REINFORCED FINGERPRINT MATCHING METHOD FOR AUTOMATED FINGERPRINT IDENTIFICATION SYSTEM 1 S.Asha, 2 T.Sabhanayagam 1 Lecturer, Department of Computer science and Engineering, Aarupadai veedu institute of technology, Chennai. asha_cse@yahoo.com 2 Asst.Professor(SG), Department of Software Engineering, SRM University, Kattankulathur, Chennai stsabha@gmail.com ABSTRACT Automated fingerprint identification is the process of automatically matching one or many unknown fingerprints against a database of known and unknown prints. To ensure the quality of AFI the finger print matching must be reliable and efficient. The proposed system for AFI consists of image acquisition, preprocessing, feature extraction and Matching.The proposed matching algorithm provides exact matching and also requires less storage and takes less time for matching. Keywords: Image enhancement; Minutiae; fingerprint. 1.1 What is A Fingerprint? A fingerprint is the feature pattern of one finger (Figure 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. 1. Introduction The biometrics is the automatic person identification claimed identity verification of an individual by using certain physiological or behavioral features associated with a given person. Traditionally, passwords (knowledge-based security) and ID cards (token-based security) have been used to access control to restricted systems or places. However, security can be easily breached in these systems when a password is divulged to an unauthorized user or a card is stolen. Furthermore, simple passwords are easy to guess by an impostor, while difficult passwords may be hard to recall a legitimate user. The emergence of biometrics technology has provided an attractive alternative to solve the problems still present in traditional verification methods. Fingerprints are fully formed during the first seven months of the fetus development and the finger ridge configurations do not change throughout the life of an individual except, due to accidents such as bruises and cuts on the fingertips [1], [2]. This property makes fingerprints a very attractive biometric identifier. Biological organisms, in general, are the consequence of the interaction of genes and environment. Figure1. 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 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.
Figure 2. Mitutia Termination and Bifurcation 1.2 What is Fingerprint Recognition? The biometrics is the automatic person identification claimed identity verification of an individual by using certain physiological or behavioral features associated with a given person. Traditionally, passwords (knowledge-based security) and ID cards (token-based security) have been used to access control to restricted systems or places. However, security can be easily breached in these systems when a password is divulged to an unauthorized user or a card is stolen. Furthermore, simple passwords are easy to guess by an impostor, while difficult passwords may be hard to recall a legitimate user. The emergence of biometrics technology has provided an attractive alternative to solve the problems still present in traditional verification methods. Fingerprints are fully formed during the first seven months of the fetus development and the finger ridge configurations do not change throughout the life of an individual except, due to accidents such as bruises and cuts on the fingertips [1], [2]. This property makes fingerprints a very attractive biometric identifier. Biological organisms, in general, are the consequence of the interaction of genes and environment [1]. The fingerprint recognition problem can be grouped into two sub-domains: one is fingerprint verification and the other is fingerprint identification. 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. Figure 3.Architecture of fingerprint Recognition 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). 2. Proposed Solution: The proposed solution consists of the following process for the implementation of Automated fingerprint identification image acquisition, preprocessing, feature extraction and Matching. 2.1 Pre processing. Pre processing is done in order to enhance the ridges and furrows in the finger print. Pre processing includes three steps Histogram Equalization, Image Binarization, ROI. 2.1.1 Histogram Equalization. Histogram equalization 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, the histogram after the histogram equalization occupies all the range from 0 to 255 and the visualization effect is enhanced. and sine value. So the tangent value of the block direction is estimated nearly the same as the way illustrated by the following formula. tg2 = 2sin cos /(cos2 -sin2 ) Figure 4 (a)original Histogram (b) After Histogram Equalization 2.1.2 Image Binarization. Image Binarization is a process which transforms the 8- bit Gray 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. Figure 6. Direction map 4.2 ROI(Region of Interest). ROI extraction is done using two Morphological operations called OPEN and CLOSE. The OPEN operation can expand images and remove peaks introduced by background noise The CLOSE operation can shrink images and eliminate small cavities. Figure 5. Image after Binarization 2.1.3 Block direction estimation. Estimate the block direction for each block of the fingerprint image with WxW in size(w is 16 pixels by default). The algorithm is: 1. 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. 2. 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. Figure 7. Region of Interest 3 Feature Extraction: The Feature extraction phase involves marking of minutia in the image by finding the ridge ending and ridge bifurcation. 3.1 Ridge Thinning. The final step in pre-processing is thinning before the extraction of minutiae. Thinning is a morphological operation that successively erodes away the foreground pixels until they are one pixel wide. The formula is easy to understand by regarding gradient values along x-direction and y-direction as cosine value
Figure 8. Image after ridge thining. 3.2 Minutiae extraction. Minutiae marking is now done using templates for each 3 x 3 pixel window as follows. 1. If the central pixel is 1 and has exactly 3 one-value neighbors, then the central pixel is a ridge branch. 2. If the central pixel is 1 and has only 1 one-value neighbor, then the central pixel is a ridge ending. earlier methods introduce some spurious minutia points in the image. So to keep the recognition system consistent these false minutiae need to be removed. The false minutiae is removed with the reference to [4].The inter ridge distance D is calculated to removed false minutiae as referred in[5]. Now the following 7 types of false minutia points are removed using these steps. Using the above Minutia Extraction process we get the Minutiae sets for the two fingerprints to be matched. Minutiae Matching process iteratively chooses any two minutiae as a reference minutia pair and then matches their associated ridges first. If the ridges match well, two fingerprint images are aligned and matching is conducted for all remaining minutia to generate a Match Score. Figure.9: Image after minutiae extraction 4. Post Processing: Figure.10. False minutiae remioval. 5.Minutiae Matching: 5.1 Constructing Minutia table. From the output of the minutiae extraction step, the proposed minutiae table is constructed as following: 1. The minutiae table is constructed by the minutiae Bifurcation and minutiae termination. 2. The table consist of two column the first column is taken as the minutiae bifurcation and named as m1,the second column is taken as minutiae termination and named as m2. 3. From the core point of the fingerprint the 20*20 pixel is taken to count the two types of minutiae and it is recorded in the minutiae table. 4. The minutiae table is created for all the samples of fingerprint and stored in the database as template. 5.2 Proposed minutiae matching algorithm. The post processing process is used to remove the false minutiae. 4.1 False minutiae removal. At this stage false ridge breaks due to insufficient amount of ink & ridge cross connections due to over inking are not totally eliminated. Also some of the 1. Get the fingerprint to be verified and the minutiae table T is obtained. 2. The threshold value of two minutiae type is obtained using histogram equalization. 3. All the minutiae table of claimed fingerprint is taken from the database and compared with the table T in order to get the geometric mean of two minutiae type. 4. The geometric mean is obtained by getting the total minutiae of all the samples.
5. If the geometric mean is les than threshold value of the claimed fingerprint then the user is genuine else it is rejected. 6.Experimental Result. 6.1 False Rejection Rate (FRR): For an image database, each sample is matched against the remaining samples of the same finger to compute the False Rejection Rate 6.2 False Acceptance Rate (FAR): 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. The average match time is calculated as the average CPU time taken by a single match operation between a template and a fingerprint image. Table 2. Match timing details Step Getting minutiae table 0.0011 Calculation of absolute difference Average time taken (sec) 0.0002 Comparing the mean 0.00004 Total match time 0.00134 7.Conclusion: Figure.11.FAR vs FRR The proposed feature extraction provides effective enhanced image for minutiae extraction. The proposed matching algorithm takes less time for matching is extremely small using our algorithm as all the process is taking geometric mean of absolute differences and requires only less space for storage. The algorithm provides matching ratio of 98%. 8.References: Table.1. Genuine Acceptance Rate(GAR),False Acceptance Rate(FAR) And False Rejection Rate(FRR). Genuine acceptance False rejection 93.82 3.18 0 92.25 4.75 0 92.23 4.7 0 33.21 1.2 0 6.3 Average match time. False acceptance [1] W. Badler, Dermatoglyphics: Science transition, vol 9,pp 95, 1991. [2] M. Kuchen, C. Newell, A Model for fingerprint formation, Europhys letters, vol. 68, No. 1, pp.141-147, 2004. [3] Yang, J. C., & Park, D. S. (2008). Fingerprint Verification Based on Invariant Moment Features and Nonlinear BPNN. International Journal of Control, Automation, and Systems, Vol. 6, No. 6, pp. 800-808 [4] Handbook of Fingerprint Recognition by Davide Maltoni, Dario Maio, Anil K. Jain & Salil Prabhakar. [5] Lu, H., Jiang, X, Yau Wei-Yun, Effective and Efficient Fingerprint Image Post processing, 7th International Conference on Control, Automation, Robotics and Vision (ICARCV), Vol. 2, 2002, pp. 985-989. [6] Paul, A.M.; Lourde, R.M, A Study on Image Enhancement Techniques for Fingerprint Identification, Video and Signal Based Surveillance, 2006. AVSS apos;06.ieeeinternational Conference,Vol.5, No.456, 2006, pp.16 20.