the ROI, a two-step method is used. The first step is block direction estimation and direction variety check [15], while the second is intrigued from some Morphological methods. Block direction estimation 1.1 Estimate the block direction for each block of the fingerprint image with WxW in size(w is 16 pixels by default). The algorithm is: I. Calculate the gradient values along x-direction (g x ) and y-direction (g y ) for each pixel of the block. Two Sobel filters are used to fulfill the task. II. For each block, use following formula to get the Least Square approximation of the block direction. tg2ß = 2 (gx*gy)/(gx 2 -gy 2 ) for all the pixels in each block. The formula is easy to understand by regarding gradient values along x-direction and y-direction as cosine value and 909

9 sine value. So the tangent value of the block direction is estimated nearly the same as the way illustrated by the following formula. tg2= 2sincos/(cos2 -sin2 ) 1.2 After finished with the estimation of each block direction, those blocks without significant information on ridges and furrows are discarded based on the following formulas: E = {2 (gx*gy)+(gx 2 -gy 2 )}/W*W*(gx 2 +gy 2 ) For each block, if its certainty level E is below a threshold, then the block is regarded as a background block. The direction map is shown in the following diagram. We assume there is only one fingerprint in each image. Fig 5.6 Direction map. Binarized fingerprint (left), Direction map (right) ROI extraction by Morphological operations Two Morphological operations called OPEN and CLOSE are adopted[15]. The OPEN operation can expand images and remove peaks introduced by background noise [Figure 5.7]. The CLOSE operation can shrink images and eliminate small cavities [Figure 5.8]. Figure 5.7,5.8,5.9,5.10 show the interest fingerprint image area and its bound. The bound is the subtraction of the closed area from the opened area. Then the algorithm throws away those leftmost, rightmost, uppermost and bottommost blocks out of the bound so as to get the tightly bounded region just containing the bound and inner area Fig 5.9 After open operation Fig5.9 ROI+Bound VI MINUTIA EXTRACTION 6.1 Fingerprint Ridge Thinning Ridge Thinning is to eliminate the redundant pixels of ridges till the ridges are just one pixel wide. [12] [14]uses an iterative, parallel thinning algorithm. In each scan of the full fingerprint image, the algorithm marks down redundant pixels in each small image window (3x3). And finally removes all those marked pixels after several scans. In my testing, such an iterative, parallel thinning algorithm has bad efficiency although it can get an ideal thinned ridge map after enough scans. [2] uses one-in-all method to extract thinned ridges from gray-level fingerprint images directly. Their method traces along the ridges having maximum gray intensity value. However, binarization is implicitly enforced since only pixels with maximum gray intensity value are remained. Also in my testing, the advancement of each trace step still has large computation complexity although it does not require the movement of pixel by pixel as in other thinning algorithms. Thus the third method is bid out which uses the built-in Morphological thinning function in MATLAB. 6.2 Minutia Marking After the fingerprint ridge thinning, marking minutia points is relatively easy. But it is still not a trivial task as most literatures declared because at least one special case evokes my caution during the minutia marking stage. In general, for each 3x3 window, if the central pixel is 1 and has exactly 3 one-value neighbors, then the central pixel is a ridge branch [Figure 4.2.1]. If the central pixel is 1 and has only 1 one-value neighbor, then the central pixel is a ridge ending[14] [Figure4.2.2]. Fig 6.1: Bifurcation Fig 6.2: Termination Fig 5.7 Original Image Area Fig 5.8 After close operation Figure 6.3 Triple counting branches 910

10 Figure 6.3 illustrates a special case that a genuine branch is triple counted. Suppose both the uppermost pixel with value 1 and the rightmost pixel with value 1 have another neighbor outside the 3x3 window, so the two pixels will be marked as branches too. But actually only one branch is located in the small region. So a check routine requiring that none of the neighbors of a branch are branches is added. Also the average inter-ridge width D is estimated at this stage. The average inter-ridge width refers to the average distance between two neighboring ridges. The way to approximate the D value is simple. Scan a row of the thinned ridge image and sum up all pixels in the row whose value is one. Then divide the row length with the above summation to get an inter-ridge width. For more accuracy, such kind of row scan is performed upon several other rows and column scans are also conducted, finally all the inter-ridge widths are averaged to get the D. Together with the minutia marking, all thinned ridges in the fingerprint image are labeled with a unique ID for further operation. The labeling operation is realized by using the Morphological operation: BWLABEL. VII MINUTIA MATCH Given two set of minutia of two fingerprint images, the minutia match algorithm determines whether the two minutia sets are from the same finger or not. An alignment-based match algorithm partially derived from the [1] is used in my project. It includes two consecutive stages: one is alignment stage and the second is match stage. 1. Alignment stage. Given two fingerprint images to be matched, choose any one minutia from each image; calculate the similarity of the two ridges associated with the two referenced minutia points. If the similarity is larger than a threshold, transform each set of minutia to a new coordination system whose origin is at the referenced point and whose x-axis is coincident with the direction of the referenced point. 2. Match stage: After we get two set of transformed minutia points, we use the elastic match algorithm to count the matched minutia pairs by assuming two minutia having nearly the same position and direction are identical. 7.1 Alignment Stage 1. The ridge associated with each minutia is represented as a series of x-coordinates (x 1, x 2 x n ) of the points on the ridge. A point is sampled per ridge length L starting from the minutia point, where the L is the average inter-ridge length. And n is set to 10 unless the total ridge length is less than 10*L. So the similarity of correlating the two ridges is derived from: S = m i=0x i X i /[ m i=0x i 2 X i 2 ]^0.5, where(x i~ x n ) and (X i~ X N ) are the set of minutia for each fingerprint image respectively. And m is minimal one of the n and N value. If the similarity score is larger than 0.8, then go to step 2, otherwise continue to match the next pair of ridges. 2. For each fingerprint, translate and rotate all other minutia with respect to the reference minutia according to the following formula: xi_new yi_new i_new =TM * ( xi x) ( yi y ) where (x,y,) is the parameters of the reference minutia, and TM is TM = cos sin 0 sin cos 0 Fig 7.1: the effect of translation and rotation The new coordinate system is originated at minutia F and the new x-axis is coincident with the direction of minutia F. No scaling effect is taken into account by assuming two fingerprints from the same finger have nearly the same size.my method to align two fingerprints is almost the same with the one used by [1] but is different at step 2. Lin s method uses the rotation angle calculated from all the sparsely sampled ridge points. My method use the rotation angle calculated earlier by densely tracing a short ridge start from the minutia with length D. Since I have already got the minutia direction at the minutia extraction stage, obviously my method reduces the redundant calculation but still holds the accuracy. Also Lin s way to do transformation is to directly align one fingerprint image to another according to the discrepancy of the reference minutia pair. But it still requires a transform to the polar coordinate system for each image at the next minutia match stage. My approach is to transform each according to its own reference minutia and then do match in a unified x-y coordinate. Therefore, less computation workload is achieved through my method. 7.2 Match Stage The matching algorithm for the aligned minutia patterns needs to be elastic since the strict match requiring that all parameters (x, y, ) are the same for two identical minutia is impossible due to the slight deformations and inexact quantizations of minutia. My approach to elastically match minutia is achieved by placing a bounding box around each template minutia. If the minutia to be matched is within the rectangle box and the direction discrepancy between them is very small, then the two minutia are regarded as a matched minutia pair. Each i, 911

11 minutia in the template image either has no matched minutia or hasonly one corresponding minutia. The final match ratio for two fingerprints is the number of total matched pair over the number of minutia of the template fingerprint. The score is 100*ratio and ranges from 0 to 100. If the score is larger than a pre-specified threshold, the two fingerprints are from the same finger. However, the elastic match algorithm has large computation complexity and is vulnerable to spurious minutia. USER MANUAL VIII IMPLEMENTATION Figure M.3 After Histogram Equalization. The image on the left side is the original fingerprint. 1. Type command start_gui_single_mode in MATLAB Figure M.1 the User Interface of the Fingerprint Recognition System. The series of buttons on the left side will be invoked sequentially in the consequent demonstration. The two blank areas are used to show the fingerprint image before and after a transaction respectively. 2.Click Load Button The enhanced image after the Histogram Equalization is shown on the right side. 4. Click fft Button Figure M.2 Load a gray level fingerprint image from a drive specified by Users. Multiple formats are supported and the image size is not limited. But the fingerprint ridges should have large gray intensity comparing with the background and valleys. 3. Click his-equalization Button Figure M.4 Captured window after click FFT button. The pop-up dialog accepts the parameter k (please refer the formula 2). The experimental optimal k value is Users can fill any other constant in the dialog to get a 912

12 better performance. The enhanced image will be shown in the left screen box, which however is not shown here. 5. Click Binarization Button 6. Click Direction Button Figure M.10 the Fingerprint image after thining, H breaks removal, isolated peaks removal and spike removal.(right). 11. Click Extract Button 12. Click Real Minutia Button Figure M.5. Screen capture after binarization (left) and block direction estimation (right). 7. Click ROI Area Button Figure M.7 ROI extraction(right). The intermediate steps for all the morphological operations such close and open are not shown. The right screen box shows the final region of interest of the fingerprint image. The subsequent operations will only operate on the region of interest. Figure M.12 Minutia Marking (right) and False Minutia Removal (Left). Bifurcations are located with yellow crosses and terminations are denotes with red stars. And the genuine minutia (left) are labeled with orientations with green arrows. 13. Click Save Button 8. Click Thinning Button 9. Click Remove H breaks Button 10. Click Remove spikes Button Figure M.13 Save minutia to a text file. 913

13 The saved text file stores the information on all genuine minutia. The exact format of the files are explained in the source code. accuracy of the system is quantified in terms of false acceptance ratio (FAR) and the false rejection ratio (FRR). An FAR of 1% was obtained for an FRR of 8% for this database. 14. Click Match Button Table of FAR and FRR Number of inputs 100 FAR 1% 8% FRR image 1 image 2 image 3 image 4 image 5 Figure M.14 Load two minutia files and do matching. Users can open two minutia data files from the dialog invoked by clicking the Match button. The match algorithm will return a prompt of the match score. But be noted that matching in the GUI mode is not encouraged since the match algorithm relies on heavy computation. Unpredicted states will happen after a long irresponsive running time. Batch testing is prepared for testing match. Please refer the source files for batch testing. IX EXPERIMENTATION RESULTS 9.1 Evaluation Indexes for Fingerprint Recognition Two indexes are well accepted to determine the performance of a fingerprint recognition system: one is FRR (false rejection rate) and the other is FAR (false acceptance rate). For an image database, each sample is matched against the remaining samples of the same finger to compute the False Rejection Rate. If the matching g against h is performed, the symmetric one (i.e., h against g) is not executed to avoid correlation. All the scores for such matches are composed into a series of Correct Score. Also the first sample of each finger in the database is matched against the first sample of the remaining fingers to compute the False Acceptance Rate. If the matching g against h is performed, the symmetric one (i.e., h against g) is not executed to avoid correlation. All the scores from such matches are composed into a series of Incorrect Score. 9.2 Experimentation Results A fingerprint database from the FVC2000 (Fingerprint Verification Competition 2000) is used to test the experiment performance. My program tests all the images without any fine-tuning for the database. I have taken 100 inputs for checking the false accept rate and false reject rate. The Figure 9.1: Graph of image degradation v/s percentage of matching Above graph shows the degradation of single fingerprint v/s percentage of matching. 150% 100% 50% 0% Y-Values Figure9.2: graph of threshold value v/s system efficiency The above figure 9.2 shows graph of threshold values v/s the system efficiency. System will be more efficient at the threshold value image 1image 2image 3image 4image 5image 6 Figure9.3: graph of different fingerprint images v/s percentage of matching The above figure 9.3 shows the graph of different fingerprint images v/s percentage of matching. 914