Correlation filters for facial recognition login access control

Size: px
Start display at page:

Download "Correlation filters for facial recognition login access control"

Transcription

1 Correlation filters for facial recognition login access control Daniel E. Riedel, Wanquan Liu and Ronny Tjahyadi Department of Computing, Curtin University of Technology, GPO Box U1987 Perth, Western Australia 6845 Abstract. Correlation filtering has recently been reintroduced to the facial recognition domain with promising recognition rates being seen over a variety of different facial databases. In this paper we utilise the minimum average correlation energy (MACE) and unconstrained minimum average correlation energy (UMACE) filters in conjunction with two correlation plane performance measures, max peak value and peak-tosidelobe ratio, to determine the effectiveness of this approach in relation to facial recognition login access control. A new technique for determining performance measure thresholds with the individual filters derived from the AMP and Biodm facial databases, was successfully developed producing high recall rates (87-94%) with 100% precision. A comparison of the precision and recall statistics obtained from the two different correlation plane measures, further demonstrated that max peak value is the better performance measure for use with MACE and UMACE filters for facial recognition login access control. 1 Introduction Facial recognition is a popular biometric approach to login access control due to the uniqueness of the human face, ease of collecting facial images and good acceptability as a result of the techniques unobtrusiveness [1]. Typically, most current operating systems use password verification for the establishment of a users identity with the requested service being access to the system. However, these systems are vulnerable to password cracking, password sniffing and acquisition of passwords through simplistic means. Facial recognition attempts to minimise these inherent vulnerabilities by controlling the port of entry into a system via utilising ones own facial signature. In comparison to other applications of facial recognition, login access control requires the system to exhibit and maintain 100% precision for all users. This is necessary to prevent unauthorised users from being incorrectly accessed to a system and secondly, to prevent authorised persons from being incorrectly identified as other valid users. The technique of correlation filtering was initially applied in pattern recognition tasks, such as automatic target recognition, through the use of matched spatial filters (MSF) generated from a single training image [2]. Unfortunately, this technique demonstrated distortion variance, poor generalisation and poor

2 localisation properties due to the use of a single training image and the broad correlation peak generated. To address these short-comings, the synthetic discriminant function (SDF) was introduced that linearly combined a set of training images into the one filter which further allowed one to constrain the filter output at the origin of the correlation plane [3]. By incorporating training images that best represent the expected distortions of an object, the SDF filter provided some degree of distortion invariance, yet like MSFs they did exhibit broad correlation peaks, making localisation difficult. To maximise peak sharpness for better object localisation and detection, the minimum average correlation energy (MACE) [3] and unconstrained MACE (UMACE) filters [4] were developed. Prior research has demonstrated that MACE and UMACE correlation filters are effective at facial recognition, producing identification rates of % and verification rates of % with the AMP and PIE facial databases [5 7, 10]. Furthermore, MACE and UMACE filters have been shown to exhibit limited built-in tolerance to illumination variation [6], which is attractive for multi-environment computing login access control. Facial recognition with correlation filters is performed by correlating a lexicographically ordered test image (transformed into the frequency domain via a Discrete Fast Fourier transform) with a synthesized, lexicographically ordered filter also in the frequency domain. The output correlation is subjected to an Inverse Fast Fourier transform and reordered into the dimensions of the original training image, prior to being phase shifted to the center of the frequency square. The resulting correlation plane is then quantified using performance measures, typically the peak-to-sidelobe (PSR) ratio. This paper investigates the use of an alternate correlation plane quantification metric (max peak value) to determine its effect on precision and recall rates in comparison to the standard PSR measure. In addition, an empirical method for deriving filter classification thresholds, is also introduced to avoid current ad hoc methods of threshold selection. Threshold selection is an important issue in login access control in order to maximise recall, whilst maintaining 100% precision. 1.1 Minimum average correlation energy filters MACE filters function to increase the peak sharpness by minimising the average correlation energy over a set of training images, whilst constraining the correlation peak height at the origin to a user-defined value. This in turn produces sharp peaks at the origin of the correlation plane, whilst producing values close to zero over the rest of the plane. The optimal solution to the MACE filter H is found using Lagrange multipliers in the frequency domain and is given by Equation (1). H = D 1 X(X + D 1 X) 1 u (1) D is a diagonal matrix of size d d, (d is the number of pixels in the image) containing the average correlation energies of the training images across its diagonals. X is a matrix of size N d where N is the number of training images

3 and + is the complex conjugate. The columns of the matrix X represent the Discrete Fourier coefficients for a particular training image X n. The column vector u of size N contains the correlation peak constraint values for a series of training images. These values are normally set to 1.0 for images of the same class [3, 7]. The UMACE filter like the MACE filter minimizes the average correlation energy over a set of training images, but does so without constraint (u), thereby maximising the peak height at the origin of the correlation plane. The UMACE filter expression H is given by Equation (2). H = D 1 X (2) D is a diagonal matrix containing the average correlation energy of the training images. X is a column vector of size d, containing the average Fourier coefficients of the training images [4]. Computationally, UMACE filters are more attractive than their MACE counterparts as they require only the inversion of a single diagonal matrix. Furthermore, UMACE filters have been shown to perform similar to MACE filters in facial recognition [6]. 1.2 Correlation plane performance measures Correlation plane performance measures are used to quantify the correlation plane generated by the correlation of a filter and a test image. In the context of facial recognition, the correlation plane is gauged with a performance metric in conjunction with a threshold, in order to classify a test image as belonging to a true or false class. Previous research with correlation filters and facial recognition has used the peak-to-sidelobe ratio (PSR) [5 7, 10] as a benchmark for correlation plane quantification. PSR can be calculated as per equation (3). P SR = peak mean σ peak is the maximum peak value in the correlation plane, mean is the average of the sidelobe region surrounding the peak (20 20 pixels for a pixel image, with a 5 5 excluded zone around the peak) and σ is the standard deviation of the sidelobe region values. More details on this technique can be found in [7] and [8]. In this study, we introduce an alternate simplistic measure, using just the maximum peak value, for measuring correlation planes in the context of facial recognition login access control. The maximum peak value is taken as the maximum correlation peak value over a correlation plane and is equivalent to the peak parameter in Equation 3. This performance metric measures only the strength of a match without taking into account sidelobe regions and is therefore more susceptible to misclassifications with correlations that generate large sidelobes. However, in relation to true class matches, it is believed that the max peak value metric should yield an equal or higher percentage of true class matches in comparison to PSR, as good correlations produce strong correlation peaks irrespective of the size of the sidelobe regions. (3)

4 1.3 Facial databases Experimentation was carried out using the Advanced Multimedia Processing (AMP) facial expression [7] and the Biodm facial databases 1. As much of the correlation filtering research in facial recognition has utilised the AMP facial database (13 subjects, 75 images per subject), it serves as a good experimental benchmark. Comparative studies were also carried out with the Biodm facial database. Images of this database were captured in the Department of Computing, Curtin University of Technology, with a real-time Linux biometric login system, incorporating facial recognition with a Logitec Quickcam Express Webcam. Histogram equalization was performed on all captured images, which were obtained over several sessions. The Biodm database comprises 11 subjects with 14 images each and of size pixels in PGM greyscale format. 1.4 Threshold derivation To determine the effectiveness of the MACE and UMACE filters for facial recognition login access control, individual classification thresholds were required for each filter synthesized. Initially, a global threshold was utilised across the filters of the same facial database but poor recognition performance was observed with both filter types. Consequently, individual upper and lower thresholds were derived using the training set images of the database for each filter, according to Fig. 1. The purpose of this approach was to find a threshold range in which to better select a classification threshold. With the individual upper and lower thresholds per filter, ratios of the difference between the upper and lower thresholds were used globally to determine an optimal pseudo-global threshold θ global to be set for all filters according to Fig. 2. As the θ global value uses the training images of a facial database to determine the maximum TP with zero FP, it is suitable for login access control, which requires a system to obtain 100% precision with a high recall rate for good usability. 2 Testing Methodology Prior to experimentation, the AMP and Biodm facial database images were segmented into two data sets: the training set and the testing set. MACE and UMACE filters were synthesized for the individuals comprising the uniformly distributed training set images, whilst the testing set was used to measure the precision and recall statistics of the approach over a range of pseudo-global thresholds. The testing set also contained 2 persons who were not part of the training set and thus should not be recognised. This particular approach of using testing images of persons not in the training set allows for a more accurate interpretation of the recognition results, by taking into account the ability of the system to reject external persons. 1 riedelde/biodm.html

5 1. Filter H i is synthesized using training images X i (of size m), where X i X, X={X 1X 2...X n} and n is the number of individuals comprising the training set. 2. True class correlations α i are performed in the frequency domain with filter H i and the training images X i. The corresponding correlation planes are quantified (β i) using an appropriate correlation plane measure and the m values in β i are then sorted in increasing order. The θ upper threshold is then set to the minimum of the of the β i values. ( is the complex conjugate) FOR j 1 TO m DO α j i H i Xj i β j i CORRELAT ION MEASURE(αj i ) ω 1 SORT (β i) θ upper β ω i 3. False class correlations γ i are performed with the filter H i and the training images Y i, where Y i X and Y i X i. The corresponding correlation planes are quantified (δ i) using the same correlation plane measure as in Step (2) and the θ lower threshold is set to the maximum of the δ i values. FOR j 1 TO m (n 1) DO γ j i H i Y j i δ j i CORRELAT ION MEASURE(γj i ) θ lower MAX(δ i) 4. IF θ lower θ upper AND ω m THEN ω = ω + 1 θ upper = β ω i REPEAT Step (4) ELSE OUTPUT θ lower and θ upper STOP Fig. 1. Upper (θ upper) and Lower (θ lower ) threshold derivation algorithm. To quantify the recognition performance of the filters with the testing sets, precision and recall statistics were applied to the performance values. Precision allows one to measure the ability of the technique to correctly classify, whilst recall measures the completeness of a techniques classification i.e. the proportion of the true class test cases that were identified [9]. 3 Experimental Results The training set for the AMP database consisted of the first 11 of 13 individuals comprising the database, with 5 training images per person (images 0,14,29,44 and 59). The corresponding testing set consisted of 40 uniformly selected images not present in the training set. Training sets for the Biodm facial database utilised the first 9 of the 11 subjects in the database, with 7 images selected per subject (images 1,3,5,7,9,11,13). The corresponding testing sets contained the remaining 7 images in the database for each of the 11 subjects (images 2,4,6,8,10,12,14). Upper and lower thresholds were derived for MACE and UMACE filters with the AMP and Biodm facial databases, using the max peak value and PSR performance measures. Figures 3-5 show the thresholds obtained from the AMP facial database using the algorithm in Fig. 1. One should note that the max peak value metric in Fig. 3. produced constant upper threshold values for the

6 1. The total number of false positives (FP) and true positives (TP) for all filters m and training images m n are determined, using thresholds lying between the θ lower and θ upper of the m filters. NUM INCREMENT S 10 CurrentIncrement 0 T P 0 F P 0 FOR i 1 TO NUM INCREMENT S DO FOR j 1 TO m n DO p ((j-1) mod m)+1 q ((j-1) div m)+1 FOR k 1 TO n DO φ k j H k Xp q λ k j CORRELAT ION MEASURE(φk j ) MaxV alue MAX(λ j ) r F IND(MaxV alue, λ j) CurrentT hreshold θ r upper -(θr upper -θr lower ) CurrentIncrement NUM INCREMENTS IF MaxV alue>currentt hreshold THEN IF r = q THEN T P T P +1 ELSE F P F P +1 IF F P > 0 THEN IF i > 1 THEN CurrentIncrement CurrentIncrement-1 OUTPUT CurrentIncrement NUM INCREMENTS STOP ELSE CurrentIncrement CurrentIncrement+1 2. The optimal threshold ratio between the θ lower and θ upper obtained in Step (1), occurs where the TP is maximum and the FP is zero. This value is set as the θ global for the facial database and can used for filter s as follows: OptimalT hreshold θupper s -(θs upper -θr lower ) θ global Matches are observed when the correlation measure value exceeds the OptimalT hreshold for a filter s. Fig. 2. Pseudo-Global threshold (θ global ) derivation algorithm. MACE filter with both databases, which can be explained by the MACE filter constraining the peak height at the origin of the correlation plane to a userdefined value [3]. Furthermore, MACE filters with the max peak value metric in Fig. 3. demonstrated good separation between upper and lower thresholds. The observed good separation may allow the future use of a global threshold for all filters of a particular facial database. UMACE filter training set correlations in Fig. 4. and Fig. 5. were observed to consistently produce variable upper thresholds in comparison to that of MACE filters for both performance measures. As predicted, the lower threshold values generated from Fig. 1. were also highly variable, as shown in Fig. 4. and Fig. 5. The inconsistent nature of the generated upper and lower thresholds for UMACE filters demonstrates an unsuitability of global thresholds for this filter type. One should note that the highly variable upper thresholds observed, are likely the

7 Fig. 3. MACE upper and lower max peak value thresholds for the AMP facial database. Fig. 4. UMACE upper and lower max peak value thresholds for the AMP facial database. result of the UMACE filter maximizing the peak height at the origin without constraint [6]. Following θ global threshold derivation, the recognition performance of the MACE and UMACE filters was ascertained using correlations with the corresponding testing sets. The correlation planes were quantified using the respective performance metric and the precision and recall statistics were in turn calculated (Table. 1.). The precision and recall rates produced with the optimal thresholds in Table 1. show that max peak value performance measure produced larger recall rates with the MACE filter. This result was found to be consistent with both filter types and facial databases. One may attribute this observation to the max peak value metric being better at true class detection than PSR and yet innately good at rejecting false class images. The lower recall rates obtained with the PSR measure could also indicate that the sidelobe regions are of less significance to facial recognition correlation plane quantification. As shown in Table 1, the recognition performance of the MACE and UMACE filters also appears to be data dependent as the UMACE filters performed better with the AMP database, yet worse with the Biodm database.

8 Fig. 5. MACE/UMACE upper and lower PSR thresholds for the AMP facial database. Table 1. Recall rates for optimal (100% precision) thresholds. Facial Database Filter Type Performance Metric Recall (%) AMP Biodm MACE UMACE MACE UMACE Max peak size 92.7% PSR 42.9% Max peak size 94.1% PSR 80.2% Max peak size 87.3% PSR 42.9% Max peak size 66.7% PSR 39.9% 4 Conclusion This paper has provided a performance overview of two correlation plane performance measures with MACE and UMACE correlation filters as well as a mechanism with which to derive a threshold selection range for correlation filters. In this study, it was found that the max peak value performance measure outperformed the standard PSR measure in relation to login access control constraints. In addition, the threshold derivation procedure was seen to be suitable for ascertaining optimal precision filter thresholds, in turn generating high recall rates. We are currently endeavouring to verify these findings with larger facial datbases, such as the PIE and BANCA databases. References 1. Jain, A., Hong, L., Pankanti S.: Biometric identification, Communications of the ACM 43(2) (2000) Vanderlugt A.B.: Signal detection by complex matched spatial filtersing, IEEE Trans. Inf. Theory IT-10 (1964) Mahalanobis, A., Vijaya Kumar, B.V.K., Casasent, D.: Minimum average correlation energy filters, Applied Optics 26(17) (1987)

9 4. Mahalanobis, A., Vijaya Kumar, B.V.K., Song, S., Sims, S.R.F., Epperson, J.F.: Unconstrained correlation filters, Applied Optics 33(17) (1994) Savvides, M., Venkataramani, K., Vijaya Kumar, B.V.K.: Incremental updating of advanced correlation filters for biometric authentication systems, Proc. Of the IEEE International Conference on Multimedia and Expo 3 (2003) Savvides, M., Vijaya Kumar, B.V.K.: Efficient design of advanced correlation filters for robust distortion-tolerant face recognition, Proc. Of the IEEE Conference on Advanced Video and Signal Based Surveillance (2003) Savvides, M., Vijaya Kumar, B.V.K., Khosla, P.: Face verification using correlation filters, Proc. Of the Third IEEE Automatic Identification Advanced Technologies (2002) Vijaya Kumar, B.V.K., Hassebrook, L.: Performance measures for correlation filters, Applied Optics 29(20) (1990) Vijay, V., Bollmann, B., Jung, G.S.: A critical investigation of recall and precision as measures of retrieval system performance, ACM Trans. Info. Sys. 7(3) (2003) Vijaya Kumar, B.V.K., Savvides, M., Venkataramani, K., Xie, C.: Spatial frequency domain image processing for biometric recognition, Proc. Of the IEEE International Conference on Image Processing 1 (2002) I-53 I-56

Spatial Frequency Domain Methods for Face and Iris Recognition

Spatial Frequency Domain Methods for Face and Iris Recognition Spatial Frequency Domain Methods for Face and Iris Recognition Dept. of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh, PA 15213 e-mail: Kumar@ece.cmu.edu Tel.: (412) 268-3026

More information

Illumination invariant face recognition and impostor rejection using different MINACE filter algorithms

Illumination invariant face recognition and impostor rejection using different MINACE filter algorithms Illumination invariant face recognition and impostor rejection using different MINACE filter algorithms Rohit Patnaik and David Casasent Dept. of Electrical and Computer Engineering, Carnegie Mellon University,

More information

Improving the Discrimination Capability with an Adaptive Synthetic Discriminant Function Filter

Improving the Discrimination Capability with an Adaptive Synthetic Discriminant Function Filter Improving the Discrimination Capability with an Adaptive Synthetic Discriminant Function Filter 83 J. Ángel González-Fraga 1, Víctor H. Díaz-Ramírez 1, Vitaly Kober 1, and Josué Álvarez-Borrego 2 1 Department

More information

POSTURE RECOGNITION USING CORRELATION FILTER CLASSIFIER

POSTURE RECOGNITION USING CORRELATION FILTER CLASSIFIER Journal of Theoretical and Applied Information Technology 5 - JATIT. All rights reserved. www.jatit.org POSTURE RECOGNITION USING CORRELATION FILTER CLASSIFIER Nooritawati Md Tahir, Aini Hussain, 3 Salina

More information

Разработки и технологии в области защитных голограмм

Разработки и технологии в области защитных голограмм Разработки и технологии в области защитных голограмм SECURITY HOLOGRAM MASTER-MATRIX AUTOMATIC QUALITY INSPECTION BASED ON SURFACE RELIEF MICRO-PHOTOGRAPHS DIGITAL PROCESSING Zlokazov E., Shaulskiy D.,

More information

Distortion-invariant Kernel Correlation Filters for General Object Recognition

Distortion-invariant Kernel Correlation Filters for General Object Recognition Distortion-invariant Kernel Correlation Filters for General Object Recognition Dissertation by Rohit Patnaik Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy

More information

Elsevier Editorial(tm) for Computer Vision and Image Understanding Manuscript Draft. Title: Face Recognition Using Correlation Filters

Elsevier Editorial(tm) for Computer Vision and Image Understanding Manuscript Draft. Title: Face Recognition Using Correlation Filters Elsevier Editorial(tm) for Computer Vision and Image Understanding Manuscript Draft Manuscript Number: Title: Face Recognition Using Correlation Filters Article Type: Regular Paper Keywords: correlation

More information

Wavelet packet correlation methods in biometrics

Wavelet packet correlation methods in biometrics Wavelet packet correlation methods in biometrics Pablo Hennings, Jason Thornton, Jelena Kovačević, and B. V. K. Vijaya Kumar We introduce wavelet packet correlation filter classifiers. Correlation filters

More information

The Role of Statistics in Biometric Authentication Based on Facial Images

The Role of Statistics in Biometric Authentication Based on Facial Images The Role of Statistics in Biometric Authentication Based on Facial Images Sinjini Mitra Department of Statistics & CyLab Carnegie Mellon University smitra@stat.cmu.edu Collaborators: Stephen E. Fienberg

More information

Radar Target Identification Using Spatial Matched Filters. L.M. Novak, G.J. Owirka, and C.M. Netishen MIT Lincoln Laboratory

Radar Target Identification Using Spatial Matched Filters. L.M. Novak, G.J. Owirka, and C.M. Netishen MIT Lincoln Laboratory Radar Target Identification Using Spatial Matched Filters L.M. Novak, G.J. Owirka, and C.M. Netishen MIT Lincoln Laboratory Abstract The application of spatial matched filter classifiers to the synthetic

More information

Image Quality Assessment Techniques: An Overview

Image Quality Assessment Techniques: An Overview Image Quality Assessment Techniques: An Overview Shruti Sonawane A. M. Deshpande Department of E&TC Department of E&TC TSSM s BSCOER, Pune, TSSM s BSCOER, Pune, Pune University, Maharashtra, India Pune

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

Semi-Supervised Clustering with Partial Background Information

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

More information

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

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

What is your Name?: A Facial Identification System. Final Report

What is your Name?: A Facial Identification System. Final Report What is your Name?: A Facial Identification System Final Report Digital Communications and Signal Processing Systems Design 18-551 Spring 2005 Group 5 Nancy Chu (nlchu@andrew.cmu.edu) Dong Keun Lee (dkl@andrew.cmu.edu)

More information

Robust Ring Detection In Phase Correlation Surfaces

Robust Ring Detection In Phase Correlation Surfaces Griffith Research Online https://research-repository.griffith.edu.au Robust Ring Detection In Phase Correlation Surfaces Author Gonzalez, Ruben Published 2013 Conference Title 2013 International Conference

More information

Automatic Target Recognition in Cluttered Visible Imagery

Automatic Target Recognition in Cluttered Visible Imagery Journal of Computer Science, 9 (5): 572-582, 2013 ISSN 1549-3636 2013 doi:10.3844/jcssp.2013.572.582 Published Online 9 (5) 2013 (http://www.thescipub.com/jcs.toc) Automatic Target Recognition in Cluttered

More information

Exploring Similarity Measures for Biometric Databases

Exploring Similarity Measures for Biometric Databases Exploring Similarity Measures for Biometric Databases Praveer Mansukhani, Venu Govindaraju Center for Unified Biometrics and Sensors (CUBS) University at Buffalo {pdm5, govind}@buffalo.edu Abstract. Currently

More information

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)

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

Maximum Margin Correlation Filter: A New Approach for Localization and Classification

Maximum Margin Correlation Filter: A New Approach for Localization and Classification 1 Maximum Margin Correlation Filter: A New Approach for Localization and Classification Andres Rodriguez, Student Member, IEEE, Vishnu Naresh Boddeti, Student Member, IEEE, B. V. K. Vijaya Kumar, Fellow,

More information

Image Biometric Verification in Spatial Frequency Domain

Image Biometric Verification in Spatial Frequency Domain Image Biometric Verification in Spatial Frequency Domain 1 Acknowledgments Dr. Marios Savvides Dr. Chunyan Xie Jason Thornton Krithika Venkataramani Pablo Hennings Technology Support Working Group (TSWG)

More information

International Research Journal of Engineering and Technology (IRJET) e-issn: Volume: 04 Issue: 09 Sep p-issn:

International Research Journal of Engineering and Technology (IRJET) e-issn: Volume: 04 Issue: 09 Sep p-issn: Automatic Target Detection Using Maximum Average Correlation Height Filter and Distance Classifier Correlation Filter in Synthetic Aperture Radar Data and Imagery Puttaswamy M R 1, Dr. P. Balamurugan 2

More information

Audio-Visual Based Multi-Sample Fusion to Enhance Correlation Filters Speaker Verification System

Audio-Visual Based Multi-Sample Fusion to Enhance Correlation Filters Speaker Verification System Audio-Visual Based Multi-Sample Fusion to Enhance Filters Speaker Verification System Dzati Athiar Ramli 1 1 School of Electrical & Electronic Engineering USM Engineering Campus, University Sains Malaysia

More information

PROOF COPY JOE. Recognition of live-scan fingerprints with elastic distortions using correlation filters

PROOF COPY JOE. Recognition of live-scan fingerprints with elastic distortions using correlation filters Recognition of live-scan fingerprints with elastic distortions using correlation filters Craig Watson National Institute of Standards and Technology MS8940 Gaithersburg, Maryland 20899 David Casasent,

More information

Motion Estimation and Optical Flow Tracking

Motion Estimation and Optical Flow Tracking Image Matching Image Retrieval Object Recognition Motion Estimation and Optical Flow Tracking Example: Mosiacing (Panorama) M. Brown and D. G. Lowe. Recognising Panoramas. ICCV 2003 Example 3D Reconstruction

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

Forensic Image Recognition using a Novel Image Fingerprinting and Hashing Technique

Forensic Image Recognition using a Novel Image Fingerprinting and Hashing Technique Forensic Image Recognition using a Novel Image Fingerprinting and Hashing Technique R D Neal, R J Shaw and A S Atkins Faculty of Computing, Engineering and Technology, Staffordshire University, Stafford

More information

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS

SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS SUMMARY: DISTINCTIVE IMAGE FEATURES FROM SCALE- INVARIANT KEYPOINTS Cognitive Robotics Original: David G. Lowe, 004 Summary: Coen van Leeuwen, s1460919 Abstract: This article presents a method to extract

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

2D Image Processing Feature Descriptors

2D Image Processing Feature Descriptors 2D Image Processing Feature Descriptors Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Overview

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

Face Detection and Recognition in an Image Sequence using Eigenedginess

Face Detection and Recognition in an Image Sequence using Eigenedginess Face Detection and Recognition in an Image Sequence using Eigenedginess B S Venkatesh, S Palanivel and B Yegnanarayana Department of Computer Science and Engineering. Indian Institute of Technology, Madras

More information

Face Recognition using FSS-DSOP for Small Sample Size Problem with Illumination

Face Recognition using FSS-DSOP for Small Sample Size Problem with Illumination Int. J. Advance. Soft Comput. Appl., Vol. 1, No. 2, November 2009 ISSN 2074-8523; Copyright ICSRS Publication, 2009 www.i-csrs.org Face Recognition using FSS-DSOP for Small Sample Size Problem with Illumination

More information

Polar Harmonic Transform for Fingerprint Recognition

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

More information

Multiple target detection in video using quadratic multi-frame correlation filtering

Multiple target detection in video using quadratic multi-frame correlation filtering Multiple target detection in video using quadratic multi-frame correlation filtering Ryan Kerekes Oak Ridge National Laboratory B. V. K. Vijaya Kumar Carnegie Mellon University March 17, 2008 1 Outline

More information

A Robust Visual Identifier Using the Trace Transform

A Robust Visual Identifier Using the Trace Transform A Robust Visual Identifier Using the Trace Transform P. Brasnett*, M.Z. Bober* *Mitsubishi Electric ITE VIL, Guildford, UK. paul.brasnett@vil.ite.mee.com, miroslaw.bober@vil.ite.mee.com Keywords: image

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

Face Recognition Based on LDA and Improved Pairwise-Constrained Multiple Metric Learning Method

Face Recognition Based on LDA and Improved Pairwise-Constrained Multiple Metric Learning Method Journal of Information Hiding and Multimedia Signal Processing c 2016 ISSN 2073-4212 Ubiquitous International Volume 7, Number 5, September 2016 Face Recognition ased on LDA and Improved Pairwise-Constrained

More information

Multidirectional 2DPCA Based Face Recognition System

Multidirectional 2DPCA Based Face Recognition System Multidirectional 2DPCA Based Face Recognition System Shilpi Soni 1, Raj Kumar Sahu 2 1 M.E. Scholar, Department of E&Tc Engg, CSIT, Durg 2 Associate Professor, Department of E&Tc Engg, CSIT, Durg Email:

More information

Face Detection Using a Dual Cross-Validation of Chrominance/Luminance Channel Decisions and Decorrelation of the Color Space

Face Detection Using a Dual Cross-Validation of Chrominance/Luminance Channel Decisions and Decorrelation of the Color Space Face Detection Using a Dual Cross-Validation of Chrominance/Luminance Channel Decisions and Decorrelation of the Color Space VICTOR-EMIL NEAGOE, MIHAI NEGHINĂ Depart. Electronics, Telecommunications &

More information

On Modeling Variations for Face Authentication

On Modeling Variations for Face Authentication On Modeling Variations for Face Authentication Xiaoming Liu Tsuhan Chen B.V.K. Vijaya Kumar Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 xiaoming@andrew.cmu.edu

More information

Reliable recognition of partially occluded objects with correlation filters

Reliable recognition of partially occluded objects with correlation filters Reliable recognition of partially occluded objects with correlation filters Alexey Ruchay a, Vitaly Kober a,b,, Jose A. Gonzalez-Fraga c a Department of Mathematics, Chelyabinsk State University, Russian

More information

Robust color segmentation algorithms in illumination variation conditions

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

More information

Unequal Error Recovery Scheme for Multimedia Streaming in Application-Level Multicast

Unequal Error Recovery Scheme for Multimedia Streaming in Application-Level Multicast Unequal Error Recovery Scheme for Multimedia Streaming in Application-Level Multicast Joonhyoung Lee, Youngha Jung, and Yoonsik Choe Department of Electrical and Electronic Engineering, Yonsei University,

More information

Face Detection on OpenCV using Raspberry Pi

Face Detection on OpenCV using Raspberry Pi Face Detection on OpenCV using Raspberry Pi Narayan V. Naik Aadhrasa Venunadan Kumara K R Department of ECE Department of ECE Department of ECE GSIT, Karwar, Karnataka GSIT, Karwar, Karnataka GSIT, Karwar,

More information

Three-Dimensional Face Recognition: A Fishersurface Approach

Three-Dimensional Face Recognition: A Fishersurface Approach Three-Dimensional Face Recognition: A Fishersurface Approach Thomas Heseltine, Nick Pears, Jim Austin Department of Computer Science, The University of York, United Kingdom Abstract. Previous work has

More information

FACE RECOGNITION USING INDEPENDENT COMPONENT

FACE RECOGNITION USING INDEPENDENT COMPONENT Chapter 5 FACE RECOGNITION USING INDEPENDENT COMPONENT ANALYSIS OF GABORJET (GABORJET-ICA) 5.1 INTRODUCTION PCA is probably the most widely used subspace projection technique for face recognition. A major

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

Subject-Oriented Image Classification based on Face Detection and Recognition

Subject-Oriented Image Classification based on Face Detection and Recognition 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050

More information

Implementing the Scale Invariant Feature Transform(SIFT) Method

Implementing the Scale Invariant Feature Transform(SIFT) Method Implementing the Scale Invariant Feature Transform(SIFT) Method YU MENG and Dr. Bernard Tiddeman(supervisor) Department of Computer Science University of St. Andrews yumeng@dcs.st-and.ac.uk Abstract The

More information

Image denoising in the wavelet domain using Improved Neigh-shrink

Image denoising in the wavelet domain using Improved Neigh-shrink Image denoising in the wavelet domain using Improved Neigh-shrink Rahim Kamran 1, Mehdi Nasri, Hossein Nezamabadi-pour 3, Saeid Saryazdi 4 1 Rahimkamran008@gmail.com nasri_me@yahoo.com 3 nezam@uk.ac.ir

More information

WATERMARKING FOR LIGHT FIELD RENDERING 1

WATERMARKING FOR LIGHT FIELD RENDERING 1 ATERMARKING FOR LIGHT FIELD RENDERING 1 Alper Koz, Cevahir Çığla and A. Aydın Alatan Department of Electrical and Electronics Engineering, METU Balgat, 06531, Ankara, TURKEY. e-mail: koz@metu.edu.tr, cevahir@eee.metu.edu.tr,

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

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009

Learning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009 Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer

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

Face Detection for Skintone Images Using Wavelet and Texture Features

Face Detection for Skintone Images Using Wavelet and Texture Features Face Detection for Skintone Images Using Wavelet and Texture Features 1 H.C. Vijay Lakshmi, 2 S. Patil Kulkarni S.J. College of Engineering Mysore, India 1 vijisjce@yahoo.co.in, 2 pk.sudarshan@gmail.com

More information

A Conflict-Based Confidence Measure for Associative Classification

A Conflict-Based Confidence Measure for Associative Classification A Conflict-Based Confidence Measure for Associative Classification Peerapon Vateekul and Mei-Ling Shyu Department of Electrical and Computer Engineering University of Miami Coral Gables, FL 33124, USA

More information

EE640 FINAL PROJECT HEADS OR TAILS

EE640 FINAL PROJECT HEADS OR TAILS EE640 FINAL PROJECT HEADS OR TAILS By Laurence Hassebrook Initiated: April 2015, updated April 27 Contents 1. SUMMARY... 1 2. EXPECTATIONS... 2 3. INPUT DATA BASE... 2 4. PREPROCESSING... 4 4.1 Surface

More information

Face Re-Lighting from a Single Image under Harsh Lighting Conditions

Face Re-Lighting from a Single Image under Harsh Lighting Conditions Face Re-Lighting from a Single Image under Harsh Lighting Conditions Yang Wang 1, Zicheng Liu 2, Gang Hua 3, Zhen Wen 4, Zhengyou Zhang 2, Dimitris Samaras 5 1 The Robotics Institute, Carnegie Mellon University,

More information

Sensor Tasking and Control

Sensor Tasking and Control Sensor Tasking and Control Outline Task-Driven Sensing Roles of Sensor Nodes and Utilities Information-Based Sensor Tasking Joint Routing and Information Aggregation Summary Introduction To efficiently

More information

Keywords:- Fingerprint Identification, Hong s Enhancement, Euclidian Distance, Artificial Neural Network, Segmentation, Enhancement.

Keywords:- Fingerprint Identification, Hong s Enhancement, Euclidian Distance, Artificial Neural Network, Segmentation, Enhancement. Volume 5, Issue 8, August 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Embedded Algorithm

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

CS 223B Computer Vision Problem Set 3

CS 223B Computer Vision Problem Set 3 CS 223B Computer Vision Problem Set 3 Due: Feb. 22 nd, 2011 1 Probabilistic Recursion for Tracking In this problem you will derive a method for tracking a point of interest through a sequence of images.

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

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

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging 1 CS 9 Final Project Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging Feiyu Chen Department of Electrical Engineering ABSTRACT Subject motion is a significant

More information

CS 231A Computer Vision (Fall 2012) Problem Set 3

CS 231A Computer Vision (Fall 2012) Problem Set 3 CS 231A Computer Vision (Fall 2012) Problem Set 3 Due: Nov. 13 th, 2012 (2:15pm) 1 Probabilistic Recursion for Tracking (20 points) In this problem you will derive a method for tracking a point of interest

More information

www.worldconferences.org Implementation of IRIS Recognition System using Phase Based Image Matching Algorithm N. MURALI KRISHNA 1, DR. P. CHANDRA SEKHAR REDDY 2 1 Assoc Prof, Dept of ECE, Dhruva Institute

More information

A Distance-Based Classifier Using Dissimilarity Based on Class Conditional Probability and Within-Class Variation. Kwanyong Lee 1 and Hyeyoung Park 2

A Distance-Based Classifier Using Dissimilarity Based on Class Conditional Probability and Within-Class Variation. Kwanyong Lee 1 and Hyeyoung Park 2 A Distance-Based Classifier Using Dissimilarity Based on Class Conditional Probability and Within-Class Variation Kwanyong Lee 1 and Hyeyoung Park 2 1. Department of Computer Science, Korea National Open

More information

DESIGN AND EVALUATION OF MACHINE LEARNING MODELS WITH STATISTICAL FEATURES

DESIGN AND EVALUATION OF MACHINE LEARNING MODELS WITH STATISTICAL FEATURES EXPERIMENTAL WORK PART I CHAPTER 6 DESIGN AND EVALUATION OF MACHINE LEARNING MODELS WITH STATISTICAL FEATURES The evaluation of models built using statistical in conjunction with various feature subset

More information

Face Tracking in Video

Face Tracking in Video Face Tracking in Video Hamidreza Khazaei and Pegah Tootoonchi Afshar Stanford University 350 Serra Mall Stanford, CA 94305, USA I. INTRODUCTION Object tracking is a hot area of research, and has many practical

More information

Classification: Linear Discriminant Functions

Classification: Linear Discriminant Functions Classification: Linear Discriminant Functions CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Discriminant functions Linear Discriminant functions

More information

SINGLE PASS DEPENDENT BIT ALLOCATION FOR SPATIAL SCALABILITY CODING OF H.264/SVC

SINGLE PASS DEPENDENT BIT ALLOCATION FOR SPATIAL SCALABILITY CODING OF H.264/SVC SINGLE PASS DEPENDENT BIT ALLOCATION FOR SPATIAL SCALABILITY CODING OF H.264/SVC Randa Atta, Rehab F. Abdel-Kader, and Amera Abd-AlRahem Electrical Engineering Department, Faculty of Engineering, Port

More information

Tracking Using Online Feature Selection and a Local Generative Model

Tracking Using Online Feature Selection and a Local Generative Model Tracking Using Online Feature Selection and a Local Generative Model Thomas Woodley Bjorn Stenger Roberto Cipolla Dept. of Engineering University of Cambridge {tew32 cipolla}@eng.cam.ac.uk Computer Vision

More information

Average of Synthetic Exact Filters

Average of Synthetic Exact Filters Average of Synthetic Exact Filters David S. Bolme Bruce A. Draper J. Ross Beveridge Colorado State University Fort Collins, CO 80521, USA bolme@cs.colostate.edu Abstract This paper introduces a class of

More information

International Journal of Innovative Research in Computer and Communication Engineering

International Journal of Innovative Research in Computer and Communication Engineering Data Hiding Using Difference Expension Method YASMEEN M.G,RAJALAKSHMI G Final year M.E, Arunai Engineering College, Thiruvannamalai, Tamilnadu, India Assistant Professor, Arunai Engineering College,Thiruvannamalai,

More information

One type of these solutions is automatic license plate character recognition (ALPR).

One type of these solutions is automatic license plate character recognition (ALPR). 1.0 Introduction Modelling, Simulation & Computing Laboratory (msclab) A rapid technical growth in the area of computer image processing has increased the need for an efficient and affordable security,

More information

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM 1 PHYO THET KHIN, 2 LAI LAI WIN KYI 1,2 Department of Information Technology, Mandalay Technological University The Republic of the Union of Myanmar

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

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

Detecting Multiple Symmetries with Extended SIFT

Detecting Multiple Symmetries with Extended SIFT 1 Detecting Multiple Symmetries with Extended SIFT 2 3 Anonymous ACCV submission Paper ID 388 4 5 6 7 8 9 10 11 12 13 14 15 16 Abstract. This paper describes an effective method for detecting multiple

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

Face Tracking. Synonyms. Definition. Main Body Text. Amit K. Roy-Chowdhury and Yilei Xu. Facial Motion Estimation

Face Tracking. Synonyms. Definition. Main Body Text. Amit K. Roy-Chowdhury and Yilei Xu. Facial Motion Estimation Face Tracking Amit K. Roy-Chowdhury and Yilei Xu Department of Electrical Engineering, University of California, Riverside, CA 92521, USA {amitrc,yxu}@ee.ucr.edu Synonyms Facial Motion Estimation Definition

More information

Visual object classification by sparse convolutional neural networks

Visual object classification by sparse convolutional neural networks Visual object classification by sparse convolutional neural networks Alexander Gepperth 1 1- Ruhr-Universität Bochum - Institute for Neural Dynamics Universitätsstraße 150, 44801 Bochum - Germany Abstract.

More information

Recognition of Control Chart Patterns using Discriminant Analysis of Shape Features

Recognition of Control Chart Patterns using Discriminant Analysis of Shape Features Proceedings of the 2010 International Conference on Industrial Engineering and Operations Management Dhaka, Bangladesh, January 9 10, 2010 Recognition of Control Chart Patterns using Discriminant Analysis

More information

Determination of 3-D Image Viewpoint Using Modified Nearest Feature Line Method in Its Eigenspace Domain

Determination of 3-D Image Viewpoint Using Modified Nearest Feature Line Method in Its Eigenspace Domain Determination of 3-D Image Viewpoint Using Modified Nearest Feature Line Method in Its Eigenspace Domain LINA +, BENYAMIN KUSUMOPUTRO ++ + Faculty of Information Technology Tarumanagara University Jl.

More information

Digital correlation hologram implemented on optical correlator

Digital correlation hologram implemented on optical correlator Digital correlation hologram implemented on optical correlator David Abookasis and Joseph Rosen Ben-Gurion University of the Negev Department of Electrical and Computer Engineering P. O. Box 653, Beer-Sheva

More information

9.9 Coherent Structure Detection in a Backward-Facing Step Flow

9.9 Coherent Structure Detection in a Backward-Facing Step Flow 9.9 Coherent Structure Detection in a Backward-Facing Step Flow Contributed by: C. Schram, P. Rambaud, M. L. Riethmuller 9.9.1 Introduction An algorithm has been developed to automatically detect and characterize

More information

Spatial Topology of Equitemporal Points on Signatures for Retrieval

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

More information

Feature Selection Using Modified-MCA Based Scoring Metric for Classification

Feature Selection Using Modified-MCA Based Scoring Metric for Classification 2011 International Conference on Information Communication and Management IPCSIT vol.16 (2011) (2011) IACSIT Press, Singapore Feature Selection Using Modified-MCA Based Scoring Metric for Classification

More information

OPTIMISATION OF PIN FIN HEAT SINK USING TAGUCHI METHOD

OPTIMISATION OF PIN FIN HEAT SINK USING TAGUCHI METHOD CHAPTER - 5 OPTIMISATION OF PIN FIN HEAT SINK USING TAGUCHI METHOD The ever-increasing demand to lower the production costs due to increased competition has prompted engineers to look for rigorous methods

More information

Two Dimensional Microwave Imaging Using a Divide and Unite Algorithm

Two Dimensional Microwave Imaging Using a Divide and Unite Algorithm Two Dimensional Microwave Imaging Using a Divide and Unite Algorithm Disha Shur 1, K. Yaswanth 2, and Uday K. Khankhoje 2 1 Indian Institute of Engineering Science and Technology, Shibpur, India 2 Indian

More information

Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines

Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines 2011 International Conference on Document Analysis and Recognition Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines Toru Wakahara Kohei Kita

More information

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin

More information

Fingerprint Matching using Gabor Filters

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

More information

Loop detection and extended target tracking using laser data

Loop detection and extended target tracking using laser data Licentiate seminar 1(39) Loop detection and extended target tracking using laser data Karl Granström Division of Automatic Control Department of Electrical Engineering Linköping University Linköping, Sweden

More information

Implementation and Comparative Analysis of Rotation Invariance Techniques in Fingerprint Recognition

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

More information

Table of Contents. Recognition of Facial Gestures... 1 Attila Fazekas

Table of Contents. Recognition of Facial Gestures... 1 Attila Fazekas Table of Contents Recognition of Facial Gestures...................................... 1 Attila Fazekas II Recognition of Facial Gestures Attila Fazekas University of Debrecen, Institute of Informatics

More information