DSW Feature Based Hidden Marcov Model: An Application on Object Identification

Size: px
Start display at page:

Download "DSW Feature Based Hidden Marcov Model: An Application on Object Identification"

Transcription

1 DSW Feature Based Hidden Marcov Model: An Application on Obect Identification Zheng Liang 1, Wang Taiqing 1, Wang Shengin 1 and Ding Xiaoqing 1 1 State Key Laboratory of Intelligent Technology and Systems 1 Department of Electronic Engineering, Tsinghua University, Beiing, , P.R.China zheng-l06@mails.tsinghua.edu.cn, wgsg@tsinghua.edu.cn Abstract This paper proposes to perform palmprint identification with Hidden Markov Models (HMM). Palmprint identification, as an emerging biometric technology, has been extensively investigated in the last decade. Due to its low-price capture device, fast implementation speed and high accuracy, palmprint identification is very competitive in biometric research area. Currently, the maority of literatures focus on palm line extraction algorithms and coding schemes, with little attention on classifier design. In this paper, Down-sliding Window (DSW) technique is employed to create a highcorrelated feature sequence while palmprint is featured by simple down-sampled images. One-to-50 experiment demonstrates that HMM with single component and six states give the best overall performance 99.80%, which indicates the feasibility of HMMs for tasks in palmprint identification. Keywords: palmprint identification; Hidden Markov Model; Down-SlidingWindow I. INTRODUCTION Palmprint identification has been arousing considerable amount of research interest in biometric field. This novel technique possesses pivotal qualities as a biometric system [1]: universality, distinctiveness, permanence, collectability. Compared with other biometric features, e.g., fingerprint, face and signature, palmprint is high in execution speed and performance, more discriminative, more acceptable, while requiring cheaper collection devices. Palmprint, the inner surface of palm, contains many unique features for recognition, such as principal lines, wrinkles, ridges, minutiae point and texture [2]. With the increasing interest in online biometric technology, lowresolution (less than 100 dpi) conditioned recognition has been a research focus. In this case, principal lines and wrinkles are most clearly observable features and a variety of research feature extraction methods have been proposed. In the texture-based methods, features are extracted by Gabor filter [3], the wavelet [4], or the ordinal filter [5]. In the palm line-based methods, the slope and intercept [6] are used. Meanwhile, coding-based approaches are among the most promising algorithms, such as PalmCode [7], Fusion Code [8], Competitive Code [6], etc. Nevertheless, the maority of recent work focuses on feature extraction and coding algorithms, with little, if any, attention on classifier design. Therefore, this paper is attempts to address the issue of palmprint identification from the point view of classifiers. Hidden Markov Model (HMM) is a statistical Markov model in which the system being modeled is assumed to be a Markov process with unobserved (hidden) states. HMM has been employed in various pattern recognition tasks such as face recognition [9], speech recognition [10], bioinformatics, etc. To the best of our knowledge, reference [11] is the only work attempting to address this issue by means of HMM. They report a continuous HMM, with Sobel operators followed by x-y proection as feature. A critical issue of HMM is to extract a highly correlated feature sequence, upon which a generative HMM model could be built. II. HIDDEN MARKOV MODEL Hidden Markov Model (HMM) is a statistical model in which assumes the system to be a Markov process whose states cannot be explicitly observed. For one hand, these states are related through a Markov process rather than independent of each other. For the other, each state has an associated probability distribution function, modeling the probability of emitting symbols from that state. Formally speaking, a discrete-time HMM could be defined as: N, M, A, B, (1) where N and M are number of states (denoted by q 1, q2,..., q N ) and number of different observation symbols per state (denoted by v 1, v2,..., vn ), respectively. The transition matrix A a i 1 i, N represents the probability of going from state q i to state q. The emission matrix B b k, 1 N, 1 k M denotes the emission probability of observation symbol v k at state q. i, 1 i Nstands for the initial state probability distribution in which 0 i 1is the initial probability of state qi and i i 1. This paper employ continuous HMM: the emission matrix is represented by mixture of finite Gaussian distribution, i.e /11/$26.00 c 2011 IEEE 502

2 M b ( O) c m1 where GO, and covariance.,,, 1 N G O (2), denotes a Gaussian density of mean In the model-training phase, given a set of observation sequences O i, standard Baum-Welch (a special case of EM algorithm) is employed to adust the model parameters to maximize P O. The parameter learning task is to find the best set of state transition and output probabilities. The training procedure is stopped after the convergence of the likelihood. The evaluation procedure, i.e. the computation of P O, given a model and a new observation sequence O, is performed using the forward-backward algorithm. This task is to compute the probability of a particular output sequence, which requires the summation over all possible state sequences. III. FEATURE EXTRACTION By adopting HMM for palmprint identification, it is of vital importance to extract features and rearrange them into a highly correlated observation sequence. For this, we employ the Down Sliding Window (DSW) algorithm first discussed by [13]. This sampling technique has been used in face recognition. The principle of this algorithm requires the target has some intrinsic fixed pattern in certain direction, such as face. Palmprint also has such quality, so it is feasible to transplant this method onto palmprint identification. As illustrated in Fig.1, a Down Sliding Window is employed to a YX image. A one-dimensional (1D) vector series of pixel observations O O1O 2... OT is generated, in which each observation Oi consists of the pixels in the LX block arranged into a column vector. Therefore, each observation vector is a block of L lines and there is a K-line overlap between successive observations. Thus, the length of the observation sequence O is given by: Y L T 1 (3) L K Assume that normalized palm images are placed as Fig.1, thus pixel blocks would appear in a predictable order. As a result, a left-right (non-ergodic) model could be built, in which only transitions between adacent states in a topbottom manner are allowed, as in Fig.2. Two stages are involved in HMM-based palmprint identification: training and testing. In the training procedure, a set of HMM parameters is trained on every palmprint category C i. Firstly, extract observation sequence of palmprint in C i. Secondly, from these sequences, compute HMM parameter i of this category by Baum-Welch algorithm. Finally, store HMM parameters of every class. Figure 1. DSW sampling technique Figure 2. State transition of an N-state left-right HMM In the testing procedure, first extract the observation vector of the palmprint under test. Then, for every HMM trained before, compute the probability of the presence of the current image in every HMM. Finally, find the maximum probability, and take the class index C i of the maximum value as recognition result. IV. EXPERIMENTAL RESULTS AND DISCUSSIONS All the experiments are performed on the Hong Kong PolyU palmprint database (version 2), which contains 7752 images captured from 193 individuals, 386 palms [12]. In this paper, for simplicity, we adopt a sub-database of palmprint of 50 random individuals. Fig.3 shows two examples from PolyU database. In section B, we employ images collected in the first session (10 images per person on average), in which a random 5 images are used for training, the rest for testing. In section C, D and E, we use all images (20 images per person on average), 10 for training (5 from session 1, 5 from session 2), the rest for testing. A. Preprocessing In palmprint recognition, preprocessing is a crucial step. The key point of preprocessing is to precisely locate reference points in the presence of transition and rotation during capture process. In this paper, the preprocessing procedure consists of six steps. (1) Low-pass Gaussian filter followed by binarization. (2) Morphological operations to eliminate noise. (3) Boundary tracking, then remove psudo-boundaries. (4) Locate two U-shaped areas between index and middle finger, ring and little finger. Find the common tangent of 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR) 503

3 these two areas, thus the tangency points are the critical points. (5) Build coordinate system and rotate the image. (6) Crop region-of-interest (ROI). The main preprocessing steps are illustrated in Fig.4. B. Find Optimal Number of States and Gaussian Mixtures First and foremost, this paper attempts to seek the optimal HMM states number N and Gaussian mixture number M. We assume N, M fall into the following range: 3 N 81 M 4 Experiment is performed with 50 randomly selected palmprint classes. For every class, we adopt those of the first collection session (10 on average), in which 5 was used for training, the rest for testing. We obtained 50 HMM parameters for new sample classification. The normalized images are 6464 in size, 8-bit gray scale. According to section III, every pixel block has a width of 64 pixels, height of 4 pixels, with step length of 4 pixels (0 overlap of adacent blocks). Therefore, parameters in Fig.1 are defined as: X 64 Y 64L 4K 0. Every individual, on average, generates 5 observations, with which a HMM with N states, M Gaussian mixtures is trained. The rest 5 images are used for testing. Experiment result is shown in Fig.5. From Fig.5, when state number N = 6, Gaussian mixture number M = 1, or N = 7, M = 1, identification rate exceeds 99%. Meanwhile, it is obvious that given state number N (except N = 4), single Gaussian mixture (dark blue bar) outperforms multi Gaussian mixtures in terms of recognition rate. This result indicates the efficiency of single Gauss function in describing data distribution. In the following experiments, we adopt M = 1, i.e. using single Gauss model to depict the distribution of continuous observation sequence. C. Varying Overlap K If there is no overlap between adacent pixel blocks, palmprint images would be partitioned into a serious of isolated, arbitrary observation sequences. In this case, some discriminating features might be cut out. In a top-bottom model without overlap, successful results depend on accurate alignment of feature sequences. However, in reality, due to some preprocessing error, feature areas are not the same for all images. On the other hand, allowing overlap during sampling may result in two functions: (1) Finer step length helps to avoid dropping important feature blocks. Therefore, larger overlap eases the effort to find feature area distribution. (2) Given palmprint image size and height of the pixel block, K determines the length of the observation sequence. Larger K results in longer observation sequence T, for palmprint is over-sampled. In fact, estimation of HMM parameters is closely related to the length of T. Smaller T means fewer occurrences of model events, which leads to worse estimation result, either is recognition accuracy. So it is of intuition that using a larger K would be advantageous. Figure 3. Two examples of PolyU database Figure 4. Palmprint preprocessing: (a) original image. (b) low-pass gaussian filter. (c) binarization. (d) morphological operations. (e) boundary tracking. (f) reference point location. (g) rotation. (h) cropping Figure 5. Recognition rate under different values of states number and Gaussian mixture number. To study the influence of overlap K on recognition accuracy, this paper first set N = 6 (according to section B). Then we varied the height of sampling window L, where 2 L 8, and 0 K L 1. Two representative results are shown in Fig.6. Fig.6 shows that, when overlap K increase, palmprint recognition error tends to decrease, which is consistent to initial expectation. But on the other hand, larger K results in larger T, and a time complexity of HMM is O (T ), so recognition time would increase linearly with K. Notably, under current parameter assumption (N = 6, M = 1, L = 4), when K = 3, recognition rate achieves 99.80%. D. Varying Window Height L The height of sliding window L mainly has 2 functions. First, L determines the feature dimension. Second, given International Conference of Soft Computing and Pattern Recognition (SoCPaR)

4 image size and overlap K, L determines the length of observation sequence T. To study the influence of window height on system performance, we consider two situations: no overlap (K = 0) and maximum overlap (K = N-1). We keep state number and Gaussian mixture number at N = 6 and M = 1, respectively. Intuitively, if L is small enough compared with image height Y, then the length of observation sequence T is large. Larger T helps to better estimate model parameter, but the difference between images would diminish due to smaller window height. As a result, the effect of L on recognition rate could be subtle. This is illustrated in Fig.7. It is obvious from Fig.7 that, when sampling window height L is small, pixel features are not discriminative enough to reflect the discrepancies between different samples. Therefore, when L = 1, recognition error is quite high. On the other hand, when we increase window height, the effect of L on error rate depends on overlap K. When K = 0, the number of observation sequence is small, and partitioning of palmprint image may be imprecise, so recognition error is relatively high. When K achieve its maximum value L-1, the number of observation sequence increases, and larger window height could adequately reflect the differences between images, so error rate is reduced. This may help to explain why the Fig.7(a) takes on U shape, while the Fig.7(b) tends to bend downward. E. Revisit to state number and Gaussian mixture number For a left-right HMM, the two parameters, state number and Gaussian mixture number, play an important role. State number determines the number of features needed to describe palmprint. If the length of observation sequence is large, we could select a larger state number to deal with the features. However, the forward-backward procedure requires 2 a time complexity of O ( N ), so smaller N corresponds to less computation time. To evaluate the effect of these two variables on the performance of palmprint identification, this paper attempts to experiment in more detail according to the results derived before. In section C, D, experiments are designed according to conclusion in section B, i.e. assuming N = 6 and M = 1 to be suitable. In this section, we would like to discuss how system performance would change with N and M. We adote L = 4, K = 3 (maximum pixel overlap), and assume 2 N 8, 1 M 3. Relationship between recognition rate and N, M is shown as Fig.8. From Fig.8(a), when M = 1, error rate is basically smaller than other values of M. If we focus on those results of M = 1, as in Fig.8(b), it is obvious that when N = 6, 7 and 8, error rate is quite small; but when N further decreases, error rate increases rapidly. When N = 6, M = 1, L = 4 and K = 3, the highest recognition rate 99.80% is achieved. Experiment result suggests that single Gaussian function could describe the data distribution quite well. In practical applications, if the system is required for real time processing, we could adopt a smaller state number N. Figure 6. Recognition error rate under different values of overlap K: (a) sliding window height L = 4. (b) L = 6. Figure 7. Recognition error rate under different values of sampling window height L: (a) no overlap. (b) maximum overlap. Figure 8. Recognition error rate under different values of state number and Gaussian mixture number: (a) variation of both state number and mixture number. (b) fix mixture number to 1. V. CONCLUSION Hidden Markov Model (HMM) has achieved remarkable performances in some pattern recognition fields. However, in the field of palmprint identification, study of the feasibility of HMM is limited. This paper employed Down Sliding Window (DSW) sampling technique to obtain observation sequences. In the experiment, this paper randomly selected 50 individuals, 1000 palmprint images from PolyU database, and discussed the influences of HMM and DSW parameters on system performance. Preliminary results suggest: (1) Hidden Markov Model is feasible for palmprint identification (with recognition precision of 99.80%). (2) Best performance is achieved when 6-states, singlemixture HMM is built, and DSW with window height 4, overlap International Conference of Soft Computing and Pattern Recognition (SoCPaR) 505

5 (3) Large overlap helps to improve performance. (4) When overlap is large, the height of sampling window has a marginal effect on recognition rate (when height is not too small). In the future work, some complex feature extraction method would be explored to for HMM based palmprint identification. Moreover, larger scale experiments would be performed to evaluate the scalability of the system. ACKNOWLEDGMENT This work was supported by the National Basic Research Program of China (973 program) under Grant No. 2007CB311004, the National Natural Science Foundation of China under Grant No and the Ph.D. Programs Foundation of Ministry of Education of China under Grant No REFERENCES [1] Anil K. Jain, Biometric Recognition: Overview and Recent Advances, Progress in Pattern Recognition, Image Analysis and Applications, vol. 4756, 2007, pp [2] A. Kong, D. Zhang and M. Kamel, A survey of palmprint recognition, Pattern Recognition, vol. 42, 2009, pp [3] D. Zhang, W. Kin Kong, J. You and M. Wong, Online Palmprint Identification, IEEE Transactions on Pattern Analysis and Machine Learning, vol. 25 (9), 2003, pp [4] X. Qian Wu, K. Quan Wang and D. Zhang, Wavelet Based Palmprint Recognition, Proc. of the ICMLC, vol. 3, 2002, pp [5] Z. Sun, T. Tan, Y. Wang and S. Z. Li, Ordinal palmprint representation for personal identification, IEEE Computer Society Conference on CVPR, vol. 1, 2005, pp [6] A. Kong, and D. Zhang, Competitive Coding Scheme for Palmprint Verification,Proc. of the ICPR, vol. 1, pp [7] D. Zhang, and W. Shu, Two Novel Characteristics in Palmprint Verification: Datum Point Invariance and Line Feature Matching, Pattern Recognition, vol. 32 (4), 1999, pp [8] A. Kong, D. Zhang and M. Kamel, Palmprint Identification Using Feature-level Fusion, Pattern Recognition, vol. 39 (3), 2006, pp [9] L. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proc. IEEE, vol. 77 (2), 1989, pp [10] A. V. Nefian, M. H. Hayes, An embeded HMM-based approach for face detection and recognition, Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 6,1999, pp [11] X. Wu, K. Wang and D. Zhang, HMMs based palmprint identification, Lecture Notes in Computer Science, Springer, vol. 3072, pp , [12] D. Zhang, PolyU Palmprint Database, Biometric Research Centre, Hong Kong Polytechnic University. Available from: ( [13] F. Samaria, Face segmentation for identification using hiden Markov models, British Machine Vision Conference, BMVA Press, 1993, pp International Conference of Soft Computing and Pattern Recognition (SoCPaR)

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

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

A Survey on Feature Extraction Techniques for Palmprint Identification

A Survey on Feature Extraction Techniques for Palmprint Identification International Journal Of Computational Engineering Research (ijceronline.com) Vol. 03 Issue. 12 A Survey on Feature Extraction Techniques for Palmprint Identification Sincy John 1, Kumudha Raimond 2 1

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

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

Palmprint Based Identification Using Principal Line Approach

Palmprint Based Identification Using Principal Line Approach Palmprint Based Identification Using Principal Line Approach Ms. Bhagyashri K. Mane, Prof. Pravin P. Kalyankar Abstract A principal line approach is used for identify accurate person based on palmprint

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

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Stefan Müller, Gerhard Rigoll, Andreas Kosmala and Denis Mazurenok Department of Computer Science, Faculty of

More information

NOVEL HYBRID GENETIC ALGORITHM WITH HMM BASED IRIS RECOGNITION

NOVEL HYBRID GENETIC ALGORITHM WITH HMM BASED IRIS RECOGNITION NOVEL HYBRID GENETIC ALGORITHM WITH HMM BASED IRIS RECOGNITION * Prof. Dr. Ban Ahmed Mitras ** Ammar Saad Abdul-Jabbar * Dept. of Operation Research & Intelligent Techniques ** Dept. of Mathematics. College

More information

中国科技论文在线.

中国科技论文在线. May 2005, Vol.20, No.3, pp.4 48 J. Comput. Sci. & Technol. Wavelet Energy Feature Extraction and Matching for Palmprint Recognition Xiang-Qian Wu, Kuan-Quan Wang, and David Zhang 2 School of Computer Science

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

Ordinal Palmprint Represention for Personal Identification

Ordinal Palmprint Represention for Personal Identification Ordinal Palmprint Represention for Personal Identification Zhenan Sun, Tieniu Tan, Yunhong Wang and Stan Z. Li {znsun, tnt, wangyh, szli}@nlpr.ia.ac.cn Center for Biometrics and Security Research National

More information

Keywords Palmprint recognition, patterns, features

Keywords Palmprint recognition, patterns, features Volume 7, Issue 3, March 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Review on Palm

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

Fabric Defect Detection Based on Computer Vision

Fabric Defect Detection Based on Computer Vision Fabric Defect Detection Based on Computer Vision Jing Sun and Zhiyu Zhou College of Information and Electronics, Zhejiang Sci-Tech University, Hangzhou, China {jings531,zhouzhiyu1993}@163.com Abstract.

More information

Local Multiple Directional Pattern of Palmprint Image

Local Multiple Directional Pattern of Palmprint Image Local Multiple Directional Pattern of Palmprint Image Lunke Fei, Jie Wen, Zheng Zhang, Ke Yan, Zuofeng Zhong Shenzhen Graduate School, Harbin Institute of Technology, Shenzhen, China Email: flksxm@126.com,

More information

Face recognition using Singular Value Decomposition and Hidden Markov Models

Face recognition using Singular Value Decomposition and Hidden Markov Models Face recognition using Singular Value Decomposition and Hidden Markov Models PETYA DINKOVA 1, PETIA GEORGIEVA 2, MARIOFANNA MILANOVA 3 1 Technical University of Sofia, Bulgaria 2 DETI, University of Aveiro,

More information

Palmprint Recognition Based On Bit-Plane Extraction

Palmprint Recognition Based On Bit-Plane Extraction Palmprint Recognition Based On Bit-Plane Extraction T.Z. Lee and D.B.L. Bong Faculty of Engineering Universiti Malaysia Sarawak 94300 Kota Samarahan MALAYSIA bbldavid@feng.unimas.my Abstract: - In this

More information

234 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 14, NO. 2, FEBRUARY 2004

234 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 14, NO. 2, FEBRUARY 2004 234 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 14, NO. 2, FEBRUARY 2004 On Hierarchical Palmprint Coding With Multiple Features for Personal Identification in Large Databases

More information

A Survey on Security in Palmprint Recognition: A Biometric Trait

A Survey on Security in Palmprint Recognition: A Biometric Trait A Survey on Security in Palmprint Recognition: A Biometric Trait Dhaneshwar Prasad Dewangan 1, Abhishek Pandey 2 Abstract Biometric based authentication and recognition, the science of using physical or

More information

An introduction on several biometric modalities. Yuning Xu

An introduction on several biometric modalities. Yuning Xu An introduction on several biometric modalities Yuning Xu The way human beings use to recognize each other: equip machines with that capability Passwords can be forgotten, tokens can be lost Post-9/11

More information

Comparative Study of ROI Extraction of Palmprint

Comparative Study of ROI Extraction of Palmprint 251 Comparative Study of ROI Extraction of Palmprint 1 Milind E. Rane, 2 Umesh S Bhadade 1,2 SSBT COE&T, North Maharashtra University Jalgaon, India Abstract - The Palmprint region segmentation is an 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

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

Research on Emotion Recognition for Facial Expression Images Based on Hidden Markov Model

Research on Emotion Recognition for Facial Expression Images Based on Hidden Markov Model e-issn: 2349-9745 p-issn: 2393-8161 Scientific Journal Impact Factor (SJIF): 1.711 International Journal of Modern Trends in Engineering and Research www.ijmter.com Research on Emotion Recognition for

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

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

An embedded system of Face Recognition based on ARM and HMM

An embedded system of Face Recognition based on ARM and HMM An embedded system of Face Recognition based on ARM and HMM Yanbin Sun 1,2, Lun Xie 1, Zhiliang Wang 1,Yi An 2 1 Department of Electronic Information Engineering, School of Information Engineering, University

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

Person Authentication from Video of Faces: A Behavioral and Physiological Approach Using Pseudo Hierarchical Hidden Markov Models

Person Authentication from Video of Faces: A Behavioral and Physiological Approach Using Pseudo Hierarchical Hidden Markov Models Person Authentication from Video of Faces: A Behavioral and Physiological Approach Using Pseudo Hierarchical Hidden Markov Models Manuele Bicego 1, Enrico Grosso 1, and Massimo Tistarelli 2 1 DEIR - University

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

CHAPTER 5 PALMPRINT RECOGNITION WITH ENHANCEMENT

CHAPTER 5 PALMPRINT RECOGNITION WITH ENHANCEMENT 145 CHAPTER 5 PALMPRINT RECOGNITION WITH ENHANCEMENT 5.1 INTRODUCTION This chapter discusses the application of enhancement technique in palmprint recognition system. Section 5.2 describes image sharpening

More information

Published by: PIONEER RESEARCH & DEVELOPMENT GROUP (www.prdg.org) 1

Published by: PIONEER RESEARCH & DEVELOPMENT GROUP (www.prdg.org) 1 Minutiae Points Extraction using Biometric Fingerprint- Enhancement Vishal Wagh 1, Shefali Sonavane 2 1 Computer Science and Engineering Department, Walchand College of Engineering, Sangli, Maharashtra-416415,

More information

A new approach to reference point location in fingerprint recognition

A new approach to reference point location in fingerprint recognition A new approach to reference point location in fingerprint recognition Piotr Porwik a) and Lukasz Wieclaw b) Institute of Informatics, Silesian University 41 200 Sosnowiec ul. Bedzinska 39, Poland a) porwik@us.edu.pl

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

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

One Dim~nsional Representation Of Two Dimensional Information For HMM Based Handwritten Recognition

One Dim~nsional Representation Of Two Dimensional Information For HMM Based Handwritten Recognition One Dim~nsional Representation Of Two Dimensional Information For HMM Based Handwritten Recognition Nafiz Arica Dept. of Computer Engineering, Middle East Technical University, Ankara,Turkey nafiz@ceng.metu.edu.

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

PALM PRINT RECOGNITION AND AUTHENTICATION USING DIGITAL IMAGE PROCESSSING TECHNIQUE

PALM PRINT RECOGNITION AND AUTHENTICATION USING DIGITAL IMAGE PROCESSSING TECHNIQUE PALM PRINT RECOGNITION AND AUTHENTICATION USING DIGITAL IMAGE PROCESSSING TECHNIQUE Prof.V.R.Raut 1, Prof.Ms.S.S.Kukde 2, Shraddha S. Pande 3 3 Student of M.E Department of Electronics and telecommunication,

More information

Advanced Authentication Scheme using Multimodal Biometric Scheme

Advanced Authentication Scheme using Multimodal Biometric Scheme Advanced Authentication Scheme using Multimodal Biometric Scheme Shreya Mohan Karunya University Coimbatore, India Ephin M Karunya University Coimbatore, India Abstract: Fingerprint recognition has attracted

More information

AN EFFICIENT BINARIZATION TECHNIQUE FOR FINGERPRINT IMAGES S. B. SRIDEVI M.Tech., Department of ECE

AN EFFICIENT BINARIZATION TECHNIQUE FOR FINGERPRINT IMAGES S. B. SRIDEVI M.Tech., Department of ECE AN EFFICIENT BINARIZATION TECHNIQUE FOR FINGERPRINT IMAGES S. B. SRIDEVI M.Tech., Department of ECE sbsridevi89@gmail.com 287 ABSTRACT Fingerprint identification is the most prominent method of biometric

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

Fingerprint Ridge Orientation Estimation Using A Modified Canny Edge Detection Mask

Fingerprint Ridge Orientation Estimation Using A Modified Canny Edge Detection Mask Fingerprint Ridge Orientation Estimation Using A Modified Canny Edge Detection Mask Laurice Phillips PhD student laurice.phillips@utt.edu.tt Margaret Bernard Senior Lecturer and Head of Department Margaret.Bernard@sta.uwi.edu

More information

Fingerprint Mosaicking by Rolling with Sliding

Fingerprint Mosaicking by Rolling with Sliding Fingerprint Mosaicking by Rolling with Sliding Kyoungtaek Choi, Hunjae Park, Hee-seung Choi and Jaihie Kim Department of Electrical and Electronic Engineering,Yonsei University Biometrics Engineering Research

More information

Wavelet Transform in Face Recognition

Wavelet Transform in Face Recognition J. Bobulski, Wavelet Transform in Face Recognition,In: Saeed K., Pejaś J., Mosdorf R., Biometrics, Computer Security Systems and Artificial Intelligence Applications, Springer Science + Business Media,

More information

Feature-Aging for Age-Invariant Face Recognition

Feature-Aging for Age-Invariant Face Recognition Feature-Aging for Age-Invariant Face Recognition Huiling Zhou, Kwok-Wai Wong, and Kin-Man Lam, Centre for Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic

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

Image Enhancement Techniques for Fingerprint Identification

Image Enhancement Techniques for Fingerprint Identification March 2013 1 Image Enhancement Techniques for Fingerprint Identification Pankaj Deshmukh, Siraj Pathan, Riyaz Pathan Abstract The aim of this paper is to propose a new method in fingerprint enhancement

More information

A Wavelet-based Feature Selection Scheme for Palm-print Recognition

A Wavelet-based Feature Selection Scheme for Palm-print Recognition Vol.1, Issue.2, pp-278-287 ISSN: 2249-6645 A Wavelet-based Feature Selection Scheme for Palm-print Recognition Hafiz Imtiaz, Shaikh Anowarul Fattah (Department of Electrical and Electronic Engineering

More information

Advanced Palm Print Recognition Using Curve Let And Recursive Histogram Equalization

Advanced Palm Print Recognition Using Curve Let And Recursive Histogram Equalization African Journal of Basic & Applied Sciences 9 (4): 09-15, 017 ISSN 079-034 IDOSI Publications, 017 DOI: 10.589/idosi.ajbas.017.09.15 Advanced Palm Print Recognition Using Curve Let And Recursive Histogram

More information

LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM

LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM Hazim Kemal Ekenel, Rainer Stiefelhagen Interactive Systems Labs, University of Karlsruhe Am Fasanengarten 5, 76131, Karlsruhe, Germany

More information

A Comparative Study of Palm Print Recognition Systems

A Comparative Study of Palm Print Recognition Systems A Comparative Study of Palm Print Recognition Systems Akash Patel akash.patel@somaiya.edu Chinmayi Tidke chinmayi.t@somaiya.edu Chirag Dhamecha Mumbai India chirag.d@somaiya.edu Kavisha Shah kavisha.shah@somaiya.edu

More information

A Novel Palm Line Extraction and Matching For Personal Identification

A Novel Palm Line Extraction and Matching For Personal Identification A Novel Palm Line Extraction and Matching For Personal Identification HosseinSalimi,SaiedFazli Abstract Palmprint-based personal identification is regarded as an effective method for automatically recognizing

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

Illumination-Robust Face Recognition based on Gabor Feature Face Intrinsic Identity PCA Model

Illumination-Robust Face Recognition based on Gabor Feature Face Intrinsic Identity PCA Model Illumination-Robust Face Recognition based on Gabor Feature Face Intrinsic Identity PCA Model TAE IN SEOL*, SUN-TAE CHUNG*, SUNHO KI**, SEONGWON CHO**, YUN-KWANG HONG*** *School of Electronic Engineering

More information

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition Linear Discriminant Analysis in Ottoman Alphabet Character Recognition ZEYNEB KURT, H. IREM TURKMEN, M. ELIF KARSLIGIL Department of Computer Engineering, Yildiz Technical University, 34349 Besiktas /

More information

Keywords: Biometrics, Fingerprint, Minutia, Fractal Dimension, Box Counting.

Keywords: Biometrics, Fingerprint, Minutia, Fractal Dimension, Box Counting. Volume 4, Issue 1, January 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Fingerprint

More information

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of

More information

Image Quality Assessment based on Improved Structural SIMilarity

Image Quality Assessment based on Improved Structural SIMilarity Image Quality Assessment based on Improved Structural SIMilarity Jinjian Wu 1, Fei Qi 2, and Guangming Shi 3 School of Electronic Engineering, Xidian University, Xi an, Shaanxi, 710071, P.R. China 1 jinjian.wu@mail.xidian.edu.cn

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

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

Palmprint Feature Extraction Based on Curvelet Transform

Palmprint Feature Extraction Based on Curvelet Transform Journal of Information Hiding and Multimedia Signal Processing c 2015 ISSN 2073-4212 Ubiquitous International Volume 6, Number 1, January 2015 Palmprint Feature Extraction Based on Curvelet Transform Feifei

More information

wavelet packet transform

wavelet packet transform Research Journal of Engineering Sciences ISSN 2278 9472 Combining left and right palmprint for enhanced security using discrete wavelet packet transform Abstract Komal Kashyap * and Ekta Tamrakar Department

More information

Gabor Surface Feature for Face Recognition

Gabor Surface Feature for Face Recognition Gabor Surface Feature for Face Recognition Ke Yan, Youbin Chen Graduate School at Shenzhen Tsinghua University Shenzhen, China xed09@gmail.com, chenyb@sz.tsinghua.edu.cn Abstract Gabor filters can extract

More information

The Method of User s Identification Using the Fusion of Wavelet Transform and Hidden Markov Models

The Method of User s Identification Using the Fusion of Wavelet Transform and Hidden Markov Models The Method of User s Identification Using the Fusion of Wavelet Transform and Hidden Markov Models Janusz Bobulski Czȩstochowa University of Technology, Institute of Computer and Information Sciences,

More information

Fast and Robust Projective Matching for Fingerprints using Geometric Hashing

Fast and Robust Projective Matching for Fingerprints using Geometric Hashing Fast and Robust Projective Matching for Fingerprints using Geometric Hashing Rintu Boro Sumantra Dutta Roy Department of Electrical Engineering, IIT Bombay, Powai, Mumbai - 400 076, INDIA {rintu, sumantra}@ee.iitb.ac.in

More information

Palmprint recognition by using enhanced completed local binary pattern (CLBP) for personal recognition

Palmprint recognition by using enhanced completed local binary pattern (CLBP) for personal recognition Palmprint recognition by using enhanced completed local binary pattern (CLBP) for personal recognition Dr. K.N. Prakash 1, M. Satya sri lakshmi 2 1 Professor, Department of Electronics & Communication

More information

Toward Part-based Document Image Decoding

Toward Part-based Document Image Decoding 2012 10th IAPR International Workshop on Document Analysis Systems Toward Part-based Document Image Decoding Wang Song, Seiichi Uchida Kyushu University, Fukuoka, Japan wangsong@human.ait.kyushu-u.ac.jp,

More information

ECE521: Week 11, Lecture March 2017: HMM learning/inference. With thanks to Russ Salakhutdinov

ECE521: Week 11, Lecture March 2017: HMM learning/inference. With thanks to Russ Salakhutdinov ECE521: Week 11, Lecture 20 27 March 2017: HMM learning/inference With thanks to Russ Salakhutdinov Examples of other perspectives Murphy 17.4 End of Russell & Norvig 15.2 (Artificial Intelligence: A Modern

More information

Available online at Procedia Computer Science 00 (2009) Procedia Computer Science 2 (2010)

Available online at   Procedia Computer Science 00 (2009) Procedia Computer Science 2 (2010) Available online at www.sciencedirect.com Procedia Computer Science 00 (2009) 000 000 Procedia Computer Science 2 (2010) 164 172 Procedia Computer Science www.elsevier.com/locate/procedia www.elsevier.com/locate/procedia

More information

Palmprint Detection and Verification Using ROI and MLBP Method

Palmprint Detection and Verification Using ROI and MLBP Method almprint Detection and Verification Using ROI and MLB Method 1 1 2 Snigdha Mankar and A.A. Bardekar Computer Science and Engineering, Sipna COET, Amravati, 444701, India 2 Information & Technology, Sipna

More information

Integrating Palmprint and Fingerprint for Identity Verification

Integrating Palmprint and Fingerprint for Identity Verification 2009 Third nternational Conference on Network and System Security ntegrating Palmprint and Fingerprint for dentity Verification Yong Jian Chin, Thian Song Ong, Michael K.O. Goh and Bee Yan Hiew Faculty

More information

Hidden Markov Model for Sequential Data

Hidden Markov Model for Sequential Data Hidden Markov Model for Sequential Data Dr.-Ing. Michelle Karg mekarg@uwaterloo.ca Electrical and Computer Engineering Cheriton School of Computer Science Sequential Data Measurement of time series: Example:

More information

Palmprint Recognition in Eigen-space

Palmprint Recognition in Eigen-space Palmprint Recognition in Eigen-space Ashutosh Kumar School of Education Technology Jadavpur University Kolkata, India ashutosh_3206@yahoo.co.in Ranjan Parekh School of Education Technology Jadavpur University

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

N.Priya. Keywords Compass mask, Threshold, Morphological Operators, Statistical Measures, Text extraction

N.Priya. Keywords Compass mask, Threshold, Morphological Operators, Statistical Measures, Text extraction Volume, Issue 8, August ISSN: 77 8X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Combined Edge-Based Text

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

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

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

FACE RECOGNITION FROM A SINGLE SAMPLE USING RLOG FILTER AND MANIFOLD ANALYSIS

FACE RECOGNITION FROM A SINGLE SAMPLE USING RLOG FILTER AND MANIFOLD ANALYSIS FACE RECOGNITION FROM A SINGLE SAMPLE USING RLOG FILTER AND MANIFOLD ANALYSIS Jaya Susan Edith. S 1 and A.Usha Ruby 2 1 Department of Computer Science and Engineering,CSI College of Engineering, 2 Research

More information

Texture Analysis of Painted Strokes 1) Martin Lettner, Paul Kammerer, Robert Sablatnig

Texture Analysis of Painted Strokes 1) Martin Lettner, Paul Kammerer, Robert Sablatnig Texture Analysis of Painted Strokes 1) Martin Lettner, Paul Kammerer, Robert Sablatnig Vienna University of Technology, Institute of Computer Aided Automation, Pattern Recognition and Image Processing

More information

Principal Component Analysis based Palmprint Recognition with Center of Mass Moments

Principal Component Analysis based Palmprint Recognition with Center of Mass Moments International Journal of Scientific & Engineering Research Volume 3, Issue 10, October-2012 1 Principal Component Analysis based Palmprint Recognition with Center of Mass Moments R.Vivekanandam, M. Madheswaran

More information

Suspecting Less and Doing Better: New Insights on Palmprint Identification for Faster and More Accurate Matching

Suspecting Less and Doing Better: New Insights on Palmprint Identification for Faster and More Accurate Matching 1 Suspecting Less and Doing Better: New Insights on Palmprint Identification for Faster and More Accurate Matching Qian Zheng, Ajay Kumar, Gang Pan Abstract This paper introduces a generalized palmprint

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

Texture Segmentation by Windowed Projection

Texture Segmentation by Windowed Projection Texture Segmentation by Windowed Projection 1, 2 Fan-Chen Tseng, 2 Ching-Chi Hsu, 2 Chiou-Shann Fuh 1 Department of Electronic Engineering National I-Lan Institute of Technology e-mail : fctseng@ccmail.ilantech.edu.tw

More information

Palm Print Recognition and Authentication Using Hough Transform For Biometric Application

Palm Print Recognition and Authentication Using Hough Transform For Biometric Application Palm Print Recognition and Authentication Using Hough Transform For Biometric Application Ranjeet Singh Chauhan 1, Jagriti Kumari 2, Rajesh Mehra 3, Shallu 4 12 ME Scholar, 3 Associate Professor, 4 Research

More information

Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET)

Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET) 47 Footprint Recognition using Modified Sequential Haar Energy Transform (MSHET) V. D. Ambeth Kumar 1 M. Ramakrishnan 2 1 Research scholar in sathyabamauniversity, Chennai, Tamil Nadu- 600 119, India.

More information

NEW ALGORITHMS FOR SKEWING CORRECTION AND SLANT REMOVAL ON WORD-LEVEL

NEW ALGORITHMS FOR SKEWING CORRECTION AND SLANT REMOVAL ON WORD-LEVEL NEW ALGORITHMS FOR SKEWING CORRECTION AND SLANT REMOVAL ON WORD-LEVEL E.Kavallieratou N.Fakotakis G.Kokkinakis Wire Communication Laboratory, University of Patras, 26500 Patras, ergina@wcl.ee.upatras.gr

More information

PALMPRINT AUTHENTICATION BASED ON GABOR WAVELET USING SLIDING WINDOW APPROACH

PALMPRINT AUTHENTICATION BASED ON GABOR WAVELET USING SLIDING WINDOW APPROACH PALMPRINT AUTHENTICATION BASED ON GABOR WAVELET USING SLIDING WINDOW APPROACH Sadiya Thazeen, Feroz Morab, Mohammed Najmus Saqhib, Seema Morab Abstract A biometric system is a pattern recognition system

More information

Local Binary LDA for Face Recognition

Local Binary LDA for Face Recognition Local Binary LDA for Face Recognition Ivan Fratric 1, Slobodan Ribaric 1 1 Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia {ivan.fratric, slobodan.ribaric}@fer.hr

More information

Palmprint Recognition using Novel Fusion Algorithm

Palmprint Recognition using Novel Fusion Algorithm Palmprint Recognition using Novel Fusion Algorithm Kannan Subramanian Dept. of MCA, Bharath University, Chennai-600073, India ABSTRACT: Palmprint is a promising biometric feature for use in access control

More information

A Novel Design for a Palm Prints Enabled Biometric System

A Novel Design for a Palm Prints Enabled Biometric System IOSR Journal of Computer Engineering (IOSRJCE) ISSN: 2278-0661, ISBN: 2278-8727 Volume 7, Issue 3 (Nov-Dec. 2012), PP 01-08 A Novel Design for a Palm Prints Enabled Biometric System Sulabh Kumra. Tanmay

More information

International Journal of Research in Advent Technology, Vol.4, No.6, June 2016 E-ISSN: Available online at

International Journal of Research in Advent Technology, Vol.4, No.6, June 2016 E-ISSN: Available online at Authentication Using Palmprint Madhavi A.Gulhane 1, Dr. G.R.Bamnote 2 Scholar M.E Computer Science & Engineering PRMIT&R Badnera Amravati 1, Professor Computer Science & Engineering at PRMIT&R Badnera

More information

Personal Authentication Using Palm Print Features

Personal Authentication Using Palm Print Features ACCV2002: The 5th Asian Conference on Computer Vision, 23 25 January 2002, Melbourne, Australia. 1 Personal Authentication Using Palm Print Features Chin-Chuan Han,Hsu-LiangCheng,andKuo-ChinFan Department

More information

A Framework for Efficient Fingerprint Identification using a Minutiae Tree

A Framework for Efficient Fingerprint Identification using a Minutiae Tree A Framework for Efficient Fingerprint Identification using a Minutiae Tree Praveer Mansukhani February 22, 2008 Problem Statement Developing a real-time scalable minutiae-based indexing system using a

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

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

An algorithm of lips secondary positioning and feature extraction based on YCbCr color space SHEN Xian-geng 1, WU Wei 2

An algorithm of lips secondary positioning and feature extraction based on YCbCr color space SHEN Xian-geng 1, WU Wei 2 International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 015) An algorithm of lips secondary positioning and feature extraction based on YCbCr color space SHEN Xian-geng

More information

Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis

Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis Sensors & Transducers 2014 by IFSA Publishing, S. L. http://www.sensorsportal.com Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis 1 Xulin LONG, 1,* Qiang CHEN, 2 Xiaoya

More information

Local Correlation-based Fingerprint Matching

Local Correlation-based Fingerprint Matching Local Correlation-based Fingerprint Matching Karthik Nandakumar Department of Computer Science and Engineering Michigan State University, MI 48824, U.S.A. nandakum@cse.msu.edu Anil K. Jain Department of

More information