Investigating Multi-touch Gestures as a Novel Biometric Modality

Size: px
Start display at page:

Download "Investigating Multi-touch Gestures as a Novel Biometric Modality"

Transcription

1 Investigating Multi-touch Gestures as a Novel Biometric Modality Napa Sae-Bae, Nasir Memon, and Katherine Isbister Computer Science Department, NYU-Poly Six Metrotech Center, Brooklyn, NY, nsae-b01@students.poly.edu, isbister@poly.edu, memon@poly.edu Abstract We propose a new behavioral biometric modality based on multi-touch gestures. We define a canonical set of multitouch gestures based on the movement characteristics of the palm and fingertips being used to perform the gesture. We developed an algorithm to generate and verify multi-touch gesture templates. We tested our techniques on a set of 22 different gestures. Employing a matching algorithm for a multi-touch verification system with a k-nn classifier we achieved 1.28% Equal Error Rate (EER). With score-based classifiers where only the first five samples of a genuine subject were considered as templates, we achieved 4.46 % EER. Further, with the combination of three commonly used gestures: pinch, zoom, and rotate, using all five fingers, 1.58% EER was achieved using a score-based classifier. These results are encouraging and point to the possibility of touch based biometric systems in real world applications like user verification and active authentication. I. INTRODUCTION Since their introduction, multi-touch phones and tablets have grown exponentially. More then 60 million mobile devices with multi-touch capabilities are expected to ship in Multi-touch interfaces bring new capabilities to existing devices and enable their use in completely new contexts. Different low cost technologies allow them to be used as part of familiar surfaces such as fabric, paper, glass and blend in our daily lives. Soon, these prototypes currently viewed as novelties, will join mainstream multi-touch devices such as smartphones and tablets already in the market, as coffee tables in our living rooms, and desks in our offices. The attractive user interaction features and the tactile/visual experience provided by multi-touch interfaces, make them strong contenders for becoming the dominant human computer interface, possibly replacing the keyboard, mouse and stylus. Typically, there has been a correspondence between a user interface and biometric modalities, as the sensing mechanisms that underlie the interface can also be used to capture user characteristics. Past research, for example, has used keystroke dynamics and mouse movements as candidate biometric modalities. In this paper, we investigate the potential of multitouch gestures as a biometric modality. Prior research has shown that biometric data can be gleaned from physiological characteristics of hand geometry [1]. Research has also been done to show that behavioral biometric traits can be captured using hand drawn signatures [2], [3] using a pen or stylus. Our study in this paper shows that multi-touch gestures contain sufficient biometric information, resulting from variation in hand geometry and muscle behavior, to allow discrimination between users. Even though this paper studies multi-touch gestures on a personal tablet device, the techniques presented could be ported to multi-touch tabletops, wall displays, etc., where multiple users may share space in a dynamic context. The rest of the paper is organized as follows. First, related work is summarized in section 2. In section 3, we present a taxonomy of multi-touch gestures and identify a set of 22 gestures that we consider in this study. In section 4, we describe details of a classification algorithm for multi-touch gestures. In section 5 we present experimental results. In section 6, we conclude our study and discuss future work. II. RELATED WORK Biometric systems are an effective way to identify or authenticate users based on the something they are property. Based on the practicality and availability of input sensors, a large number of biometric systems have been proposed. The characteristics used in a biometric system are classified into two types: physiological and behavioral. Some examples of physiological traits include retina[4], iris[5], fingerprint[6], face[7], vein[8] and palm[9]. Some behavioral biometric traits include dynamic signature[2], [10], voice[11], and gait[12]. Many such traits have been well studied, and can potentially be employed for authentication once there are sensors available in end user devices. Some techniques, such as iris scans, require specialized sensors. For computing devices, which generally come equipped with a keyboard and mouse, a lot of research on keystroke and mouse dynamics has been performed [13], [14], [15]. One desirable characteristic of such biometric systems is they simultaneously capture physical as well as behavioral traits. Recently, Hamdy, et al[16], have proposed a novel mouse-based biometric system using a virtual keyboard. Their approach differs from previous work since their system homogeneously captures physiological and behavioral biometrics via mouse movement where the features are derived from physiological properties such as visual scan and detection, and short-term memory as well as a type of behavioral property called dynamic mouse movement. Motivated by a recent paradigm shift of user interface from the keyboard and mouse to a touch interface, we propose a novel touch-based biometric system using five finger multitouch gestures /12/$ IEEE 156

2 III. GESTURE TAXONOMY This paper explores the possibility of recognizing an individual based on physiological and behavioral biometric gleaned from hand geometry and muscle movement of five finger multi-touch gestures. Are multi-touch gestures sufficiently discriminative to provide biometric information? If yes, then what types of gestures can be used and which ones provide biometric distinguishability? Clearly not all multitouch gestures would be equally discriminative. For example a simple one finger drag gesture appears to contain less information about a user than a pinch or zoom gesture. In order to study these questions we first created a gestural taxonomy, based on movement of the two major components of the hand, the palm and the fingertips, as described below. 1) Palm movement: Some gestures involve placing one s hand in a static position for the entire gesture, whereas others require the hand to traverse while executing the gesture. Thus, we can divide gestures into two classes: Static palm: For examples, pinch or zoom gesture. Dynamic palm: For example, a drag or swipe gesture. 2) Fingertip movement: Most of the distinguishing features of multi-touch gestures derive from the movement of fingertips. We divide fingertip movement into four categories: Parallel: All fingertips are moving in the same direction during the gesture. For example, a five-finger swipe, in which all five fingers move from left to right. Close: All fingertips are moving inward toward the center of the hand. For example, a pinch gesture. Open: All fingertips are moving outward from the center of the hand. For example, a reverse pinch gesture. Circular: All fingertips are rotating around the center of the hand. For example, clockwise rotation. 3) Dynamic fingertips: In a gesture there may be one or more fingertips resting in a fixed position on the screen. This can help stabilize the gesture for the user. This yields an additional classification in our taxonomy. All fingertips moving: Example the pinch gesture. One or more fingertips resting: For example, resting a thumb while rotating the remaining fingers. The above classification results in a set of 22 gestures, noting that some of the combinations are not possible to perform such as dynamic palm with at least one fixed-finger. In addition, some commonly used gestures may have the same movement characteristic but they differ in direction of the palm movement or the speed, for example, swipe, flick and drag. The resulting set of 22 gestures is described in Table I. IV. MULTI-TOUCH GESTURE RECOGNITION A. Pre-processing A multi-touch gesture is basically a time-series of the set of x-y coordinates of finger touch points. Each set consists of five touch points where each touch point is generated from one fingertip. However, we do not know which fingertip corresponds to which touch point, as the system orders them based on how users lay their fingertips down. The first finger of the user to touch the surface may vary from one instance to another for the same gesture. And this order keeps fluctuating from one set within the time series to another within the same gesture. As a result, a set of touch points ordered by the system cannot be directly compared with another. Hence, the first step is to label each of the touch points with the corresponding fingertip. Specifically, for every touch point set S t = {(x i, y i ) i = 1,..., 5} at time instance t, we have to compute the unique bijective mapping from the set of five touch points to the set of fingertip labels I = {1,..., 5}. That is, we have to compute f t : S t I. Fig. 1: The illustration of a simple polygon generated from fingertip order We note that the closed path drawn from the five fingertip points in circular order is always a simple polygon, as shown in Figure 1. Therefore, we propose to compute the mapping f t, at each time instance as follows. Starting with the first set, S 0, the x-y coordinates of the five points in this set are used to compute their centroid. Then the points are sorted in ascending order by the angle they make with this centroid. Next, the thumb is identified by exploiting the property observed from typical hand geometry that the thumb is the furthest away from its immediate neighbors (in circular order) among all the fingers. Once we find the thumb, we find the index finger by following the x-y coordinates of the remaining points in a circular arc. Noting that, if the gesture is left handed the detected order will be thumb, pinky, ring, middle, and Index fingers respectively. However, this does not affect matching performance as the order is always consistent within the subject. Once we have computed f 0, that is, we have mapped the first set of points to the corresponding fingertips, the mapping for the subsequent remaining touch point sets can be modeled as an optimization problem where the possible mappings are constrained by the natural characteristic of hand geometry which dictates that when touch points corresponding to physically adjacent fingers are connected and the pinky is finally connected to the thumb, we get a simple polygon. In other words, if the label assignment is valid, connecting the points in S t ordered by its label in circular order ( ) will form a simple polygon. Given f t 1, the objective function in the optimization is to 157

3 TABLE I: Gesture descriptions and the number of subjects from whom data was collected per gesture Annotation Palm movement Fingertip movement Dynamic fingertips of subjects CCR Static Circular(CCW) All 32 CR Static Circular(CW) All 33 Closed Static Close All 34 Drag Dynamic( ) Parallel All 33 DDC Dynamic( ) Close All 33 DUO Dynamic( ) Open All 30 FBD Static Parallel( ) Fixed thumb and pinky 30 FBSB Static Parallel( shape) Fixed thumb and pinky 26 FBSA Static Parallel( shape) Fixed thumb and pinky 27 FPCCR Static Circular(CCW) Fixed pinky 28 FPC Static Close Fixed pinky 31 FPO Static open Fixed pinky 26 FPP Static Parallel( ) Fixed pinky 28 FTCCR Static Circular(CCW) Fixed thumb 30 FTCR Static Circular(CW) Fixed thumb 30 FTC Static Close Fixed thumb 31 FTO Static Open Fixed thumb 30 FTP Static Parallel( ) Fixed thumb 30 Flick Dynamic( ) Parallel All(Quick) 33 Opened Static Open All 34 Scrawl Dynamic(Customized) Parallel All 30 Swipe Dynamic( ) Parallel All 34 search for the current mapping function f t, such that the sum of the Euclidean distances between corresponding fingertips from the previous assigned sequence f t 1 to f is minimized. That is, we search for, f t = argmin f i I f 1 t 1 (i) f 1 (i) (1) such that {e i, i = 1,..., 5} constructs a simple polygon, where e i = ( f 1 (i), f 1 (i + 1) ) is the line segment drawn from the touch point corresponding to index i to the touch point corresponding to index i + 1 of the mapping function f : S t I. Noting that process may start from the last touch point set of a time-series input if the last set creates a larger simple polygon than the first set. B. Feature transformation According to differences in the hand s position and device s orientation within the same gesture, different trials from the same subject may result in different 2-D patterns on the touch surface. To cope with these variations, we extract higher order features by computing distances between pairs of the labeled points obtained after pre-processing. With different orientations and positions of the plane, the distance between any two points remains unchanged. This ensures that the features are rotation and translation invariant. To describe a polygonal curve < p 1, p 2,..., p n > of a gesture input, which is a sequence of n touch point sets, we calculate a feature vector for each touch point set to describe a high dimensional point p i as, 1) Euclidean distance feature: Let S t = {(x i, y i ) i = 1,.., 5} be a sorted set of touch points, each of the feature attributes F t (i, j) are calculated as, F t (i, j) = (x i x j ) 2 + (y i y j ) 2, (2) where i and j = 1,...,5. The number of distinct features for each touch point set in this case is 5 C 2 or 10. Afterward, F t is linearized, using only the upper triangle of the matrix (since the matrix is symmetric with all 0 s along the diagonal) to form a 10-dimensional point p i. 2) First order Euclidean distance feature: With the simple Euclidean distance feature set above, the movement direction and distance between two consecutive sets is not captured. Consequently, it could result in lower system accuracy. Therefore, we derive additional features as the following. Let S t = {(x ț i, yt i ) i = 1,.., 5} and S t+1 = {(x t+1,i, y t+1 i ) i = 1,.., 5} be two consecutive sorted sets of touch points, the additional feature attributes are calculated as, F t(i, k) = (x t i xt+1 i+k )2 + (y t i yt+1 i+k )2, k = 0, 1 (3) where i is the fingertip label in circular order ranging from 1 to 5. The number of distinct features for two consecutive sets is 5 C 2 or 10. To form a a point in 20-dimensional space, p i, the vector of 10 Euclidean distance from the first feature set is concatenated with F t(i, 0) and F t(i, 1). C. Distance function Taking a curve similarity approach, we use two different functions to measure the distance between a pair of polygonal curves representing touch sequences which may have different lengths. Let π =< p 1, p 2,..., p m > and σ =< q 1, q 2,..., q n > be two polygonal curves, M = {(p i, q i )} be an orderpreserving complete correspondence between π and σ, and d(p, q) is a matching cost between p and q, the following distances are defined as the following, 1) Discrete Frèchet distance: The discrete Frèchet distance is defined as [17], ( ) δ D (π, σ) = min M max d(p, q) (p,q) M (4) 158

4 2) Dynamic Time Warping distance: The dynamic time warping, which is a well-known matching algorithm to measure a similarity between two sequences which may vary in length, is defined as, DT W (π, σ) = min M (p,q) M d(p, q) min(m, n) D. Matching cost of curve distance functions Measuring curve similarity involves computing matching cost between two points on a fixed dimensional space. In our experiment, the performance of our system was evaluated using the following three cost functions, Let p and q be two points in l-dimensional Euclidean space, 1) Manhattan distance defined as, d M (p, q) = (5) l p i q i (6) i=1 2) Euclidean distance function is defined as, 3) Cosine distance is defined as, E. Decision rules d E (p, q) = l (p i q i ) 2 (7) i=1 d C (p, q) = 1 p q p q In this paper, we investigate two decision rules which are suitable for different applications and require different training sets. 1) A variant of k-nn based rule: In a variant of the k- NN based rule, the weight of each of k nearest instances is assigned as the inverse function of its distance to a test instance. Let d j be the distance from a test instance to its j th nearest neighbor among k nearest ones, the weight w j is given by [18], (8) w j = d k d j d k d 1 (9) In the verification case, the voting score needs to be normalized in order to cope with the differences between intrauser variations. To achieve that, the total weight of all nearest neighbors are normalized to 1. The normalized weight w j is defined as, w j w j = k i=1 w (10) i The verification score is then the sum of all weights of the neighbors belonging to the subject. The major disadvantage for k-nn is that it could only be used to classify a sample from a known class. That is, training the classifier requires samples from all classes. Practically, in some scenario, we may not have complete control over the input. In other words, the input might be from an unknown user. In this case, the performance of k-nn is unpredictable. 2) Score-based rule: For the situation where only positive samples (from an enrolled user) are known to the system, the score can only be computed based on these samples. In this case, we compute the score using a min rule given by, Score (G, T ) = min i (D (T i, G)) (11) Where Score (G, T ) is the distance from the input sample G to the set of training samples T, Ti is i th training sample, and D (Ti, G) is the curve distance between T i to G. V. EXPERIMENTAL RESULT AND ANALYSIS A. Data collection To collect user gesture data we implemented an ipad application using version 3.2 of ios, which has multi-touch capability to track up to 5 points at a time, to capture users gestures. The screen resolution was We recruited 34 participants of which 30 were right-handed, 28 had some multi-touch device experience, while only six had prior experience with the ipad. Their ages ranged from 15 to 50 years. Out of these, 24 were male. The data collection session began by explaining to the subject the purpose of study without informing them anything about the template creation or matching mechanisms. Next the participant filled out a brief pre-survey with demographic questions. Then, each subject was asked to practice performing the gesture a few times before supplying 10 samples and giving the feedback related to the gesture. In total, each of them was asked to supply 10 samples for each of the 22 multi-touch gestures identified above. They could skip any gesture they did not feel comfortable performing. We show in Table 1 the number of users that provided data for each gesture. Finally, the participants answered a set of questions about the overall experience. To evaluate performance of a multi-touch gestures based verification system, the samples of the gestures from a particular user were used to test against the samples from all other subjects. Specifically, each test sample was used N times, where N was the number of subjects. One time was to test as a positive sample label against its own class and each of (N- 1) times was to test as a negative sample label against (N-1) other classes. For k-nn classifier of each class, the positive training set composed of the sample gestures from a particular subject and the negative training set composed of the sample gestures from all other subjects. For score-based rule, only the sample gestures from a particular subject were used to train the classifier. To evaluate the gesture performance in verification mode, the Equal Error Rate (EER), the rate at which False Acceptance Rate(FAR) and False Rejection Rate(FRR) are equal, was adopted as a measurement matrix. B. A single gesture In this mode, the performance of each gesture was evaluated individually. First, we conducted the evaluation using a k-nn classifier trained on the first five samples from all subjects. Table II shows the performance of each gesture in terms of 159

5 TABLE II: EER for different curve distance functions and cost functions with k-nn classifier where k = 5 when the training set consists of the first five samples from all the subjects, and EER is an average of EER differences from the best EER at each gesture 10 feature set 20 feature set Gesture DTW Frèchet DTW Frèchet d M d E d C d M d E d C d M d E d C d M d E d C CCR CR Closed Drag DDC DUO FBD FBSB FBSA FPCCR FPC FPO FPP FTCCR FTCR FTC FTO FTP Flick Opened Scrawl Swipe EER EER when different distance functions, and the associated cost functions were applied. In total, there are six gestures that gave EER ranging from 5% to 10%, and 16 gestures that gave EER ranging from 0% to 5%. Overall, the average performance of each gesture was 3.63%EER, when the lowest EER for each gesture was considered. By evaluating the effect of curve distance functions, the results show that DTW distance outperformed Frèchet distance more than 2% on the average, for both feature sets. However, the results are very similar when using three different cost functions. In addition, the 20- feature set led to a better average EER than the set of 10 features in all cost functions using DTW distance. Next, we did experiments with the score-based approach in two settings. For the first setting, only the first five samples from a particular subject were used as the training. The test set consisted of the last five sample of a particular subject as a positive label and all ten samples from all others as a negative label. For the second one, we performed the experiment using the leave-one-out technique. In this test, one sample from a verifying class was used as a test sample with a positive label exactly once. When it was used as a test instance, all the others from the same subject were used as the training. The results from DTW distance using three cost functions are given in Table III. It is seen that Manhattan distance performed similar to Euclidean one and both outperformed the cosine distance. Since the final score in this work is basically the minimum distance from an input to the templates, this performance disparity could result from differences between inter-user as well as intra-user variations of different approaches. In other words, Manhattan and Euclidean distance functions produce smaller variations than the cosine function does. Therefore, using the global threshold approach, they reported the lower TABLE III: EER for DTW distance function of 20 features set with three different cost functions based on score-based classifier Gesture First 5 samples training Leave-one-out test d M d E d C d M d E d C CCR CR Closed Drag DDC DUO FBD FBSB FBSA FPCCR FPC FPO FPP FTCCR FTCR FTC FTO FTP Flick Opened Scrawl Swipe Average EER EER. Moreover, in leave-one-out setting, EER for each cost function was decreased by 3% by average when compared to the first five sample setting. This implies that the number of training samples have an impact on system s accuracy. C. Multiple gestures In this mode, multiple defined gestures from the same subject, one sample per gesture, were combined to form an input. The objective here is to evaluate the possibility of improving the system performance by combining different information extracted from multiple gestures. To test out the strategy, we 160

6 carried out the experiment where we used only the first five samples of all selected gestures from a particular subject. In each setting, the test set consisted of all possible permutations. For example, with two gestures combination, for the first setting, the number of test samples with a positive label for each subject was 25 which are all permutations from the last five samples from each gesture. Figure 2 shows the Detection Error Trade-off curves (DET) of different combinations using the first five samples as the training. The gestures included static counter-clockwise rotation, closed and opened, all with five fingertips, which are commonly used to interact with the multi-touch devices. It shows that more number of gestures generally provide more discrimination power to the system. As seen that, specifically, at 2% FAR, the system achieved 1.15% FRR when this 3-gesture applied compared to greater than 3% when only 2 gestures applied and greater than 13% when a single gestures applied. In addition, the best EER at 1.58% obtained when all three gestures are applied. Fig. 2: Detection error trade-off curve of different combinations and the base line curves from a single gesture using first five samples as the templates VI. CONCLUSION AND FUTURE WORK In this paper, we have investigated the feasibility of a new behavioral biometric modality based on multi-touch gestures. We first defined a multi-touch gesture taxonomy specifically for biometric verification purpose and identified a set of 22 gesture candidates for our experiments. In order to design a classifier we developed a feature set that is invariant to translation and orientation. Based on the designed feature set, we tested 2 different curve distance functions and 3 different matching cost functions. The result showed that the normalized DTW outperformed the Frèchet distance for our feature set. For the different matching cost functions, the results were all similar for the k-nn classifier. However, for the score based classifier, the cosine function performed poorer than Euclidean and Manhattan distances. We also showed that multiple gestures strategy resulted in lower EER. This indicates that complementary information can be extracted from different gestures. Our results show that multi-touch interaction has a potential not only in the design of a novel user-interface, but also to develop a biometric based authentication application. For future work, we plan to further evaluate the property of a multi-touch gesture by investigating intra-user variation over a longer time span as well as collecting the data from more subjects to confirm the level of accuracy achievable. We also plan to investigate a fusion method to combine different classifiers or other biometric modalities in order to obtain higher accuracy. In addition, we will investigate how to incorporate other information like pressure, to improve performance. ACKNOWLEDGMENT The authors would like to thank Kowsar Ahmed for helping collect the data throughout our experiment and Umut Topkara for his insightful comments early in the project. REFERENCES [1] D. Zhang, W. Zuo, and F. Yue, A comparative study of palmprint recognition algorithms, ACM Comput. Surv., vol. 44, no. 1, pp. 2:1 2:37, Jan [2] M. Faundez-Zanuy, On-line signature recognition based on vq-dtw, in Pattern Recogn., March 2007, pp [3] A. Kholmatov and B. Yanikoglu, Biometric authentication using online signatures, in Proc. ISCIS, Springer LNCS-3280 (2004) Springer-Verlag, 2004, pp [4] R. B. Hill, Retina identification, pp , [5] R. Sanchez-Reillo and C. Sanchez-Avila, Iris recognition with low template size, in Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication, ser. AVBPA 01. London, UK: Springer-Verlag, 2001, pp [6] A. K. Jain and D. Maltoni, Handbook of fingerprint recognition, [7] M. Turk and A. Pentland, Face recognition using eigenfaces, in Computer Vision and Pattern Recognition, Proceedings CVPR 91., IEEE Computer Society Conference on, jun 1991, pp [8] C.-L. Lin and K.-C. Fan, Biometric verification using thermal images of palm-dorsa vein patterns, Circuits and Systems for Video Technology, IEEE Transactions on, vol. 14, no. 2, pp , feb [9] A. Jain, A. Ross, and S. Pankanti, A prototype hand geometry-based verification system, in 2nd Int l Conference on Audio- and Video-based Biometric Person Authentication, Washington D.C., [10] A. Kholmatov and B. Yanikoglu, SUSIG: an on-line signature database, associated protocols and benchmark results, Pattern Analysis & Applications, [11] D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, Speaker verification using adapted gaussian mixture models, Digital Signal Processing, vol. 10, no. 1-3, pp , [12] D. Gafurov, K. Helkala, and T. Sndrol, Biometric gait authentication using accelerometer sensor, Journal of Computers, vol. 1, no. 7, [13] M. Obaidat and B. Sadoun, Verification of computer users using keystroke dynamics, Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 27, no. 2, pp , apr [14] R. Maxion and K. Killourhy, Keystroke biometrics with number-pad input, in Dependable Systems and Networks (DSN), 2010 IEEE/IFIP International Conference on, july , pp [15] C. Shen, Z. Cai, X. Guan, H. Sha, and J. Du, Feature analysis of mouse dynamics in identity authentication and monitoring, in Communications, ICC 09. IEEE International Conference on, june 2009, pp [16] O. Hamdy and I. Traoré, Homogeneous physio-behavioral visual and mouse-based biometric, ACM Trans. Comput.-Hum. Interact., vol. 18, pp. 12:1 12:30, August [17] B. Aronov, S. Har-Peled, C. Knauer, Y. Wang, and C. Wenk, Frèchet distance for curves, revisited, in Proceedings of the 14th conference on Annual European Symposium - Volume 14, 2006, pp [18] S. A. Dudani, The distance-weighted k-nearest-neighbor rule, Systems, Man and Cybernetics, IEEE Transactions on, vol. SMC-6, no. 4, pp , april

An Efficient on-line Signature Verification System Using Histogram Features

An Efficient on-line Signature Verification System Using Histogram Features RESEARCH ARTICLE OPEN ACCESS An Efficient on-line Signature Verification System Using Histogram Features Mr.Abilash S 1, Mrs.M.Janani, M.E 2 ME Computer Science and Engineering,Department of CSE, Annai

More information

Keywords Wavelet decomposition, SIFT, Unibiometrics, Multibiometrics, Histogram Equalization.

Keywords Wavelet decomposition, SIFT, Unibiometrics, Multibiometrics, Histogram Equalization. Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Secure and Reliable

More information

Fusion of Hand Geometry and Palmprint Biometrics

Fusion of Hand Geometry and Palmprint Biometrics (Working Paper, Dec. 2003) Fusion of Hand Geometry and Palmprint Biometrics D.C.M. Wong, C. Poon and H.C. Shen * Department of Computer Science, Hong Kong University of Science and Technology, Clear Water

More information

DEFORMABLE MATCHING OF HAND SHAPES FOR USER VERIFICATION. Ani1 K. Jain and Nicolae Duta

DEFORMABLE MATCHING OF HAND SHAPES FOR USER VERIFICATION. Ani1 K. Jain and Nicolae Duta DEFORMABLE MATCHING OF HAND SHAPES FOR USER VERIFICATION Ani1 K. Jain and Nicolae Duta Department of Computer Science and Engineering Michigan State University, East Lansing, MI 48824-1026, USA E-mail:

More information

International Journal of Advanced Research in Computer Science and Software Engineering

International Journal of Advanced Research in Computer Science and Software Engineering ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: Fingerprint Recognition using Robust Local Features Madhuri and

More information

A Study on the Consistency of Features for On-line Signature Verification

A Study on the Consistency of Features for On-line Signature Verification A Study on the Consistency of Features for On-line Signature Verification Center for Unified Biometrics and Sensors State University of New York at Buffalo Amherst, NY 14260 {hlei,govind}@cse.buffalo.edu

More information

A Combined Method for On-Line Signature Verification

A Combined Method for On-Line Signature Verification BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 14, No 2 Sofia 2014 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.2478/cait-2014-0022 A Combined Method for On-Line

More information

An Efficient Secure Multimodal Biometric Fusion Using Palmprint and Face Image

An Efficient Secure Multimodal Biometric Fusion Using Palmprint and Face Image International Journal of Computer Science Issues, Vol. 2, 2009 ISSN (Online): 694-0784 ISSN (Print): 694-084 49 An Efficient Secure Multimodal Biometric Fusion Using Palmprint and Face Image Nageshkumar.M,

More information

Biometrics Technology: Multi-modal (Part 2)

Biometrics Technology: Multi-modal (Part 2) Biometrics Technology: Multi-modal (Part 2) References: At the Level: [M7] U. Dieckmann, P. Plankensteiner and T. Wagner, "SESAM: A biometric person identification system using sensor fusion ", Pattern

More information

A BIOMETRIC FUSION OF HAND AND FINGER VEIN APPROACH FOR AN EFFICIENT PERSONAL AUTHENTICATION IN HEALTH CARE

A BIOMETRIC FUSION OF HAND AND FINGER VEIN APPROACH FOR AN EFFICIENT PERSONAL AUTHENTICATION IN HEALTH CARE A BIOMETRIC FUSION OF HAND AND FINGER VEIN APPROACH FOR AN EFFICIENT PERSONAL AUTHENTICATION IN HEALTH CARE N S Priya 1, A Lenin Fred 2 1 Assistant Professor, Department of Computer Science and Engineering,

More information

Feature-level Fusion for Effective Palmprint Authentication

Feature-level Fusion for Effective Palmprint Authentication Feature-level Fusion for Effective Palmprint Authentication Adams Wai-Kin Kong 1, 2 and David Zhang 1 1 Biometric Research Center, Department of Computing The Hong Kong Polytechnic University, Kowloon,

More information

Peg-Free Hand Geometry Verification System

Peg-Free Hand Geometry Verification System Peg-Free Hand Geometry Verification System Pavan K Rudravaram Venu Govindaraju Center for Unified Biometrics and Sensors (CUBS), University at Buffalo,New York,USA. {pkr, govind} @cedar.buffalo.edu http://www.cubs.buffalo.edu

More information

Gurmeet Kaur 1, Parikshit 2, Dr. Chander Kant 3 1 M.tech Scholar, Assistant Professor 2, 3

Gurmeet Kaur 1, Parikshit 2, Dr. Chander Kant 3 1 M.tech Scholar, Assistant Professor 2, 3 Volume 8 Issue 2 March 2017 - Sept 2017 pp. 72-80 available online at www.csjournals.com A Novel Approach to Improve the Biometric Security using Liveness Detection Gurmeet Kaur 1, Parikshit 2, Dr. Chander

More information

Graph Matching Iris Image Blocks with Local Binary Pattern

Graph Matching Iris Image Blocks with Local Binary Pattern Graph Matching Iris Image Blocs with Local Binary Pattern Zhenan Sun, Tieniu Tan, and Xianchao Qiu Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of

More information

Biometrics Technology: Hand Geometry

Biometrics Technology: Hand Geometry Biometrics Technology: Hand Geometry References: [H1] Gonzeilez, S., Travieso, C.M., Alonso, J.B., and M.A. Ferrer, Automatic biometric identification system by hand geometry, Proceedings of IEEE the 37th

More information

Ujma A. Mulla 1 1 PG Student of Electronics Department of, B.I.G.C.E., Solapur, Maharashtra, India. IJRASET: All Rights are Reserved

Ujma A. Mulla 1 1 PG Student of Electronics Department of, B.I.G.C.E., Solapur, Maharashtra, India. IJRASET: All Rights are Reserved Generate new identity from fingerprints for privacy protection Ujma A. Mulla 1 1 PG Student of Electronics Department of, B.I.G.C.E., Solapur, Maharashtra, India Abstract : We propose here a novel system

More information

An Algorithm for Feature Level Fusion in Multimodal Biometric System

An Algorithm for Feature Level Fusion in Multimodal Biometric System An Algorithm for Feature Level Fusion in Multimodal Biometric System 1 S.K.Bhardwaj 1 Research Scholar, Singhania University, Jhunjhunu, Rajasthan (India) Abstract The increasing demand for high secure

More information

Biometric Security System Using Palm print

Biometric Security System Using Palm print ISSN (Online) : 2319-8753 ISSN (Print) : 2347-6710 International Journal of Innovative Research in Science, Engineering and Technology Volume 3, Special Issue 3, March 2014 2014 International Conference

More information

K-Nearest Neighbor Classification Approach for Face and Fingerprint at Feature Level Fusion

K-Nearest Neighbor Classification Approach for Face and Fingerprint at Feature Level Fusion K-Nearest Neighbor Classification Approach for Face and Fingerprint at Feature Level Fusion Dhriti PEC University of Technology Chandigarh India Manvjeet Kaur PEC University of Technology Chandigarh India

More information

Real-Time Model-Based Hand Localization for Unsupervised Palmar Image Acquisition

Real-Time Model-Based Hand Localization for Unsupervised Palmar Image Acquisition Real-Time Model-Based Hand Localization for Unsupervised Palmar Image Acquisition Ivan Fratric 1, Slobodan Ribaric 1 1 University of Zagreb, Faculty of Electrical Engineering and Computing, Unska 3, 10000

More information

Palmprint Recognition Using Transform Domain and Spatial Domain Techniques

Palmprint Recognition Using Transform Domain and Spatial Domain Techniques Palmprint Recognition Using Transform Domain and Spatial Domain Techniques Jayshri P. Patil 1, Chhaya Nayak 2 1# P. G. Student, M. Tech. Computer Science and Engineering, 2* HOD, M. Tech. Computer Science

More information

Biometric Security Roles & Resources

Biometric Security Roles & Resources Biometric Security Roles & Resources Part 1 Biometric Systems Skip Linehan Biometrics Systems Architect, Raytheon Intelligence and Information Systems Outline Biometrics Overview Biometric Architectures

More information

Signature Recognition by Pixel Variance Analysis Using Multiple Morphological Dilations

Signature Recognition by Pixel Variance Analysis Using Multiple Morphological Dilations Signature Recognition by Pixel Variance Analysis Using Multiple Morphological Dilations H B Kekre 1, Department of Computer Engineering, V A Bharadi 2, Department of Electronics and Telecommunication**

More information

Implementation and Comparative Analysis of Rotation Invariance Techniques in Fingerprint Recognition

Implementation and Comparative Analysis of Rotation Invariance Techniques in Fingerprint Recognition RESEARCH ARTICLE OPEN ACCESS Implementation and Comparative Analysis of Rotation Invariance Techniques in Fingerprint Recognition Manisha Sharma *, Deepa Verma** * (Department Of Electronics and Communication

More information

Finger or Stylus: Their Impact on the Performance of Online Signature Verification Systems

Finger or Stylus: Their Impact on the Performance of Online Signature Verification Systems MACRo 2017-6 th International Conference on Recent Achievements in Mechatronics, Automation, Computer Science and Robotics Finger or Stylus: Their Impact on the Performance of Online Signature Verification

More information

Semi-Supervised PCA-based Face Recognition Using Self-Training

Semi-Supervised PCA-based Face Recognition Using Self-Training Semi-Supervised PCA-based Face Recognition Using Self-Training Fabio Roli and Gian Luca Marcialis Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d Armi, 09123 Cagliari, Italy

More information

6. Multimodal Biometrics

6. Multimodal Biometrics 6. Multimodal Biometrics Multimodal biometrics is based on combination of more than one type of biometric modalities or traits. The most compelling reason to combine different modalities is to improve

More information

Fingerprint Matching using Gabor Filters

Fingerprint Matching using Gabor Filters Fingerprint Matching using Gabor Filters Muhammad Umer Munir and Dr. Muhammad Younas Javed College of Electrical and Mechanical Engineering, National University of Sciences and Technology Rawalpindi, Pakistan.

More information

BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition

BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition Hiren D. Joshi Phd, Dept. of Computer Science Rollwala Computer Centre

More information

Finger Print Enhancement Using Minutiae Based Algorithm

Finger Print Enhancement Using Minutiae Based Algorithm Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 8, August 2014,

More information

Improving Personal Identification Accuracy Using Multisensor Fusion for Building Access Control Applications

Improving Personal Identification Accuracy Using Multisensor Fusion for Building Access Control Applications Improving Personal Identification Accuracy Using Multisensor Fusion for Building Access Control Applications Lisa Osadciw, Pramod Varshney, and Kalyan Veeramachaneni laosadci,varshney,kveerama@syr.edu

More information

Performance Analysis of Fingerprint Identification Using Different Levels of DTCWT

Performance Analysis of Fingerprint Identification Using Different Levels of DTCWT 2012 International Conference on Information and Computer Applications (ICICA 2012) IPCSIT vol. 24 (2012) (2012) IACSIT Press, Singapore Performance Analysis of Fingerprint Identification Using Different

More information

Semi-Supervised Clustering with Partial Background Information

Semi-Supervised Clustering with Partial Background Information Semi-Supervised Clustering with Partial Background Information Jing Gao Pang-Ning Tan Haibin Cheng Abstract Incorporating background knowledge into unsupervised clustering algorithms has been the subject

More information

A Contactless Palmprint Recognition Algorithm for Mobile Phones

A Contactless Palmprint Recognition Algorithm for Mobile Phones A Contactless Palmprint Recognition Algorithm for Mobile Phones Shoichiro Aoyama, Koichi Ito and Takafumi Aoki Graduate School of Information Sciences, Tohoku University 6 6 05, Aramaki Aza Aoba, Sendai-shi

More information

Hybrid Biometric Person Authentication Using Face and Voice Features

Hybrid Biometric Person Authentication Using Face and Voice Features Paper presented in the Third International Conference, Audio- and Video-Based Biometric Person Authentication AVBPA 2001, Halmstad, Sweden, proceedings pages 348-353, June 2001. Hybrid Biometric Person

More information

Multimodal Biometric System by Feature Level Fusion of Palmprint and Fingerprint

Multimodal Biometric System by Feature Level Fusion of Palmprint and Fingerprint Multimodal Biometric System by Feature Level Fusion of Palmprint and Fingerprint Navdeep Bajwa M.Tech (Student) Computer Science GIMET, PTU Regional Center Amritsar, India Er. Gaurav Kumar M.Tech (Supervisor)

More information

: BIOMETRIC AUTHENTICATION TOOL FOR USER IDENTIFICATION

: BIOMETRIC AUTHENTICATION TOOL FOR USER IDENTIFICATION 2006-287: BIOMETRIC AUTHENTICATION TOOL FOR USER IDENTIFICATION Mario Garcia, Texas A&M University-Corpus Christi American Society for Engineering Education, 2006 Page 11.277.1 Biometric Authentication

More information

Outline. Incorporating Biometric Quality In Multi-Biometrics FUSION. Results. Motivation. Image Quality: The FVC Experience

Outline. Incorporating Biometric Quality In Multi-Biometrics FUSION. Results. Motivation. Image Quality: The FVC Experience Incorporating Biometric Quality In Multi-Biometrics FUSION QUALITY Julian Fierrez-Aguilar, Javier Ortega-Garcia Biometrics Research Lab. - ATVS Universidad Autónoma de Madrid, SPAIN Loris Nanni, Raffaele

More information

IRIS Recognition System Based On DCT - Matrix Coefficient Lokesh Sharma 1

IRIS Recognition System Based On DCT - Matrix Coefficient Lokesh Sharma 1 Volume 2, Issue 10, October 2014 International Journal of Advance Research in Computer Science and Management Studies Research Article / Survey Paper / Case Study Available online at: www.ijarcsms.com

More information

Iris Recognition for Eyelash Detection Using Gabor Filter

Iris Recognition for Eyelash Detection Using Gabor Filter Iris Recognition for Eyelash Detection Using Gabor Filter Rupesh Mude 1, Meenakshi R Patel 2 Computer Science and Engineering Rungta College of Engineering and Technology, Bhilai Abstract :- Iris recognition

More information

Fingerprint Indexing using Minutiae and Pore Features

Fingerprint Indexing using Minutiae and Pore Features Fingerprint Indexing using Minutiae and Pore Features R. Singh 1, M. Vatsa 1, and A. Noore 2 1 IIIT Delhi, India, {rsingh, mayank}iiitd.ac.in 2 West Virginia University, Morgantown, USA, afzel.noore@mail.wvu.edu

More information

Computationally Efficient Serial Combination of Rotation-invariant and Rotation Compensating Iris Recognition Algorithms

Computationally Efficient Serial Combination of Rotation-invariant and Rotation Compensating Iris Recognition Algorithms Computationally Efficient Serial Combination of Rotation-invariant and Rotation Compensating Iris Recognition Algorithms Andreas Uhl Department of Computer Sciences University of Salzburg, Austria uhl@cosy.sbg.ac.at

More information

Parallel versus Serial Classifier Combination for Multibiometric Hand-Based Identification

Parallel versus Serial Classifier Combination for Multibiometric Hand-Based Identification A. Uhl and P. Wild. Parallel versus Serial Classifier Combination for Multibiometric Hand-Based Identification. In M. Tistarelli and M. Nixon, editors, Proceedings of the 3rd International Conference on

More information

A study of the Graphical User Interfaces for Biometric Authentication System

A study of the Graphical User Interfaces for Biometric Authentication System A study of the Graphical User Interfaces for Biometric Authentication System Hiroshi Dozono 1, Takayuki Inoue 1, Masanori Nakakun 2 i 1 Faculty of Science and Engineering, Saga University, 1-Honjyo Saga,

More information

Online Signature Verification Technique

Online Signature Verification Technique Volume 3, Issue 1 ISSN: 2320-5288 International Journal of Engineering Technology & Management Research Journal homepage: www.ijetmr.org Online Signature Verification Technique Ankit Soni M Tech Student,

More information

FVC2004: Third Fingerprint Verification Competition

FVC2004: Third Fingerprint Verification Competition FVC2004: Third Fingerprint Verification Competition D. Maio 1, D. Maltoni 1, R. Cappelli 1, J.L. Wayman 2, A.K. Jain 3 1 Biometric System Lab - DEIS, University of Bologna, via Sacchi 3, 47023 Cesena -

More information

Technical White Paper. Behaviometrics. Measuring FAR/FRR/EER in Continuous Authentication

Technical White Paper. Behaviometrics. Measuring FAR/FRR/EER in Continuous Authentication Technical White Paper Behaviometrics Measuring FAR/FRR/EER in Continuous Authentication Draft version 12/22/2009 Table of Contents Background... 1 Calculating FAR/FRR/EER in the field of Biometrics...

More information

Spatial Topology of Equitemporal Points on Signatures for Retrieval

Spatial Topology of Equitemporal Points on Signatures for Retrieval Spatial Topology of Equitemporal Points on Signatures for Retrieval D.S. Guru, H.N. Prakash, and T.N. Vikram Dept of Studies in Computer Science,University of Mysore, Mysore - 570 006, India dsg@compsci.uni-mysore.ac.in,

More information

Online and Offline Fingerprint Template Update Using Minutiae: An Experimental Comparison

Online and Offline Fingerprint Template Update Using Minutiae: An Experimental Comparison Online and Offline Fingerprint Template Update Using Minutiae: An Experimental Comparison Biagio Freni, Gian Luca Marcialis, and Fabio Roli University of Cagliari Department of Electrical and Electronic

More information

Fingertips Tracking based on Gradient Vector

Fingertips Tracking based on Gradient Vector Int. J. Advance Soft Compu. Appl, Vol. 7, No. 3, November 2015 ISSN 2074-8523 Fingertips Tracking based on Gradient Vector Ahmad Yahya Dawod 1, Md Jan Nordin 1, and Junaidi Abdullah 2 1 Pattern Recognition

More information

Rotation Invariant Finger Vein Recognition *

Rotation Invariant Finger Vein Recognition * Rotation Invariant Finger Vein Recognition * Shaohua Pang, Yilong Yin **, Gongping Yang, and Yanan Li School of Computer Science and Technology, Shandong University, Jinan, China pangshaohua11271987@126.com,

More information

Multimodal Biometric Authentication using Face and Fingerprint

Multimodal Biometric Authentication using Face and Fingerprint IJIRST National Conference on Networks, Intelligence and Computing Systems March 2017 Multimodal Biometric Authentication using Face and Fingerprint Gayathri. R 1 Viji. A 2 1 M.E Student 2 Teaching Fellow

More information

An Enhanced Face Recognition System based on Rotated Two Dimensional Principal Components

An Enhanced Face Recognition System based on Rotated Two Dimensional Principal Components An Enhanced Face Recognition System based on Two Dimensional Principal Components Garima, Sujit Tiwari Abstract Face has been one of the widely used modality from very beginning of biometrics recognition

More information

Projected Texture for Hand Geometry based Authentication

Projected Texture for Hand Geometry based Authentication Projected Texture for Hand Geometry based Authentication Avinash Sharma Nishant Shobhit Anoop Namboodiri Center for Visual Information Technology International Institute of Information Technology, Hyderabad,

More information

Fingerprint Classification Using Orientation Field Flow Curves

Fingerprint Classification Using Orientation Field Flow Curves Fingerprint Classification Using Orientation Field Flow Curves Sarat C. Dass Michigan State University sdass@msu.edu Anil K. Jain Michigan State University ain@msu.edu Abstract Manual fingerprint classification

More information

A Biometric Authentication System That Automatically Generates Feature Points

A Biometric Authentication System That Automatically Generates Feature Points A Biometric Authentication System That Automatically Generates Feature Points Hiroshi Dozono 1, Youki Inaba 1, Masanori Nakakuni 2 1 Faculty of Science and Engineering, Saga University, 1-Honjyo Saga,

More information

On-line Signature Verification on a Mobile Platform

On-line Signature Verification on a Mobile Platform On-line Signature Verification on a Mobile Platform Nesma Houmani, Sonia Garcia-Salicetti, Bernadette Dorizzi, and Mounim El-Yacoubi Institut Telecom; Telecom SudParis; Intermedia Team, 9 rue Charles Fourier,

More information

An Overview of Biometric Image Processing

An Overview of Biometric Image Processing An Overview of Biometric Image Processing CHAPTER 2 AN OVERVIEW OF BIOMETRIC IMAGE PROCESSING The recognition of persons on the basis of biometric features is an emerging phenomenon in our society. Traditional

More information

A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation

A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation * A. H. M. Al-Helali, * W. A. Mahmmoud, and * H. A. Ali * Al- Isra Private University Email: adnan_hadi@yahoo.com Abstract:

More information

Performance Improvement of Phase-Based Correspondence Matching for Palmprint Recognition

Performance Improvement of Phase-Based Correspondence Matching for Palmprint Recognition Performance Improvement of Phase-Based Correspondence Matching for Palmprint Recognition Vincent Roux Institut Supérieur d électronique de Paris,, rue Notre Dame des Champs, 76 Paris, France vincent.roux@isep.fr

More information

Color-Based Classification of Natural Rock Images Using Classifier Combinations

Color-Based Classification of Natural Rock Images Using Classifier Combinations Color-Based Classification of Natural Rock Images Using Classifier Combinations Leena Lepistö, Iivari Kunttu, and Ari Visa Tampere University of Technology, Institute of Signal Processing, P.O. Box 553,

More information

ISSN Vol.07,Issue.12, August-2015, Pages:

ISSN Vol.07,Issue.12, August-2015, Pages: ISSN 2348 2370 Vol.07,Issue.12, August-2015, Pages:2349-2355 www.ijatir.org Online Signature Verification on Mobile Devices MENDRA SHIRISHA 1, P. ASHOK KUMAR 2 1 PG Scholar, Dept of ECE, Samskruti College

More information

Approach to Increase Accuracy of Multimodal Biometric System for Feature Level Fusion

Approach to Increase Accuracy of Multimodal Biometric System for Feature Level Fusion Approach to Increase Accuracy of Multimodal Biometric System for Feature Level Fusion Er. Munish Kumar, Er. Prabhjit Singh M-Tech(Scholar) Global Institute of Management and Emerging Technology Assistant

More information

CHAPTER 6 RESULTS AND DISCUSSIONS

CHAPTER 6 RESULTS AND DISCUSSIONS 151 CHAPTER 6 RESULTS AND DISCUSSIONS In this chapter the performance of the personal identification system on the PolyU database is presented. The database for both Palmprint and Finger Knuckle Print

More information

A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION

A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION Hazim Kemal Ekenel, Rainer Stiefelhagen Interactive Systems Labs, Universität Karlsruhe (TH) 76131 Karlsruhe, Germany

More information

POLYBIO Multibiometrics Database: Contents, description and interfacing platform

POLYBIO Multibiometrics Database: Contents, description and interfacing platform POLYBIO Multibiometrics Database: Contents, description and interfacing platform Anixi Antonakoudi 1, Anastasis Kounoudes 2 and Zenonas Theodosiou 3 1 Philips College, 4-6 Lamias str. 2001, P.O. Box 28008,

More information

Accelerometer Gesture Recognition

Accelerometer Gesture Recognition Accelerometer Gesture Recognition Michael Xie xie@cs.stanford.edu David Pan napdivad@stanford.edu December 12, 2014 Abstract Our goal is to make gesture-based input for smartphones and smartwatches accurate

More information

Haresh D. Chande #, Zankhana H. Shah *

Haresh D. Chande #, Zankhana H. Shah * Illumination Invariant Face Recognition System Haresh D. Chande #, Zankhana H. Shah * # Computer Engineering Department, Birla Vishvakarma Mahavidyalaya, Gujarat Technological University, India * Information

More information

Histogram-based matching of GMM encoded features for online signature verification

Histogram-based matching of GMM encoded features for online signature verification Histogram-based matching of GMM encoded features for online signature verification Vivek Venugopal On behalf of Abhishek Sharma,Dr. Suresh Sundaram Multimedia Analytics Laboratory, Electronics and Electrical

More information

Signature Verification Why xyzmo offers the leading solution

Signature Verification Why xyzmo offers the leading solution Dynamic (Biometric) Signature Verification The signature is the last remnant of the hand-written document in a digital world, and is considered an acceptable and trustworthy means of authenticating all

More information

Tutorial 1. Jun Xu, Teaching Asistant January 26, COMP4134 Biometrics Authentication

Tutorial 1. Jun Xu, Teaching Asistant January 26, COMP4134 Biometrics Authentication Tutorial 1 Jun Xu, Teaching Asistant csjunxu@comp.polyu.edu.hk COMP4134 Biometrics Authentication January 26, 2017 Table of Contents Problems Problem 1: Answer the following questions Problem 2: Biometric

More information

Multimodal Biometrics for Voice and Handwriting

Multimodal Biometrics for Voice and Handwriting Multimodal Biometrics for Voice and Handwriting Claus Vielhauer and Tobias Scheidat School of Computer Science, Department of Technical and Business Information Systems, Advanced Multimedia and Security

More information

Implementation of the USB Token System for Fingerprint Verification

Implementation of the USB Token System for Fingerprint Verification Implementation of the USB Token System for Fingerprint Verification Daesung Moon, Youn Hee Gil, Sung Bum Pan, and Yongwha Chung Biometrics Technology Research Team, ETRI, Daejeon, Korea {daesung, yhgil,

More information

REINFORCED FINGERPRINT MATCHING METHOD FOR AUTOMATED FINGERPRINT IDENTIFICATION SYSTEM

REINFORCED FINGERPRINT MATCHING METHOD FOR AUTOMATED FINGERPRINT IDENTIFICATION SYSTEM 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

More information

Digital Signature Generation using Fingerprint, Password and Smart Card

Digital Signature Generation using Fingerprint, Password and Smart Card Digital Signature Generation using Fingerprint, Password and Smart Card FAWAD AHMED and MOHAMMED YAKOOB SIYAL School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang

More information

Embedded Palmprint Recognition System on Mobile Devices

Embedded Palmprint Recognition System on Mobile Devices Embedded Palmprint Recognition System on Mobile Devices Yufei Han, Tieniu Tan, Zhenan Sun, and Ying Hao Center for Biometrics and Security Research National Labrotory of Pattern Recognition,Institue of

More information

1.1 Performances of a Biometric System

1.1 Performances of a Biometric System Performance Analysis of Multimodal Biometric Based Authentication System Mrs.R.Manju, a Mr.A.Rajendran a,dr.a.shajin Narguna b, a Asst.Prof, Department Of EIE,Noorul Islam University, a Lecturer, Department

More information

Hand gesture recognition with Leap Motion and Kinect devices

Hand gesture recognition with Leap Motion and Kinect devices Hand gesture recognition with Leap Motion and devices Giulio Marin, Fabio Dominio and Pietro Zanuttigh Department of Information Engineering University of Padova, Italy Abstract The recent introduction

More information

CPSC 695. Geometric Algorithms in Biometrics. Dr. Marina L. Gavrilova

CPSC 695. Geometric Algorithms in Biometrics. Dr. Marina L. Gavrilova CPSC 695 Geometric Algorithms in Biometrics Dr. Marina L. Gavrilova Biometric goals Verify users Identify users Synthesis - recently Biometric identifiers Courtesy of Bromba GmbH Classification of identifiers

More information

Discovering Computers Chapter 5 Input

Discovering Computers Chapter 5 Input Discovering Computers 2009 Chapter 5 Input Chapter 5 Objectives Define input List the characteristics of a keyboard Describe different mouse types and how they work Summarize how various pointing devices

More information

Indexing Fingerprints using Minutiae Quadruplets

Indexing Fingerprints using Minutiae Quadruplets Indexing Fingerprints using Minutiae Quadruplets Ogechukwu Iloanusi University of Nigeria, Nsukka oniloanusi@gmail.com Aglika Gyaourova and Arun Ross West Virginia University http://www.csee.wvu.edu/~ross

More information

Model-based segmentation and recognition from range data

Model-based segmentation and recognition from range data Model-based segmentation and recognition from range data Jan Boehm Institute for Photogrammetry Universität Stuttgart Germany Keywords: range image, segmentation, object recognition, CAD ABSTRACT This

More information

Using Support Vector Machines to Eliminate False Minutiae Matches during Fingerprint Verification

Using Support Vector Machines to Eliminate False Minutiae Matches during Fingerprint Verification Using Support Vector Machines to Eliminate False Minutiae Matches during Fingerprint Verification Abstract Praveer Mansukhani, Sergey Tulyakov, Venu Govindaraju Center for Unified Biometrics and Sensors

More information

Fingerprint Identification System Based On Neural Network

Fingerprint Identification System Based On Neural Network Fingerprint Identification System Based On Neural Network Mr. Lokhande S.K., Prof. Mrs. Dhongde V.S. ME (VLSI & Embedded Systems), Vishwabharati Academy s College of Engineering, Ahmednagar (MS), India

More information

User Identification by Hierarchical Fingerprint and Palmprint Matching

User Identification by Hierarchical Fingerprint and Palmprint Matching User Identification by Hierarchical Fingerprint and Palmprint Matching Annapoorani D #1, Caroline Viola Stella Mary M *2 # PG Scholar, Department of Information Technology, * Prof. and HOD, Department

More information

Gaussian Mixture Model Coupled with Independent Component Analysis for Palmprint Verification

Gaussian Mixture Model Coupled with Independent Component Analysis for Palmprint Verification Gaussian Mixture Model Coupled with Independent Component Analysis for Palmprint Verification Raghavendra.R, Bernadette Dorizzi, Ashok Rao, Hemantha Kumar G Abstract In this paper we present a new scheme

More information

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,

More information

Multimodal Fusion Vulnerability to Non-Zero Effort (Spoof) Imposters

Multimodal Fusion Vulnerability to Non-Zero Effort (Spoof) Imposters Multimodal Fusion Vulnerability to Non-Zero Effort (Spoof) mposters P. A. Johnson, B. Tan, S. Schuckers 3 ECE Department, Clarkson University Potsdam, NY 3699, USA johnsopa@clarkson.edu tanb@clarkson.edu

More information

Incorporating Image Quality in Multi-Algorithm Fingerprint Verification

Incorporating Image Quality in Multi-Algorithm Fingerprint Verification Incorporating Image Quality in Multi-Algorithm Fingerprint Verification Julian Fierrez-Aguilar 1, Yi Chen 2, Javier Ortega-Garcia 1, and Anil K. Jain 2 1 ATVS, Escuela Politecnica Superior, Universidad

More information

Gaithashing: a two-factor authentication scheme based on gait features

Gaithashing: a two-factor authentication scheme based on gait features Gaithashing: a two-factor authentication scheme based on gait features Christoforos Ntantogian, Stefanos Malliaros, Christos Xenakis Department of Digital Systems, University of Piraeus, Piraeus, Greece

More information

Robust color segmentation algorithms in illumination variation conditions

Robust color segmentation algorithms in illumination variation conditions 286 CHINESE OPTICS LETTERS / Vol. 8, No. / March 10, 2010 Robust color segmentation algorithms in illumination variation conditions Jinhui Lan ( ) and Kai Shen ( Department of Measurement and Control Technologies,

More information

Fingerprint Recognition using Texture Features

Fingerprint Recognition using Texture Features Fingerprint Recognition using Texture Features Manidipa Saha, Jyotismita Chaki, Ranjan Parekh,, School of Education Technology, Jadavpur University, Kolkata, India Abstract: This paper proposes an efficient

More information

A Method for the Identification of Inaccuracies in Pupil Segmentation

A Method for the Identification of Inaccuracies in Pupil Segmentation A Method for the Identification of Inaccuracies in Pupil Segmentation Hugo Proença and Luís A. Alexandre Dep. Informatics, IT - Networks and Multimedia Group Universidade da Beira Interior, Covilhã, Portugal

More information

Polar Harmonic Transform for Fingerprint Recognition

Polar Harmonic Transform for Fingerprint Recognition International Journal Of Engineering Research And Development e-issn: 2278-067X, p-issn: 2278-800X, www.ijerd.com Volume 13, Issue 11 (November 2017), PP.50-55 Polar Harmonic Transform for Fingerprint

More information

A Two-stage Scheme for Dynamic Hand Gesture Recognition

A Two-stage Scheme for Dynamic Hand Gesture Recognition A Two-stage Scheme for Dynamic Hand Gesture Recognition James P. Mammen, Subhasis Chaudhuri and Tushar Agrawal (james,sc,tush)@ee.iitb.ac.in Department of Electrical Engg. Indian Institute of Technology,

More information

A Biometric Verification System Based on the Fusion of Palmprint and Face Features

A Biometric Verification System Based on the Fusion of Palmprint and Face Features A Biometric Verification System Based on the Fusion of Palmprint and Face Features Slobodan Ribaric, Ivan Fratric and Kristina Kis Faculty of Electrical Engineering and Computing, University of Zagreb,

More information

Multiple Classifier Fusion using k-nearest Localized Templates

Multiple Classifier Fusion using k-nearest Localized Templates Multiple Classifier Fusion using k-nearest Localized Templates Jun-Ki Min and Sung-Bae Cho Department of Computer Science, Yonsei University Biometrics Engineering Research Center 134 Shinchon-dong, Sudaemoon-ku,

More information

Discovering Computers Chapter 5 Input. CSA 111 College of Applied Studies UOB

Discovering Computers Chapter 5 Input. CSA 111 College of Applied Studies UOB Discovering Computers 2008 Chapter 5 Input 1 Chapter 5 Objectives Define input List the characteristics of a keyboard Describe different mouse types and how they work Summarize how various pointing devices

More information

Hand Geometry Verification based on Chain Code and Dynamic Time Warping

Hand Geometry Verification based on Chain Code and Dynamic Time Warping Hand Geometry Verification based on Chain Code and Dynamic Time Warping I Ketut Gede Darma Putra Department of Electrical Engineering Udayana University, Bali, Indonesia Made Ari Sentosa Alumni of Department

More information

Robust biometric image watermarking for fingerprint and face template protection

Robust biometric image watermarking for fingerprint and face template protection Robust biometric image watermarking for fingerprint and face template protection Mayank Vatsa 1, Richa Singh 1, Afzel Noore 1a),MaxM.Houck 2, and Keith Morris 2 1 West Virginia University, Morgantown,

More information