Fusion of multiple clues for photo-attack detection in face recognition systems

Size: px
Start display at page:

Download "Fusion of multiple clues for photo-attack detection in face recognition systems"

Transcription

1 Fusion of multiple clues for photo-attack detection in face recognition systems Roberto Tronci, Daniele Muntoni, Gianluca Fadda, Maurizio Pili, Nicola Sirena, Gabriele Murgia, Marco Ristori Sardegna Ricerche, Ambient Intelligence Lab. Loc. Piscinamanna, 91 Pula (CA), Italy Fabio Roli Deparment of Electrical and Electronic Engineering, Univ. of Cagliari Piazza d Armi, 9123 Cagliari, Italy roli@diee.unica.it Abstract We faced the problem of detecting 2-D face spoofing attacks performed by placing a printed photo of a real user in front of the camera. For this type of attack it is not possible to relay just on the face movements as a clue of vitality because the attacker can easily simulate such a case, and also because real users often show a low vitality during the authentication session. In this paper, we perform both video and static analysis in order to employ complementary information about motion, texture and liveness and consequently to obtain a more robust classification. 1. Introduction Biometrics had been introduced to improve the reliability and the security for access control by an automatic assessment of an individual s identity. Improvement is granted by the fact that while traditional identification systems depend on a passwords to remember or a key to possess, a biometric is always with the individual and it can t be lost or forgotten [2]. As biometric systems spread over and increase their performance, growing interest should be given to possible direct attacks, where potential intruders may gain access to the system by directly interacting with the system input device, like a normal user would. Such attempts are commonly referred as spoofing attacks [9]. A lot of work exists in the literature about fingerprint spoofing (probably because it is the most used biometric) and since the early works[6], many methods for liveness verification have been developed to recognize fake fingers or even real fingers taken away from people or from death bodies. On the other hand, although face recognition systems had captured increasing attention in the past decades, the possibility to deceive a face recognition system is not widely studied. Despite of lower relative performance with respect to other biometrics, like fingerprint and iris recognition, face recognition proves to be a good basis for complete user friendly solutions [12], that makes it a perfect solution especially for low risk applications. However, its technology is intrinsically prone to spoof attacks. The main reason is that a biometric sample is a face represented in a digital image, which is intrinsically highly reproducible by several means like printed photos and electronic portable devices capable of showing images and videos (laptops, UMPCs and even cellular phones have nowadays wide and very good quality screens). In general, there are three possible ways to generate a face spoof attack [8]: generating a photograph of a valid user reproducing a video of a valid user presenting a 3D reproduction of the face of a valid user A few articles mention the video spoof attacks, but solutions are demanded to future researches [8]. To the best of our knowledge, there are no papers that regard 3D face reproductions without hardware assistance. Instead, 3D information is used only as a clue to detect photo attacks (e.g. the Lambertian surface in [1]). But in the next future this will be the next challenge in face spoofing also because nowadays some technologies exist to produce high quality wearable masks /11/$ IEEE

2 Obviously, these types of attacks can be easily detected with the help of specific hardware sensors (IR sensors, stereoscopic cameras), or with the use of multimodality (parallel use of different biometrics or serial approaches), or exploiting the interaction with the user (like challenge response). Besides, a face recognition system can be built with very low cost hardware, and it is particularly suitable for low risk application, therefore in these cases addition of specific hardware or interaction to ensure reliability is not necessarily an affordable solution. This implies that a simple photo spoofing attack can represent a security problem for a face recognition system. In fact, most of papers in the literature refer to the problem as a task of photo attack detection as it represents a cheap and effective way to perform an attack. Commonly cited papers refer to the problem of photo attack detection in two major complementary directions [8]: static analysis, based on the fundamental idea that during the manufacturing process of a photo attack a certain loss of information occurs and also peculiar noise is introduced. video analysis, that tries to detect, as humans do, facial physiological clues like blinks, mouth movements and changes in facial expression. Many static analysis approaches start from the observation that real sessions and reproductions may differ in high frequency details because of the loss of information [4]. Video analysis, conversely, rely on the information extracted from the sequences of images. In [8][1] blinks are used in order to assess vitality. Thus, face photo attacks can be detected through many state of the art algorithms that recognize physiological clues of vitality, such as facial expression variation, mouth movement, head rotation, eye change. However, also this kind of verification is not a definitive proof of vitality due to the possibility to easily reproduce videos of the real users. This implies that static and video analysis must be combined to ensure high reliability in detecting face spoofing attacks. In this work, we regard the problem of 2-D face spoofing attacks detection as a combination of several clues that result from both static and dynamic analysis of the scenes. Static analysis, that allows to detect photo attacks, is therefore reinforced with a video analysis based on motion and liveness clues. The paper is organized as follows: in section 2 we describe our approach with full details about static and video analysis and the fusion algorithm that we propose; section 3 describes experimental results on a photo attack dataset; finally in section 4 we draw our conclusions. 2. Fusion of multiple clues for face spoofing detection Most of the approaches proposed in literature are specifically designed to detect single aspects of vitality and nonvitality (physiological movements, printed photo details, manufacturing details detection), and in fact, with these regards, state of the art algorithms already prove excellent results. However, the reported performance are strictly linked to the specific kind of attack they refer to. For example, there are really good vitality detectors based on image movements that attackers can spoof by waving randomly a photo or by bending it [3] in order to generate non-rigid deformations. So datasets that don t provide this kind of behavior by attackers risk to result in algorithms with a little robustness against such a kind of attacker s adaptations. Besides, the datasets used in the experimental setups risk to be biased and therefore inevitable lack of universality in the datasets doesn t grant performance for real attacks. Our method is therefore a multi-clue algorithm that aims to avoid specificity and lack of universality. The major concern of this approach is that typical vitality features are often strictly correlated. Consequently, the contribute of fusion in a standard multiple classifier system framework is expected to be normally small in terms of performance, due to the fact that classic fusion schemes rely on the statistical independence between classifiers. However the contribution in terms of robustness can be highly significant. Therefore our aim is not only the search for good classification performance but also the search for the robustness in case an attacker manages to spoof the single methods. These facts lead to the rationale behind our method, that is, a fusion of static and video analysis is a strict requirement for spoof detection, provided that no other hardware detection system is available. The method consists of three steps: static feature extraction, video based feature extraction and score level fusion. We first collect a series of possible clues that we separated into two different categories: static features and video features. Then for each category we provide a set of selected scores that we fuse with the Dynamic Combination (DSC) methodology [11] Static Analysis The aim of static analysis is to discover some peculiarities related to the visual structure of the input samples used in the verification process. The basic idea is that differences exists in the visual information between data captured from a real scene, and from a photo or video attack. Basically, these differences can be captured directly from a single image or frame by frame if we are acquiring a video. This approach has the big advantage that it needs only

3 few images/frames in order to have an estimation of whether the input belongs to a real person or to a fake. Instead, in the case of vitality detection several seconds of video are needed to perform the analysis. As mentioned in the introduction, some papers exploit the loss of information at high frequency [4] to detect an attack. In this paper, instead, we propose to use different visual features that are usually used in the content based image retrieval field. Doing so, we are able to detect differences at different visual levels. The visual features that we propose to use are: Color and Edge Directivity Descriptor, Fuzzy Color and Texture Histogram, MPEG-7 Descriptors (like Scalable Color and Edge Histogram), Gabor Texture, Tamura Texture, RGB and HSV Histograms, and JPEG Histogram. These features take into account different visual aspects of an image. In this way we can represent each image with a set of different feature spaces. After obtaining the above mentioned representations, we can train (one for each feature space) a classifier. Thus, for each frame of a video and for each feature space we can obtain a similarity scores i,f with the class real user or face spoof attack through the classifier. Thus, for each frame we have N scores, where N is the number of visual features used. This allows to use Multiple Classifier System also at frame level. Moreover, if the input data is a video composed by M frames, through this schema we obtain for each videon M similarity scores. To obtain a single similarity score for the video we propose to use the Dynamic Combination (DSC) methodology [11]. s sa = (1 α) min{s i,f }+α max{s i,f } (1) This combination rule is able to perform a dynamic combination at score level, that results in the dynamic selection of the best scores and weights to be combined for each video. In [11] different methods to compute dynamically the weights α are presented. In this paper we propose a novel method to compute the weights for the DSC by reviewing the majority vote rule: for each videoαwill be the percentage of frames, among all the visual feature spaces, that are classified as a real user Video Analysis Video analysis, in our approach, is performed as combination of simple measures of movement using standard state of the art methods. Simplicity is the criterion that allows the chosen algorithms to be suitable for real-time or near realtime applications, Owing to our goal of making an online. liveness detection software. The first clue we look for in the video is the classic vitality clue, represented by blinks [8]. Blinks have been exploited for liveness detection in face recognition since the early works in literature. A wide set of publications show blink detection methods that provide excellent results. Blink detector used in this work is the one used in [7]. The original algorithm was modified in order to get a more robust localization through a set of heuristics and in order to work in a multi-threaded application. We take into account the possibility that the algorithm, as well as other state of the art blink detectors, may show a certain number of detection errors. In fact, a number of false detections was observed especially in hand photo attacks, where movement of the photo and light reflections can easily lead detector to some mistakes. It is worth noting that even if blinks are a proof of vitality, a total absence of blinks is not sufficient to infer that the video provided is an attack. On the other hand, this is perfectly acceptable, as it is a recurrent unconscious behavior for the cooperative users to keep steady during authentication. Conversely, for the same reasons, we also have to consider the case of failures to detect real blinks. Therefore a single blink will not be considered as a proof and increasing number of detections must correspond to an increasing confidence and strengthen the evidence of vitality. A normalized score is computed for each video as a function of the number of blinks. The values grow with the number of blinks and tend asymptotically to 1. Besides, for ordinary numbers of blinks, the function should output non-saturated scores in order to ensure the highest sensibility. The above mentioned considerations were taken into account with the introduction of a translation term and a scale factor α in the logistic function. Therefore, the score is computed as: s bl (n b ) = ( 2 1+e α n b ) 1 wheren b is the total number of blinks detected in the video. We then perform a second analysis on videos, based on the simple measure of movement in order to provide some evidence when very little movement is observed in the video. Of course this is a strong proof of non-vitality, but it occurs only when a photo attack is performed with a fixed printed photo. However, this measure tends to strengthen the algorithms when the attack is performed with a very high quality photo. Movement is measured on the foreground mask extracted from a classic motion detection system [5]. The movement scores m is computed through the average movement across the image (the quantity of movement assigned to each pixel): avg m = n mov n tot wheren mov is the number of moving pixels detected by the

4 motion detection and n tot is the total number of pixel in each image. Finally the score s m is computed through a normalization function, once again performed with the logistic function Fusion Fusion was performed at score level using a weighted sum: photo detection provided excellent results, therefore it was given a higher weight in combination; movement measures provided some contribute only for fixed photo attacks therefore the score is used only in case of very little movement. By taking into account the above considerations, we used the following score combination scheme: { s α ssa +(1 α) s = bl, ifs m is high α 1 s sa +α 2 s bl +α 3 s m, ifs m is low (2) where s sa is the score obtained by the static analysis proposed in Section 2.1, while s bl and s m are respectively the scores derived from the blink and motion detection described in Section Experiments For our experiments we used the Print-Attack Replay Database developed for the IJCB 211 Competition on counter measures to 2D facial spoofing attacks from the Idiap Research Institute 2. This dataset consists of 2 video clips of printed-photo attack attempts to 5 clients, under different lighting conditions. It also contains 2 realaccess attempt videos from the same clients. The data is split into 3 sub-groups: training (3% of the data), development (3% of the data), and test (4% of the data). Moreover, the clients that appear on the one of the dataset do not appear in any other set. The dataset were generated by either having a (real) client trying to access a laptop through a built-in webcam or by displaying a printed photo of the same client for at least 9 seconds (videos are acquired with a frame rate of 25 Hz). The photo attack was generated by using high-resolution photos from each client taken under the same conditions as in their authentication sessions. The attacks can be divided into two subsets. The first subset is composed of videos generated using a stand to hold the client printed photo ( fixed ). For the second set, the attacker holds the picture with their own hands. Moreover, all the data (real and attack) is divided in two categories: controlled, office light was turned on, blinds are down, background is homogenous; adverse, blinds up, more complex background, office lights are out. Following the competition instructions, we employed the training set to train our anti-spoof classifiers, the develop- 2 ment set for estimating thresholds and weights to be used in the final fusion scheme applied to the test set. For the static analysis we used the visual features cited in Section 2.1. And for the computation of the similarity scores we used different Support Vector Machines with a radial basis function for their kernels. The results of this analysis are plotted in Figure 1 in terms of score distributions of real access and spoofing attacks. From the figure is clear that both for the development and the test dataset the analysis proposed in Section 2.1 achieve a perfect separation Static Analysis: development dataset Static Analysis: test dataset Figure 1. distributions of the similarity scores obtained only from static analysis for spoofing attacks (in red) and real access (in blue). In Figure 2 we can clearly see that the vitality detection performed through blinks is able to distinguish between real accesses and spoofing attacks only if the number of blinks is high. If the number is low we can t infer that the proposed pattern is an attack due to some false detection rate and the fact that some real access shows no blinks. These

5 2 Blink Detection: development dataset 6 Total Movement distribution: developement dataset Number of Blinks 3 Blink Detection: test dataset Figure 3. Distribution of scores for movement analysis of the videos: the fixed attacks (in red) can highly distinguished from the hand attacks (in green) and the real access (in blue) Number of Blinks Figure 2. Distributions of number of blinks detected in the videos for spoofing attacks (in red) and real access (in blue). experimental results confirm what we claimed in 2.2: in the case of low vitality scores we can t claim that the access tentative is a fake/spoof. The motion detection score distributions depicted in Figure 3 allow to detect, for the development set, when a fixed hand attack is performed. These experimental results confirm the fusion schema proposed in Equation 2: when the motion is above a certain threshold we can t infer if the input video is from a real access or a spoofing attack. Finally, in Figure 4 we show the results of the formula proposed in section 2.3 in terms of score distributions. It can be clearly seen in the figures that a perfect separation of the score distributions can be achieved for both development set and test set (where the weights are estimated on the development set). By comparing Figure 1 and 4 it is clear that for this specific dataset the static analysis allows to obtain a bet- ter classification than the motion analysis. Nevertheless, we believe that a spoofing detection system must take into account also vitality and video analysis (even if in a small portion). 4. Conclusions In this work, we addressed the problem of photo detection within the context of automatic face verification systems. We proposed a linear fusion combination between static and video analysis. The video analysis was used to detect vitality and motion clues through state of the art algorithms. While a novel static analysis was used to find clues frame by frame. The proposed static analysis exploits different visual features and SVM classifiers through a dynamic score combination methodology and provides excellent results in terms of performance. The results achieved only with the static analysis point out that actually photo spoofing attacks can be easily detected by using this kind of analysis. Moreover, the proposed static analysis is able to work also by using only a single frame. This is a clear advantage with respect of other methods that also look for visual degradation clues, but they need to process a portion of video. Obviously, a biometric spoofing detector can t discard vitality information. Thus the proposed combination rule proposed in this paper allows to take into account different clues from the static and the video analysis by giving a better confidence on the classification results. As a part of future work, by considering the speed in the evolution of spoofing attacks and technologies, we will investigate other forms of 2-D and 3-D attacks for face spoofing.

6 Static and Video Analysis combination: development dataset Static and Video Analysis combination: test dataset Figure 4. distributions of the similarity scores obtained from the fusion schema proposed for spoofing attacks (in red) and real access (in blue). Acknowledgements [3] K. Kollreider, H. Fronthaler, and J. Bigun. Verifying liveness by multiple experts in face biometrics. In Computer Vision and Pattern Recognition Workshops, 28. CVPRW 8. IEEE Computer Society Conference on, pages 1 6, june 28. [4] J. Li, Y. Wang, T. Tan, and A. K. Jain. Live face detection based on the analysis of fourier spectra. In In Biometric Technology for Human Identification, pages , 24. [5] L. Li, W. Huang, I. Y. H. Gu, and Q. Tian. Foreground object detection from videos containing complex background. In In MULTIMEDIA 3: Proceedings of the eleventh ACM international conference on Multimedia, pages 2 1. ACM Press, 23. [6] T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino. Impact of Artificial Gummy Fingers on Fingerprint Systems. volume Society of Photo-optical Instrumentation Engineers, International Society for Optical Engineering, 22. [7] G. Pan, L. Sun, and Z. Wu. Eyeblink-based anti-spoofing in face recognition from a generic webcamera, 27. [8] G. Pan, Z. Wu, and L. Sun. Liveness detection for face recognition. In Recent Advances in Face Recognition, pages I-Tech, 28. [9] S. A. C. Schuckers, S. A. C. Schuckers, P. D, and P. D. Spoofing and anti-spoofing measures. Information Security Technical Report, 7:56 62, 22. [1] X. Tan, Y. Li, J. Liu, and L. Jiang. Face liveness detection from a single image with sparse low rank bilinear discriminative model. In Proceedings of the 11th European conference on Computer vision: Part VI, ECCV 1, pages , Berlin, Heidelberg, 21. Springer-Verlag. [11] R. Tronci, G. Giacinto, and F. Roli. Dynamic score combination: A supervised and unsupervised score combination method. In P. Perner, editor, Machine Learning and Data Mining in Pattern Recognition, volume 5632 of Lecture Notes in Computer Science, pages Springer Berlin / Heidelberg, 29. [12] W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld. Face recognition: A literature survey. ACM Computing Surveys, 35: , 23. This work was partially supported by the TABULA RASA project, 7th Framework Research Programme of the European Union (EU), grant agreement number: , and by the PRIN 28 project Biometric Guards - Electronic guards for protection and security of biometric systems funded by the Italian Ministry of University and Scientific Research (MIUR). References [1] M. Chau and M. Betke. Real time eye tracking and blink detection with usb cameras. Technical report, 25. [2] A. K. Jain, A. Ross, and S. Prabhakar. An introduction to biometric recognition. IEEE Trans. on Circuits and Systems for Video Technology, 14:4 2, 24.

Analysis and Selection of Features for the Fingerprint Vitality Detection

Analysis and Selection of Features for the Fingerprint Vitality Detection Analysis and Selection of Features for the Fingerprint Vitality Detection Pietro Coli, Gian Luca Marcialis, and Fabio Roli Department of Electrical and Electronic Engineering University of Cagliari Piazza

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

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

Masked Face Detection based on Micro-Texture and Frequency Analysis

Masked Face Detection based on Micro-Texture and Frequency Analysis International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015 INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Masked

More information

Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks

Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks Neslihan Kose, Jean-Luc Dugelay Multimedia Department EURECOM Sophia-Antipolis, France {neslihan.kose, jean-luc.dugelay}@eurecom.fr

More information

THE AMBIENT INTELLIGENCE LABORATORY OF THE SARDEGNA DISTRICT

THE AMBIENT INTELLIGENCE LABORATORY OF THE SARDEGNA DISTRICT THE AMBIENT INTELLIGENCE LABORATORY OF THE SARDEGNA DISTRICT Roberto Tronci, Gabriele Murgia, Maurizio Pili, Marco Ristori, Nicola Sirena, Fabio Roli AmILAB - Laboratorio Intelligenza d Ambiente, Sardegna

More information

Multi-feature face liveness detection method combining motion information

Multi-feature face liveness detection method combining motion information Volume 04 - Issue 11 November 2018 PP. 36-40 Multi-feature face liveness detection method combining motion information Changlin LI (School of Computer Science and Technology, University of Science and

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

ENHANCEMENT OF KERNEL DISCRIMINATIVE ANALYSIS (KDA) IN FACE. SPOOFING DETECTION METHOD S.Menaka, E.P.Prakash, V.Dhinakari

ENHANCEMENT OF KERNEL DISCRIMINATIVE ANALYSIS (KDA) IN FACE. SPOOFING DETECTION METHOD S.Menaka, E.P.Prakash, V.Dhinakari ENHANCEMENT OF KERNEL DISCRIMINATIVE ANALYSIS (KDA) IN FACE ABSTRACT SPOOFING DETECTION METHOD S.Menaka, E.P.Prakash, V.Dhinakari 1 PG Student, SNS College Of Engineering, Coimbatore 2 Assistant Professor,

More information

Face Spoofing Detection from a Single Image using Diffusion Speed Model

Face Spoofing Detection from a Single Image using Diffusion Speed Model 2018 IJSRST Volume 4 Issue 2 Print ISSN: 2395-6011 Online ISSN: 2395-602X Themed Section: Science and Technology Face Spoofing Detection from a Single Image using Diffusion Speed Model K. Sreenivasulu

More information

Color Local Texture Features Based Face Recognition

Color Local Texture Features Based Face Recognition Color Local Texture Features Based Face Recognition Priyanka V. Bankar Department of Electronics and Communication Engineering SKN Sinhgad College of Engineering, Korti, Pandharpur, Maharashtra, India

More information

IMPROVED FACE RECOGNITION USING ICP TECHNIQUES INCAMERA SURVEILLANCE SYSTEMS. Kirthiga, M.E-Communication system, PREC, Thanjavur

IMPROVED FACE RECOGNITION USING ICP TECHNIQUES INCAMERA SURVEILLANCE SYSTEMS. Kirthiga, M.E-Communication system, PREC, Thanjavur IMPROVED FACE RECOGNITION USING ICP TECHNIQUES INCAMERA SURVEILLANCE SYSTEMS Kirthiga, M.E-Communication system, PREC, Thanjavur R.Kannan,Assistant professor,prec Abstract: Face Recognition is important

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

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

Spoofing Face Recognition Using Neural Network with 3D Mask

Spoofing Face Recognition Using Neural Network with 3D Mask Spoofing Face Recognition Using Neural Network with 3D Mask REKHA P.S M.E Department of Computer Science and Engineering, Gnanamani College of Technology, Pachal, Namakkal- 637018. rekhaps06@gmail.com

More information

Face Liveness Detection Based on Texture and Frequency Analyses

Face Liveness Detection Based on Texture and Frequency Analyses Face Liveness Detection Based on Texture and Frequency Analyses Gahyun Kim 1, Sungmin Eum 1, Jae Kyu Suhr 2, Dong Ik Kim 1, Kang Ryoung Park 3 and Jaihie Kim 1 1 School of Electrical and Electronic Engineering,

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

Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction

Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali University of Louisville Louisville, KY {hmrara01,syelha01,amali003}@louisville.edu Mike Miller,

More information

An Introduction to Content Based Image Retrieval

An Introduction to Content Based Image Retrieval CHAPTER -1 An Introduction to Content Based Image Retrieval 1.1 Introduction With the advancement in internet and multimedia technologies, a huge amount of multimedia data in the form of audio, video and

More information

Reference Point Detection for Arch Type Fingerprints

Reference Point Detection for Arch Type Fingerprints Reference Point Detection for Arch Type Fingerprints H.K. Lam 1, Z. Hou 1, W.Y. Yau 1, T.P. Chen 1, J. Li 2, and K.Y. Sim 2 1 Computer Vision and Image Understanding Department Institute for Infocomm Research,

More information

Counter-Measures to Photo Attacks in Face Recognition: a public database and a baseline

Counter-Measures to Photo Attacks in Face Recognition: a public database and a baseline Counter-Measures to Photo Attacks in Face Recognition: a public database and a baseline André Anjos and Sébastien Marcel Idiap Research Institute Centre du Parc - rue Marconi 9 CH-90 Martigny, Suisse {andre.anjos,sebastien.marcel}@idiap.ch

More information

An Adaptive Threshold LBP Algorithm for Face Recognition

An Adaptive Threshold LBP Algorithm for Face Recognition An Adaptive Threshold LBP Algorithm for Face Recognition Xiaoping Jiang 1, Chuyu Guo 1,*, Hua Zhang 1, and Chenghua Li 1 1 College of Electronics and Information Engineering, Hubei Key Laboratory of Intelligent

More information

Multimodal Anti-Spoofing in Biometric Recognition Systems

Multimodal Anti-Spoofing in Biometric Recognition Systems Multimodal Anti-Spoofing in Biometric Recognition Systems Giorgio Fumera, Gian Luca Marcialis, Battista Biggio, Fabio Roli and Stephanie Caswell Schuckers Abstract While multimodal biometric systems were

More information

LivDet 2011 Fingerprint Liveness Detection Competition 2011

LivDet 2011 Fingerprint Liveness Detection Competition 2011 LivDet 11 Fingerprint Liveness Detection Competition 11 David Yambay 1, Luca Ghiani 2, Paolo Denti 2, Gian Luca Marcialis 2, Fabio Roli 2, S Schuckers 1 1 Clarkson University - Department of Electrical

More information

A Novel Approach to Improve the Biometric Security using Liveness Detection

A Novel Approach to Improve the Biometric Security using Liveness Detection Volume 8, No. 5, May June 2017 International Journal of Advanced Research in Computer Science RESEARCH PAPER Available Online at www.ijarcs.info ISSN No. 0976-5697 A Novel Approach to Improve the Biometric

More information

Robust & Accurate Face Recognition using Histograms

Robust & Accurate Face Recognition using Histograms Robust & Accurate Face Recognition using Histograms Sarbjeet Singh, Meenakshi Sharma and Dr. N.Suresh Rao Abstract A large number of face recognition algorithms have been developed from decades. Face recognition

More information

Video Inter-frame Forgery Identification Based on Optical Flow Consistency

Video Inter-frame Forgery Identification Based on Optical Flow Consistency Sensors & Transducers 24 by IFSA Publishing, S. L. http://www.sensorsportal.com Video Inter-frame Forgery Identification Based on Optical Flow Consistency Qi Wang, Zhaohong Li, Zhenzhen Zhang, Qinglong

More information

Critique: Efficient Iris Recognition by Characterizing Key Local Variations

Critique: Efficient Iris Recognition by Characterizing Key Local Variations Critique: Efficient Iris Recognition by Characterizing Key Local Variations Authors: L. Ma, T. Tan, Y. Wang, D. Zhang Published: IEEE Transactions on Image Processing, Vol. 13, No. 6 Critique By: Christopher

More information

Face anti-spoofing using Image Quality Assessment

Face anti-spoofing using Image Quality Assessment Face anti-spoofing using Image Quality Assessment Speakers Prisme Polytech Orléans Aladine Chetouani R&D Trusted Services Emna Fourati Outline Face spoofing attacks Image Quality Assessment Proposed method

More information

Finger Vein Biometric Approach for Personal Identification Using IRT Feature and Gabor Filter Implementation

Finger Vein Biometric Approach for Personal Identification Using IRT Feature and Gabor Filter Implementation Finger Vein Biometric Approach for Personal Identification Using IRT Feature and Gabor Filter Implementation Sowmya. A (Digital Electronics (MTech), BITM Ballari), Shiva kumar k.s (Associate Professor,

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

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

EFFECTIVE METHODOLOGY FOR DETECTING AND PREVENTING FACE SPOOFING ATTACKS

EFFECTIVE METHODOLOGY FOR DETECTING AND PREVENTING FACE SPOOFING ATTACKS EFFECTIVE METHODOLOGY FOR DETECTING AND PREVENTING FACE SPOOFING ATTACKS 1 Mr. Kaustubh D.Vishnu, 2 Dr. R.D. Raut, 3 Dr. V. M. Thakare 1,2,3 SGBAU, Amravati,Maharashtra, (India) ABSTRACT Biometric system

More information

Real time facial expression recognition from image sequences using Support Vector Machines

Real time facial expression recognition from image sequences using Support Vector Machines Real time facial expression recognition from image sequences using Support Vector Machines I. Kotsia a and I. Pitas a a Aristotle University of Thessaloniki, Department of Informatics, Box 451, 54124 Thessaloniki,

More information

Face Liveness Detection Using Euler Method Based On Diffusion Speed Calculation

Face Liveness Detection Using Euler Method Based On Diffusion Speed Calculation Face Liveness Detection Using Euler Method Based On Diffusion Speed Calculation 1 Ms. Nishigandha S. Bondare, 2 Mr. P.S.Mohod 1 M.Tech Student, Department of CSE, G.H.Raisoni College of Engineering, Nagpur,

More information

Graph Geometric Approach and Bow Region Based Finger Knuckle Biometric Identification System

Graph Geometric Approach and Bow Region Based Finger Knuckle Biometric Identification System _ Graph Geometric Approach and Bow Region Based Finger Knuckle Biometric Identification System K.Ramaraj 1, T.Ummal Sariba Begum 2 Research scholar, Assistant Professor in Computer Science, Thanthai Hans

More information

Combining Gabor Features: Summing vs.voting in Human Face Recognition *

Combining Gabor Features: Summing vs.voting in Human Face Recognition * Combining Gabor Features: Summing vs.voting in Human Face Recognition * Xiaoyan Mu and Mohamad H. Hassoun Department of Electrical and Computer Engineering Wayne State University Detroit, MI 4822 muxiaoyan@wayne.edu

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

Liveness Detection for Face Recognition in Biometrics: A Review

Liveness Detection for Face Recognition in Biometrics: A Review Liveness Detection for Face Recognition in Biometrics: A Review Meenakshi Saini 1, Dr. Chander Kant 2 1,2 (Department Of Computer Science and Applications, Kurukshetra University, Kurukshetra, India) (

More information

Computationally Efficient Face Spoofing Detection with Motion Magnification

Computationally Efficient Face Spoofing Detection with Motion Magnification Computationally Efficient Face Spoofing Detection with Motion Samarth Bharadwaj, Tejas I. Dhamecha, Mayank Vatsa and Richa Singh IIIT-Delhi, India {samarthb, tejasd, mayank, rsingh}@iiitd.ac.in Abstract

More information

Visible and Long-Wave Infrared Image Fusion Schemes for Situational. Awareness

Visible and Long-Wave Infrared Image Fusion Schemes for Situational. Awareness Visible and Long-Wave Infrared Image Fusion Schemes for Situational Awareness Multi-Dimensional Digital Signal Processing Literature Survey Nathaniel Walker The University of Texas at Austin nathaniel.walker@baesystems.com

More information

Figure 1. Example sample for fabric mask. In the second column, the mask is worn on the face. The picture is taken from [5].

Figure 1. Example sample for fabric mask. In the second column, the mask is worn on the face. The picture is taken from [5]. ON THE VULNERABILITY OF FACE RECOGNITION SYSTEMS TO SPOOFING MASK ATTACKS Neslihan Kose, Jean-Luc Dugelay Multimedia Department, EURECOM, Sophia-Antipolis, France {neslihan.kose, jean-luc.dugelay}@eurecom.fr

More information

Fingerprint verification by decision-level fusion of optical and capacitive sensors

Fingerprint verification by decision-level fusion of optical and capacitive sensors Fingerprint verification by decision-level fusion of optical and capacitive sensors Gian Luca Marcialis and Fabio Roli Department of Electrical and Electronic Engineering University of Cagliari Piazza

More information

Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition

Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition Sikha O K 1, Sachin Kumar S 2, K P Soman 2 1 Department of Computer Science 2 Centre for Computational Engineering and

More information

arxiv: v2 [cs.cv] 26 Aug 2014

arxiv: v2 [cs.cv] 26 Aug 2014 Learn Convolutional Neural Network for Face Anti-Spoofing Jianwei Yang, Zhen Lei and Stan Z. Li arxiv:48.56v2 [cs.cv] 26 Aug 24 Abstract Though having achieved some progresses, the hand-crafted texture

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

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

ANTI-SPOOFING AND AUTHENTICATION OF A FACE IMAGE USING DIFFUSION SPEED MODEL

ANTI-SPOOFING AND AUTHENTICATION OF A FACE IMAGE USING DIFFUSION SPEED MODEL ANTI-SPOOFING AND AUTHENTICATION OF A FACE IMAGE USING DIFFUSION SPEED MODEL Athira Prem 1, Bineesh. V 2 1,2Department of Computer Science and Engineering, MEA Engineering College, Calicut University,

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

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

An Overview of Matchmoving using Structure from Motion Methods

An Overview of Matchmoving using Structure from Motion Methods An Overview of Matchmoving using Structure from Motion Methods Kamyar Haji Allahverdi Pour Department of Computer Engineering Sharif University of Technology Tehran, Iran Email: allahverdi@ce.sharif.edu

More information

Texture Image Segmentation using FCM

Texture Image Segmentation using FCM Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Texture Image Segmentation using FCM Kanchan S. Deshmukh + M.G.M

More information

Survey of Various Face Liveness Detection Techniques for Biometric Antispoofing Applications

Survey of Various Face Liveness Detection Techniques for Biometric Antispoofing Applications www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 6 Issue 4 April 2017, Page No. 21120-21125 Index Copernicus value (2015): 58.10 DOI: 10.18535/ijecs/v6i4.55

More information

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images Karthik Ram K.V & Mahantesh K Department of Electronics and Communication Engineering, SJB Institute of Technology, Bangalore,

More information

Shape and Texture Based Countermeasure to Protect Face Recognition Systems Against Mask Attacks

Shape and Texture Based Countermeasure to Protect Face Recognition Systems Against Mask Attacks 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Shape and Texture Based Countermeasure to Protect Face Recognition Systems Against Mask Attacks Neslihan Kose and Jean-Luc Dugelay

More information

AN OVERVIEW OF FACE LIVENESS DETECTION

AN OVERVIEW OF FACE LIVENESS DETECTION AN OVERVIEW OF FACE LIVENESS DETECTION Saptarshi Chakraborty 1 and Dhrubajyoti Das 2 1,2 Dept. of Computer Science and Engineering, National Institute of Technology, Silchar, India ABSTRACT Face recognition

More information

An efficient face recognition algorithm based on multi-kernel regularization learning

An efficient face recognition algorithm based on multi-kernel regularization learning Acta Technica 61, No. 4A/2016, 75 84 c 2017 Institute of Thermomechanics CAS, v.v.i. An efficient face recognition algorithm based on multi-kernel regularization learning Bi Rongrong 1 Abstract. A novel

More information

Complementary Countermeasures for Detecting Scenic Face Spoofing Attacks

Complementary Countermeasures for Detecting Scenic Face Spoofing Attacks Complementary Countermeasures for Detecting Scenic Face Spoofing Attacks Jukka Komulainen, Abdenour Hadid, Matti Pietikäinen Center for Machine Vision Research, University of Oulu P.O. Box 4500 FI-90014

More information

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN 2016 International Conference on Artificial Intelligence: Techniques and Applications (AITA 2016) ISBN: 978-1-60595-389-2 Face Recognition Using Vector Quantization Histogram and Support Vector Machine

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

Screen Fingerprints: A Novel Modality for Active Authentication

Screen Fingerprints: A Novel Modality for Active Authentication Security: DArPA Screen Fingerprints: A Novel Modality for Active Authentication Vishal M. Patel, University of Maryland, College Park Tom Yeh, University of Colorado, Boulder Mohammed E. Fathy and Yangmuzi

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

Tri-modal Human Body Segmentation

Tri-modal Human Body Segmentation Tri-modal Human Body Segmentation Master of Science Thesis Cristina Palmero Cantariño Advisor: Sergio Escalera Guerrero February 6, 2014 Outline 1 Introduction 2 Tri-modal dataset 3 Proposed baseline 4

More information

A Systematic Analysis of Face and Fingerprint Biometric Fusion

A Systematic Analysis of Face and Fingerprint Biometric Fusion 113 A Systematic Analysis of Face and Fingerprint Biometric Fusion Sukhchain Kaur 1, Reecha Sharma 2 1 Department of Electronics and Communication, Punjabi university Patiala 2 Department of Electronics

More information

Dr. Enrique Cabello Pardos July

Dr. Enrique Cabello Pardos July Dr. Enrique Cabello Pardos July 20 2011 Dr. Enrique Cabello Pardos July 20 2011 ONCE UPON A TIME, AT THE LABORATORY Research Center Contract Make it possible. (as fast as possible) Use the best equipment.

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

Medical images, segmentation and analysis

Medical images, segmentation and analysis Medical images, segmentation and analysis ImageLab group http://imagelab.ing.unimo.it Università degli Studi di Modena e Reggio Emilia Medical Images Macroscopic Dermoscopic ELM enhance the features of

More information

Dynamic Human Fatigue Detection Using Feature-Level Fusion

Dynamic Human Fatigue Detection Using Feature-Level Fusion Dynamic Human Fatigue Detection Using Feature-Level Fusion Xiao Fan, Bao-Cai Yin, and Yan-Feng Sun Beijing Key Laboratory of Multimedia and Intelligent Software, College of Computer Science and Technology,

More information

Semi-Fragile Watermarking in Biometric Systems: Template Self-Embedding

Semi-Fragile Watermarking in Biometric Systems: Template Self-Embedding Semi-Fragile Watermarking in Biometric Systems: Template Self-Embedding Reinhard Huber 1, Herbert Stögner 1, and Andreas Uhl 1,2 1 School of CEIT, Carinthia University of Applied Sciences, Austria 2 Department

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

Enhanced Iris Recognition System an Integrated Approach to Person Identification

Enhanced Iris Recognition System an Integrated Approach to Person Identification Enhanced Iris Recognition an Integrated Approach to Person Identification Gaganpreet Kaur Research Scholar, GNDEC, Ludhiana. Akshay Girdhar Associate Professor, GNDEC. Ludhiana. Manvjeet Kaur Lecturer,

More information

A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods

A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.5, May 2009 181 A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods Zahra Sadri

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

Time Analysis of Pulse-based Face Anti-Spoofing in Visible and NIR

Time Analysis of Pulse-based Face Anti-Spoofing in Visible and NIR Time Analysis of Pulse-based Face Anti-Spoofing in Visible and NIR Javier Hernandez-Ortega, Julian Fierrez, Aythami Morales, and Pedro Tome Biometrics and Data Pattern Analytics BiDA Lab Universidad Autónoma

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

ILLUMINATION NORMALIZATION USING LOCAL GRAPH STRUCTURE

ILLUMINATION NORMALIZATION USING LOCAL GRAPH STRUCTURE 3 st January 24. Vol. 59 No.3 25-24 JATIT & LLS. All rights reserved. ILLUMINATION NORMALIZATION USING LOCAL GRAPH STRUCTURE HOUSAM KHALIFA BASHIER, 2 LIEW TZE HUI, 3 MOHD FIKRI AZLI ABDULLAH, 4 IBRAHIM

More information

Detecting motion by means of 2D and 3D information

Detecting motion by means of 2D and 3D information Detecting motion by means of 2D and 3D information Federico Tombari Stefano Mattoccia Luigi Di Stefano Fabio Tonelli Department of Electronics Computer Science and Systems (DEIS) Viale Risorgimento 2,

More information

Latest development in image feature representation and extraction

Latest development in image feature representation and extraction International Journal of Advanced Research and Development ISSN: 2455-4030, Impact Factor: RJIF 5.24 www.advancedjournal.com Volume 2; Issue 1; January 2017; Page No. 05-09 Latest development in image

More information

FACE DETECTION AND RECOGNITION OF DRAWN CHARACTERS HERMAN CHAU

FACE DETECTION AND RECOGNITION OF DRAWN CHARACTERS HERMAN CHAU FACE DETECTION AND RECOGNITION OF DRAWN CHARACTERS HERMAN CHAU 1. Introduction Face detection of human beings has garnered a lot of interest and research in recent years. There are quite a few relatively

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

Face Quality Assessment System in Video Sequences

Face Quality Assessment System in Video Sequences Face Quality Assessment System in Video Sequences Kamal Nasrollahi, Thomas B. Moeslund Laboratory of Computer Vision and Media Technology, Aalborg University Niels Jernes Vej 14, 9220 Aalborg Øst, Denmark

More information

Eye Detection by Haar wavelets and cascaded Support Vector Machine

Eye Detection by Haar wavelets and cascaded Support Vector Machine Eye Detection by Haar wavelets and cascaded Support Vector Machine Vishal Agrawal B.Tech 4th Year Guide: Simant Dubey / Amitabha Mukherjee Dept of Computer Science and Engineering IIT Kanpur - 208 016

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

Generic Face Alignment Using an Improved Active Shape Model

Generic Face Alignment Using an Improved Active Shape Model Generic Face Alignment Using an Improved Active Shape Model Liting Wang, Xiaoqing Ding, Chi Fang Electronic Engineering Department, Tsinghua University, Beijing, China {wanglt, dxq, fangchi} @ocrserv.ee.tsinghua.edu.cn

More information

Mobile Human Detection Systems based on Sliding Windows Approach-A Review

Mobile Human Detection Systems based on Sliding Windows Approach-A Review Mobile Human Detection Systems based on Sliding Windows Approach-A Review Seminar: Mobile Human detection systems Njieutcheu Tassi cedrique Rovile Department of Computer Engineering University of Heidelberg

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

Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation

Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation Graph-Based Superpixel Labeling for Enhancement of Online Video Segmentation Alaa E. Abdel-Hakim Electrical Engineering Department Assiut University Assiut, Egypt alaa.aly@eng.au.edu.eg Mostafa Izz Cairo

More information

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK 1 Po-Jen Lai ( 賴柏任 ), 2 Chiou-Shann Fuh ( 傅楸善 ) 1 Dept. of Electrical Engineering, National Taiwan University, Taiwan 2 Dept.

More information

Secure Learning Algorithm for Multimodal Biometric Systems against Spoof Attacks

Secure Learning Algorithm for Multimodal Biometric Systems against Spoof Attacks 2011 International Conference on Information and etwork Technology IPCSIT vol.4 (2011) (2011) IACSIT Press, Singapore Secure Learning Algorithm for Multimodal Biometric Systems against Spoof Attacks Zahid

More information

McPAD and HMM-Web: two different approaches for the detection of attacks against Web applications

McPAD and HMM-Web: two different approaches for the detection of attacks against Web applications McPAD and HMM-Web: two different approaches for the detection of attacks against Web applications Davide Ariu, Igino Corona, Giorgio Giacinto, Fabio Roli University of Cagliari, Dept. of Electrical and

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

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

International Journal of Advanced Research in Computer Science and Software Engineering

International Journal of Advanced Research in Computer Science and Software Engineering Volume 3, Issue 2, February 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Level of Fusion

More information

A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b and Guichi Liu2, c

A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b and Guichi Liu2, c 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2015) A Background Modeling Approach Based on Visual Background Extractor Taotao Liu1, a, Lin Qi2, b

More information

Multimodal Information Spaces for Content-based Image Retrieval

Multimodal Information Spaces for Content-based Image Retrieval Research Proposal Multimodal Information Spaces for Content-based Image Retrieval Abstract Currently, image retrieval by content is a research problem of great interest in academia and the industry, due

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

Use of Mean Square Error Measure in Biometric Analysis of Fingerprint Tests

Use of Mean Square Error Measure in Biometric Analysis of Fingerprint Tests Journal of Information Hiding and Multimedia Signal Processing c 2015 ISSN 2073-4212 Ubiquitous International Volume 6, Number 5, September 2015 Use of Mean Square Error Measure in Biometric Analysis of

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

Dynamic skin detection in color images for sign language recognition

Dynamic skin detection in color images for sign language recognition Dynamic skin detection in color images for sign language recognition Michal Kawulok Institute of Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland michal.kawulok@polsl.pl

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