DETC D FACE RECOGNITION UNDER ISOMETRIC EXPRESSION DEFORMATIONS

Size: px
Start display at page:

Download "DETC D FACE RECOGNITION UNDER ISOMETRIC EXPRESSION DEFORMATIONS"

Transcription

1 Proceedings of the ASME 2014 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference IDETC/CIE 2014 August 17-20, 2014, Buffalo, New York, USA DETC D FACE RECOGNITION UNDER ISOMETRIC EXPRESSION DEFORMATIONS Javad Sovizi Department of Mechanical and Aerospace Engineering University at Buffalo Buffalo, New York Rahul Rai Venkat Krovi Department of Mechanical and Aerospace Engineering University at Buffalo Buffalo, New York In this paper, 3D face recognition under isometric deformation (induced by facial expressions) is considered. The main objective is to employ the shape descriptors that are invariant to (isometric) deformations to provide an efficient face recognition algorithm. Two methods of the correspondence are utilized for automatic landmark assignment to the query face. One is based on the conventional iterative closest point (ICP) method and another is based upon the geometrical/topological features of the human face. The shape descriptor is chosen to be the well-known geodesic distance (GD) measure. The recognition task is performed on SHREC08 database for both correspondence methods and the effect of feature (GD) vector size as well as landmark positions on the recognition accuracy were argued. INTRODUCTION 3D objects recognition/retrieval has been a challenging problem in the computer vision studies. It has found several applications in robotics, manufacturing, video surveillance etc. A novel topic in this area is recognition of the 3D non-rigid shapes that are subjected to the deformations. Dealing with non-rigid 3D objects, two classes of the problems can be assumed, articulated and non-articulated deformations. The former, as the name suggests, concerns the objects that are piecewise rigid but can change their shape/configuration due to the articulations. A robotic arm or human hand movements are some illustrative examples of these deformations. However, the recognition task is Address all correspondence to this author. more problematic when the deforming object is not articulated. Change of the human face under different expressions (smile, laugh, anger etc.) can be categorized in this class of the problems that is the main focus of the current work. Although the 2D face recognition has been well addressed in the literature, however, the major works concerning 3D face recognition go back to last few years. A comprehensive survey on the existing approaches on 2D, 3D and 2D+3D face recognition has been reported in [1]. Using the depth component in the face recognition is significantly effective in the robustness of the algorithms against the facial expressions, lighting, make ups etc. that are negatively affecting the performance of the 2D image recognition schemes. Bronstein et al. [2] proposed an expression-invariant 3D face recognition scheme in which the face surface gradient field is used as the shape descriptor for the recognition purpose. Kakadiaris et al. [3] developed a deformable model through which the 3D data are projected on the 2D grid. Hence, the algorithm uses the descriptive information provided by 3D data and is computationally efficient as it works in 2D regular grid. In another effort, Mian et al. [4] utilized the spherical face representations to reject several candidate faces in the recognition task. In addition, they developed an automatic segmentation algorithm that subdivides the face to the areas sensitive and insensitive to the expressions. Many other sophisticated approaches have been utilized to tackle the 3D face recognition problem under facial expressions. For example, Chang et al. [5] addressed this problem by investigating multiple overlapping regions around the nose. Li et 1 Copyright c 2014 by ASME

2 al. [6] tackled the expression deformation by sparse representation technique applied to a set of geometrical features ranked based on their sensitivity to the expression. Al-Osaimi et al. [7] proposed a method that differentiates between deformations induced by expressions and interpersonal disparities. In their work, a key factor is learning the expression deformations in a PCA subspace. The main goals of this work include: 1) developing an automatic correspondence algorithm for landmark assignment; 2) using relatively simpler shape descriptors that are invariant to the isometric deformations (induced by facial expressions); and 3) investigation of the effect of feature vector size as well as landmark positions on the recognition accuracy. Geodesic distance (GD) vector is used as the shape descriptor that is invariant under the isometric deformations. The use of the GD vector in this study is motivated by the work of Smeets et al. [8]. They used the GD matrix as the shape representative for both articulated shapes retrieval and 3D face recognitions. GD matrix is a symmetric matrix whose elements (g i, j ) are the geodesic distance between the points (landmarks) i and j. However, in the current work, we use only the elements g i, j where i j to construct our shape descriptor vector. The rest of this paper is organized as follows. Next section describes the database (SHREC 2008 [9]) and the details of the available information along with preprocessing of the 3D faces mesh data. Afterward, automatic landmark assignment via two correspondence algorithms are discussed. One is based on the conventional ICP (iterative closest point) algorithm and another is based upon the geometrical/topological features of the human face. In the next section, the recognition based on the GD shape descriptor is performed. Effect of the GD vector cardinality as well as landmark positions on the recognition accuracy were investigated for both landmark assignment approaches. Finally, in the last section, a brief discussion and directions for future work are presented. FIGURE 1: 7 DIFFERENT 3D FACE SAMPLES OF A SINGLE SUBJECT; SHREC 2008 DATABASE [9] tip of the nose to all other mesh vertices are calculated. The vertices whose corresponding GD is more than predefined threshold are removed from the mesh. Consequently, a new mesh is generated using the processed point cloud. Fig. 2 shows the cropping procedure for one of the samples in the database. DATABASE AND PREPROCESSING Besides the complexity of the recognition problem, providing the realistic 3D face databases is also a tedious task. The database used in this study is obtained from internet repository SHREC 2008 [9]. The data is a subset of GavabDB: a 3D Face Database [10] in which different scans of 61 subjects are acquired with the Minolta VI-700 laser range scanner. In this work 3D face data corresponding to 50 subjects are used. There are 7 different samples per subject. 2 frontal view, 1 look up, 1 look down, 1 smile, 1 laugh and 1 random expressions. So, the entire database contains 350 3D face data. Fig. 1 shows 7 different realizations of a single subject. As Fig. 1 shows, the raw data include some extra parts that are not used in the recognition process, e.g. subjects ears, hairs, neck, shirt etc. To crop the main part of the mesh, GD s from the FIGURE 2: CROPPING EXAMPLE FOR ONE OF THE DATABASE SAMPLES AUTOMATIC LANDMARK ASSIGNMENT For recognition purpose, it is crucial to automatically assign the landmarks to different (predefined) spots on the query 2 Copyright c 2014 by ASME

3 face surface. The GD vector associated to these landmarks will then be used as the shape descriptor for recognition. Here, two methods, one based on the conventional ICP algorithm and another based on the geodesic distance and geometrical/topological features of the human face are utilized for correspondence and automatic landmark assignment. In both of these methods, 15 different landmarks are manually assigned to a reference face model and the goal is to find the landmarks corresponding point on the new face mesh vertices. Fig. 3 shows a reference face surface and 15 different landmarks that have been manually selected on the face surface. Different factors may be considered for choosing the landmark positions as feasibility of the automatic landmark assignment, sensitivity to the facial expressions and the discriminativity of the resulting feature vector. Most of the landmarks shown in Fig. 3 are approximately located in the local extrema of the surface height function. This facilitates the geometrical/topological landmark assignment that will be described shortly. In addition, we have set landmarks 0, 3, 4, 9 and 10 along the symmetry line of the face among which the position of landmarks 0, 3 and 4 are less sensitive to several facial expressions. Moreover, it is expected that the position of landmarks 9 and 10 is not significantly changing in many expressions with closed mouth. Other landmarks are distributed on the left and right sides of the face to provide sufficient and welldiscriminating information from the subject face. In this paper, we have not employed a sophisticated approach to determine the optimal choice of the landmark positions. However, existing literature on 3D face recognition as well as investigating the accuracy of the recognition corresponding to different choices of the landmark positions were effective in choosing the landmark positions illustrated in Fig3. FIGURE 3: 15 LANDMARKS POSITIONS ON THE REFER- ENCE FACE MODEL In the first method, using the ICP algorithm, 3D point cloud of the query object will be transformed such that the best alignment is achieved with the reference model point cloud. Euclidean distance is then used to find the closest point to each of the landmarks on the reference surface. Fig. 4 shows the procedure for landmark assignment based on this method. FIGURE 4: ICP LANDMARK ASSIGNMENT FIGURE 5: CANDIDATE POINTS AND REJECTION BASED ON THE LOCATION RELATIVE TO THE NOSE TIP In the second approach, to find the vertex corresponding to ith (i = 1,...,14) landmark, we first calculate the GD from nose tip (whose location is known) to that landmark on the reference model, denoting by g re f n,i. In the next step, an interval I i = [g re f n,i a i,g re f n,i +a i ] is considered (where a i is a scalar design parameter) and all vertices in the query mesh whose geodesic distance from the nose tip belongs to I i will be considered as candidate corresponding points. Next, several candidate points will be rejected based on the relative position of the landmarks respect to the nose tip. For example, to find the vertex corresponding to landmark 3 on the reference model, the candidate points (on the query) whose Y coordinates are less than nose tip will be rejected. Fig. 5 illustrates this procedure. The corresponding point is finally selected from the set of remaining candidate points based on a simple weight function assignment. Denoting the ith landmark weight function by W i, then the weight associated with candidate point j is W i j = α i X j X n +β i Y j Y n +γ i Z j Z n (1) where X j, Y j and Z j are the coordinates of the candidate point 3 Copyright c 2014 by ASME

4 constructed as G i 50 1 = [gi 0,1,...,gi 0,14,gi 4,1,...,gi 4,14,gi 7,1,...,gi 7,3,gi 7,5,...,g i 7,14,gi 8,1,...,gi 8,3,gi 8,5,gi 8,6,gi 8,8,...,gi 8,14 ]T (2) FIGURE 6: WEIGHT FUNTIONS ASSOCIATED WITH EACH LANDMARK and X n, Y n and Z n are the coordinates of the nose tip on the query surface. α i, β i and γ i are the constant parameters associated with the ith landmark. Fig. 6 shows the landmarks weight functions and their tuned parameters. As an example, landmark 3 is located between two eyebrows and is expected to have a very close X coordinate to nose tip, even under severe expressions. So, the weight function penalizes the absolute difference in the X components by α 3 = 4. For the landmarks 5 and 6, the candidates with higher difference in the Z components are more probable to be the correct corresponding vertex. So, the weighting function multiplies the Z coordinate difference by positive constants γ 5 = γ 6 = 3. The sign of the other constants are determined based on the same interpretation of the topological features of the human face and the weights are tuned such that the best accuracy is achieved. Note that, while defining the interval I i, a i has to be chosen such that the resulting candidate points are in the close neighborhood of the desired landmark (this can be tuned by, for example, visual inspection of the resulting candidate points corresponding to different values of a i ). Otherwise, selection based on the weight functions may be erroneous. Fig. 7 shows the result of the landmark assignment to some of the 3D faces in the database based on the proposed method. 3D FACE RECOGNITION Once the query 3D face is preprocessed (cropped) and the vertices corresponding to the landmarks are determined, the geodesic distance vector can be constructed. Then, different distance measures are utilized to obtain the similarity of a query face geodesic distance vector with those of the database 3D faces. The results are obtained corresponding to both landmark assignment schemes. It will be shown that recognition based on the geometrical/topological landmark assignment yields higher accuracy than that based on the ICP correspondence. The geodesic distance vector of the ith 3D face model is There are several choices for constructing G i that will ultimately result in different accuracies of the recognition. Although we have not performed a systematic survey on this problem here, however, we have chosen four landmarks (one on the nose tip, two on the cheeks and one on the forehead) whose locations are not drastically changing in facial expressions. In addition, their geodesic distance from other landmarks provide discriminative information (based on different trials results). To measure the similarity between the GD vectors the following distance measures are used [8]. Mean normalized max. norm distance Euclidean distance Mean normalized Manhattan distance χ 2 distance Mn = max 2 G i k G j k k G i k + G j k D i, j m D i, j Ec = (G i k G j k )2 k=1 D i, j m Mnh = 2 G i k G j k k=1 G i k + G j k G i k D i, j Cs = m k=1 2 G j k G i k + G j k To examine the recognition accuracy, the entire database is used as query in 7 trials. In each trial, one of the 7 expressions is chosen as a query and other 6 expressions are used as the available database. The GD vector associated to each subject is calculated by averaging over these 6 remaining expressions. So, 50 tests are performed per trial that is 350 tests after 7 trials. The recognition accuracy for different similarity measures are summarized in Tab. 1. It can be seen that Mean normalized Manhattan distance and χ 2 -distance outperform the Euclidean distance, and Euclidean distance outperforms the maximum norm distance measure. In addition, as the results show, comparing to ICP based landmark assignment, the geometrical/topological landmark assignment method yields higher accuracies, for all distance measures and in both first and second rank recognition rates. The ICP assignment may introduce larger errors in the cases of severe facial expressions while the geometrical/topological based method proves to be more robust to the shape deformations induced by facial expressions. Moreover, the impact of distance measure and landmark assignment method on the accuracy of the recognition can also be investigated from the results. From Tab. 1, it 4 Copyright c 2014 by ASME

5 FIGURE 7: LANDMARK ASSIGNMENT RESULTS BASED ON THE GEOMETRICAL/TOPOLOGICAL FEATURES TABLE 1: 3D FACE RECOGNITION ACCURACY OVER 350 TESTS; GD VECTOR IS 50 1 Maximum norm distance Euclidean distance Manhattan distance χ 2 -distance First rank accuracy Geometrical/topological land. ass. First rank accuracy ICP land. ass. Second rank accuracy Geometrical/topological land. ass. Second rank accuracy ICP land. ass % % % % % 46 % % % % % % % % % % % is clear that distance measure has a higher impact on the results. For example, while the increase of accuracy due to the geometrical/topological landmark assignment method (compared to ICPbased method) is 7.15 %, using χ 2 -distance instead of maximum norm distance increases the accuracy by 28 %. Fig. 8 shows the first and second rank recognition accuracies variations versus the dimension of the GD vector. It can be seen that the overall accuracy increases by populating the GD vector, however, at some steps adding more elements decreases the recognition accuracy. This implies the significance of the landmarks positions. For example, landmarks located in the areas with large expression displacements, e.g. those in the lower part of the face (for example, lip corners), may introduce error in the correspondence that in turn decrease the recognition accuracy once their corresponding geodesic distances are added to the GD vector. In addition, the results plotted in Fig. 8 convey information about the sensitivity of different distance measures to the GD vector size (cardinality). For example, the maximum norm distance measure shows the least sensitivity but also provides the minimum accuracy among other evaluated measures. Conversely, χ 2 -distance has maximum sensitivity but it also gives the maximum accuracy. Solid lines in Fig. 8 show the accuracies corresponding to the geometrical/topological landmark assignment and dashed lines are the results based on the ICP landmark assignment. It can be clearly seen that for GD vectors with more than 5 elements the geometrical/topological landmark assignment method yields higher accuracy than the ICP based correspondence method. DISCUSSION In this work 3D face recognition problem under facial expression deformations was considered. The geodesic distance measure, that is invariant under the isometric deformations, was 5 Copyright c 2014 by ASME

6 ICP based approach for all distance measures. Clearly, more experiments need to be performed with different available databases to robustly establish the accuracy and effectiveness of the proposed methods, that will be the subject of our future study. ACKNOWLEDGMENT This work was partially supported by the National Science Foundation awards IIS and CNS FIGURE 8: (a) First and (b) second rank accuracy versus number of GD vector elements used as the shape descriptor. 3D faces in the database were preprocessed and two different automatic landmark assignment methods were utilized. One based on the ICP algorithm and another based on the geometrical/topological features of the human face. Different distance metrics were examined to measure the similarity of the geodesic distance vectors of the 3D faces and the results of the recognition were obtained for both landmark assignment approaches. Clearly, the size of the feature vector affected the recognition accuracy. However, we were also able to quantitatively establish the sensitivity of different distance measures to the number of feature vector elements. For example, the maximum norm vector is the least sensitive but is also the least accurate. The χ 2 -distance and Manhattan distance perform the best followed by the Euclidean distance and the saturation effects, in these measures, start to be observed after about 50 GD vector elements. Moreover, the geometrical/topological landmark assignment approach turned out to be more accurate than a b REFERENCES [1] Bowyer, K. W., Chang, K., and Flynn, P., A Survey of Approaches and Challenges in 3D and Multi-Modal 3D+2D Face Recognition. Computer Vision and Image Understanding, 101(1), pp [2] Bronstein, A. M., Bronstein, M. M., and Kimmel, R., Three-Dimensional Face Recognition. International Journal of Computer Vision, 64(1), pp [3] Kakadiaris, I. A., Passalis, G., Toderici, G., Murtuza, M. N., Lu, Y., Karampatziakis, N., and Theoharis, T., Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach. IEEE Transactions on Pattern Analysis and Mchine Intelligence, 29(4), pp [4] Mian, A., Bennamoun, M., and Owens, R., Automatic 3d face detection, normalization and recognition. In 3D Data Processing, Visualization, and Transmission, pp [5] Chang, K. I., Bowyer, K. W., Flynn, P. J., and Member, S., Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression. IEEE Transaction on Pattern Analysis and Machine Intelligence, 28, pp [6] Li, X., Jia, T., and Zhang, H., Expression-insensitive 3d face recognition using sparse representation. In IEEE Conference on Computer Vision and Pattern Recognition, pp [7] Al-Osaimi, F., Bennamoun, M., and Mian, A., An Expression Deformation Approach to Non-Rigid 3D Face Recognition. International Journal of Computer Vision, 81(3), pp [8] Smeets, D., Hermans, J., Vandermeulen, D., and Suetens, P., Isometric Deformation Invariant 3D Shape Recognition. Pattern Recognition, 45(7), July, pp [9] SHREC [10] Moreno, A. B., and Sanchez, A., Gavabdb: a 3d face database. In Workshop on Biometrics on the Internet, pp Copyright c 2014 by ASME

Component-based Registration with Curvature Descriptors for Expression Insensitive 3D Face Recognition

Component-based Registration with Curvature Descriptors for Expression Insensitive 3D Face Recognition Component-based Registration with Curvature Descriptors for Expression Insensitive 3D Face Recognition Neşe Alyüz Boğaziçi University Computer Engineering Dept. Istanbul, Turkey nese.alyuz@boun.edu.tr

More information

3D Signatures for Fast 3D Face Recognition

3D Signatures for Fast 3D Face Recognition 3D Signatures for Fast 3D Face Recognition Chris Boehnen, Tanya Peters, and Patrick J. Flynn Department of Computer Science and Engineering University of Notre Dame, USA {cboehnen,tpeters,flynn}@nd.edu

More information

Point-Pair Descriptors for 3D Facial Landmark Localisation

Point-Pair Descriptors for 3D Facial Landmark Localisation Point-Pair Descriptors for 3D Facial Landmark Localisation Marcelo Romero and Nick Pears Department of Computer Science The University of York York, UK {mromero, nep}@cs.york.ac.uk Abstract Our pose-invariant

More information

Conformal mapping-based 3D face recognition

Conformal mapping-based 3D face recognition Conformal mapping-based 3D face recognition Przemyslaw Szeptycki, Mohsen Ardabilian, Liming Chen MI Department, LIRIS Laboratory, Ecole Centrale de Lyon, 69134 Lyon, France {przemyslaw.szeptycki, mohsen.ardabilian,

More information

2 The remainder of this paper is organized as follows: in the next section, we will review relevant previous work. An overview of the usage of shape f

2 The remainder of this paper is organized as follows: in the next section, we will review relevant previous work. An overview of the usage of shape f 1 Robust 3D Face Recognition by Using Shape Filtering Liang Cai Student cailiang-23@163.com Feipeng Da Prof Research Institute of Automation Southeast University Nanjing, China dafp@seu.edu.cn Abstract

More information

Landmark Localisation in 3D Face Data

Landmark Localisation in 3D Face Data 2009 Advanced Video and Signal Based Surveillance Landmark Localisation in 3D Face Data Marcelo Romero and Nick Pears Department of Computer Science The University of York York, UK {mromero, nep}@cs.york.ac.uk

More information

New Experiments on ICP-Based 3D Face Recognition and Authentication

New Experiments on ICP-Based 3D Face Recognition and Authentication New Experiments on ICP-Based 3D Face Recognition and Authentication Boulbaba Ben Amor Boulbaba.Ben-Amor@ec-lyon.fr Liming Chen Liming.Chen@ec-lyon.fr Mohsen Ardabilian Mohsen.Ardabilian@ec-lyon.fr Abstract

More information

Compact signatures for 3D face recognition under varying expressions

Compact signatures for 3D face recognition under varying expressions Compact signatures for 3D face recognition under varying expressions Fahad Daniyal, Prathap Nair and Andrea Cavallaro Queen Mary University of London School of Electronic Engineering and Computer Science

More information

Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression

Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 28, NO. 10, OCTOBER 2006 1 Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression Kyong I. Chang, Kevin

More information

3D Face Recognition Using Spherical Vector Norms Map *

3D Face Recognition Using Spherical Vector Norms Map * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 3, XXXX-XXXX (016) 3D Face Recognition Using Spherical Vector Norms Map * XUE-QIAO WANG ab, JIA-ZHENG YUAN ac AND QING LI ab a Beijing Key Laboratory of Information

More information

Enhancing 3D Face Recognition By Mimics Segmentation

Enhancing 3D Face Recognition By Mimics Segmentation Enhancing 3D Face Recognition By Mimics Segmentation Boulbaba Ben Amor, Mohsen Ardabilian, and Liming Chen MI Department, LIRIS Laboratory, CNRS 5205 Ecole Centrale de Lyon, 36 av. Guy de Collongue, 69134

More information

Heat Front Propagation Contours for 3D Face Recognition

Heat Front Propagation Contours for 3D Face Recognition Heat Front Propagation Contours for 3D Face Recognition Mostafa Abdelrahman 1, Aly A. Farag 1, and Moumen El-Melegy 1,2 1 Computer Vision and Image Processing Laboratory University of Louisville, Louisville,

More information

Published in: International Journal of Computer Vision. DOI: /s Document Version Peer reviewed version

Published in: International Journal of Computer Vision. DOI: /s Document Version Peer reviewed version An Expression Deformation Approach to Non-rigid 3D Face Recognition Al-Osaimi, F. R. M., Bennamoun, M., & Mian, A. (2009). An Expression Deformation Approach to Non-rigid 3D Face Recognition. International

More information

EI3D: Expression-Invariant 3D Face Recognition based on Feature and Shape Matching

EI3D: Expression-Invariant 3D Face Recognition based on Feature and Shape Matching 1 Pattern Recognition Letters journal homepage: www.elsevier.com EI3D: Expression-Invariant 3D Face Recognition based on Feature and Shape Matching Yulan Guo a,, Yinjie Lei b, Li Liu c, Yan Wang d, Mohammed

More information

Pattern Recognition 42 (2009) Contents lists available at ScienceDirect. Pattern Recognition

Pattern Recognition 42 (2009) Contents lists available at ScienceDirect. Pattern Recognition Pattern Recognition 42 (2009) 1895 -- 1905 Contents lists available at ScienceDirect Pattern Recognition journal homepage: www.elsevier.com/locate/pr Automatic 3D face recognition from depth and intensity

More information

THE ability to consistently extract features is at the heart of

THE ability to consistently extract features is at the heart of International Journal of Information and Communication Engineering 5:4 29 Scale-Space Volume Descriptors for Automatic 3D Facial Feature Extraction Daniel Chen, George Mamic, Clinton Fookes, Sridha Sridharan

More information

Intensity Augmented ICP for Registration of Laser Scanner Point Clouds

Intensity Augmented ICP for Registration of Laser Scanner Point Clouds Intensity Augmented ICP for Registration of Laser Scanner Point Clouds Bharat Lohani* and Sandeep Sashidharan *Department of Civil Engineering, IIT Kanpur Email: blohani@iitk.ac.in. Abstract While using

More information

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

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

More information

Automatic 3D Face Detection, Normalization and Recognition

Automatic 3D Face Detection, Normalization and Recognition Automatic 3D Face Detection, Normalization and Recognition Ajmal Mian, Mohammed Bennamoun and Robyn Owens School of Computer Science and Software Engineering The University of Western Australia 35 Stirling

More information

The Novel Approach for 3D Face Recognition Using Simple Preprocessing Method

The Novel Approach for 3D Face Recognition Using Simple Preprocessing Method The Novel Approach for 3D Face Recognition Using Simple Preprocessing Method Parvin Aminnejad 1, Ahmad Ayatollahi 2, Siamak Aminnejad 3, Reihaneh Asghari Abstract In this work, we presented a novel approach

More information

Landmark Detection on 3D Face Scans by Facial Model Registration

Landmark Detection on 3D Face Scans by Facial Model Registration Landmark Detection on 3D Face Scans by Facial Model Registration Tristan Whitmarsh 1, Remco C. Veltkamp 2, Michela Spagnuolo 1 Simone Marini 1, Frank ter Haar 2 1 IMATI-CNR, Genoa, Italy 2 Dept. Computer

More information

Journal of Industrial Engineering Research

Journal of Industrial Engineering Research IWNEST PUBLISHER Journal of Industrial Engineering Research (ISSN: 2077-4559) Journal home page: http://www.iwnest.com/aace/ Mammogram Image Segmentation Using voronoi Diagram Properties Dr. J. Subash

More information

UR3D-C: Linear Dimensionality Reduction for Efficient 3D Face Recognition

UR3D-C: Linear Dimensionality Reduction for Efficient 3D Face Recognition UR3D-C: Linear Dimensionality Reduction for Efficient 3D Face Recognition Omar Ocegueda 1, Georgios Passalis 1,2, Theoharis Theoharis 1,2, Shishir K. Shah 1, Ioannis A. Kakadiaris 1 Abstract We present

More information

I CP Fusion Techniques for 3D Face Recognition

I CP Fusion Techniques for 3D Face Recognition I CP Fusion Techniques for 3D Face Recognition Robert McKeon University of Notre Dame Notre Dame, Indiana, USA rmckeon@nd.edu Patrick Flynn University of Notre Dame Notre Dame, Indiana, USA flynn@nd.edu

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

EXPLOITING 3D FACES IN BIOMETRIC FORENSIC RECOGNITION

EXPLOITING 3D FACES IN BIOMETRIC FORENSIC RECOGNITION 18th European Signal Processing Conference (EUSIPCO-2010) Aalborg, Denmark, August 23-27, 2010 EXPLOITING 3D FACES IN BIOMETRIC FORENSIC RECOGNITION Marinella Cadoni, Andrea Lagorio, Enrico Grosso Massimo

More information

Algorithm research of 3D point cloud registration based on iterative closest point 1

Algorithm research of 3D point cloud registration based on iterative closest point 1 Acta Technica 62, No. 3B/2017, 189 196 c 2017 Institute of Thermomechanics CAS, v.v.i. Algorithm research of 3D point cloud registration based on iterative closest point 1 Qian Gao 2, Yujian Wang 2,3,

More information

Multiscale 3D Feature Extraction and Matching

Multiscale 3D Feature Extraction and Matching Multiscale 3D Feature Extraction and Matching Hadi Fadaifard and George Wolberg Graduate Center, City University of New York May 18, 2011 Hadi Fadaifard and George Wolberg Multiscale 3D Feature Extraction

More information

Robust PDF Table Locator

Robust PDF Table Locator Robust PDF Table Locator December 17, 2016 1 Introduction Data scientists rely on an abundance of tabular data stored in easy-to-machine-read formats like.csv files. Unfortunately, most government records

More information

Topics for thesis. Automatic Speech-based Emotion Recognition

Topics for thesis. Automatic Speech-based Emotion Recognition Topics for thesis Bachelor: Automatic Speech-based Emotion Recognition Emotion recognition is an important part of Human-Computer Interaction (HCI). It has various applications in industrial and commercial

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

Robust Shape Retrieval Using Maximum Likelihood Theory

Robust Shape Retrieval Using Maximum Likelihood Theory Robust Shape Retrieval Using Maximum Likelihood Theory Naif Alajlan 1, Paul Fieguth 2, and Mohamed Kamel 1 1 PAMI Lab, E & CE Dept., UW, Waterloo, ON, N2L 3G1, Canada. naif, mkamel@pami.uwaterloo.ca 2

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

A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking

A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking Przemyslaw Szeptycki, Mohsen Ardabilian and Liming Chen Abstract Automatic 2.5D face landmarking aims at locating facial

More information

Expression Invariant 3D Face Recognition with a Morphable Model

Expression Invariant 3D Face Recognition with a Morphable Model Expression Invariant 3D Face Recognition with a Morphable Model Brian Amberg brian.amberg@unibas.ch Reinhard Knothe reinhard.knothe@unibas.ch Thomas Vetter thomas.vetter@unibas.ch Abstract We describe

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

State of The Art In 3D Face Recognition

State of The Art In 3D Face Recognition State of The Art In 3D Face Recognition Index 1 FROM 2D TO 3D 3 2 SHORT BACKGROUND 4 2.1 THE MOST INTERESTING 3D RECOGNITION SYSTEMS 4 2.1.1 FACE RECOGNITION USING RANGE IMAGES [1] 4 2.1.2 FACE RECOGNITION

More information

Integrated 3D Expression Recognition and Face Recognition

Integrated 3D Expression Recognition and Face Recognition Integrated 3D Expression Recognition and Face Recognition Chao Li, Armando Barreto Electrical & Computer Engineering Department Florida International University Miami, Florida, 33174, USA {cli007, barretoa}@fiu.edu

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

Invariant shape similarity. Invariant shape similarity. Invariant similarity. Equivalence. Equivalence. Equivalence. Equal SIMILARITY TRANSFORMATION

Invariant shape similarity. Invariant shape similarity. Invariant similarity. Equivalence. Equivalence. Equivalence. Equal SIMILARITY TRANSFORMATION 1 Invariant shape similarity Alexer & Michael Bronstein, 2006-2009 Michael Bronstein, 2010 tosca.cs.technion.ac.il/book 2 Invariant shape similarity 048921 Advanced topics in vision Processing Analysis

More information

Integrating Range and Texture Information for 3D Face Recognition

Integrating Range and Texture Information for 3D Face Recognition Integrating Range and Texture Information for 3D Face Recognition Xiaoguang Lu and Anil K. Jain Dept. of Computer Science & Engineering Michigan State University East Lansing, MI 48824 {Lvxiaogu, jain}@cse.msu.edu

More information

Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks

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

More information

Robust Facial Feature Detection for Registration

Robust Facial Feature Detection for Registration Robust Facial Feature Detection for Registration Taher KHADHRAOUI khadhra.th@gmail.com Fouazi BENZARTI benzartif@yahoo.fr Hamid AMIRI hamidlamiri@yahoo.com Abstract Face image analysis, in the context

More information

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

Multimodal Expression-Invariant Face Recognition Using Dual-Tree Complex Wavelet Transform

Multimodal Expression-Invariant Face Recognition Using Dual-Tree Complex Wavelet Transform Multimodal Expression-Invariant Face Recognition Using Dual-Tree Complex Wavelet Transform Author Ayatollahi Fazael A. Raie Abolghasem Hajati Farshid Published 2013 Conference Title The 8th Iranian Conference

More information

Geometric Registration for Deformable Shapes 3.3 Advanced Global Matching

Geometric Registration for Deformable Shapes 3.3 Advanced Global Matching Geometric Registration for Deformable Shapes 3.3 Advanced Global Matching Correlated Correspondences [ASP*04] A Complete Registration System [HAW*08] In this session Advanced Global Matching Some practical

More information

ARTICLE IN PRESS. Computers & Graphics

ARTICLE IN PRESS. Computers & Graphics Computers & Graphics 34 (2010) 231 241 Contents lists available at ScienceDirect Computers & Graphics journal homepage: www.elsevier.com/locate/cag Technical Section Expression modeling for expression-invariant

More information

3-D Shape Matching for Face Analysis and Recognition

3-D Shape Matching for Face Analysis and Recognition 3-D Shape Matching for Face Analysis and Recognition Wei Quan, Bogdan J. Matuszewski and Lik-Kwan Shark Robotics and Computer Vision Research Laboratory, Applied Digital Signal and Image Processing (ADSIP)

More information

Topological Mapping. Discrete Bayes Filter

Topological Mapping. Discrete Bayes Filter Topological Mapping Discrete Bayes Filter Vision Based Localization Given a image(s) acquired by moving camera determine the robot s location and pose? Towards localization without odometry What can be

More information

3D face recognition based on a modified ICP method

3D face recognition based on a modified ICP method University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2011 3D face recognition based on a modified ICP method Kankan Zhao University

More information

Empirical Evaluation of Advanced Ear Biometrics

Empirical Evaluation of Advanced Ear Biometrics Empirical Evaluation of Advanced Ear Biometrics Ping Yan Kevin W. Bowyer Department of Computer Science and Engineering University of Notre Dame, IN 46556 Abstract We present results of the largest experimental

More information

Intensity-Depth Face Alignment Using Cascade Shape Regression

Intensity-Depth Face Alignment Using Cascade Shape Regression Intensity-Depth Face Alignment Using Cascade Shape Regression Yang Cao 1 and Bao-Liang Lu 1,2 1 Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai

More information

Combining Statistics of Geometrical and Correlative Features for 3D Face Recognition

Combining Statistics of Geometrical and Correlative Features for 3D Face Recognition 1 Combining Statistics of Geometrical and Correlative Features for 3D Face Recognition Yonggang Huang 1, Yunhong Wang 2, Tieniu Tan 1 1 National Laboratory of Pattern Recognition Institute of Automation,

More information

Accurate 3D Face and Body Modeling from a Single Fixed Kinect

Accurate 3D Face and Body Modeling from a Single Fixed Kinect Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this

More information

OWing to an increase in the availability of 3D data,

OWing to an increase in the availability of 3D data, 1 Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition Georgios Passalis 1,2, Panagiotis Perakis 1,2, Theoharis Theoharis 1,2 and Ioannis A. Kakadiaris 2, Senior Member, IEEE

More information

Categorization by Learning and Combining Object Parts

Categorization by Learning and Combining Object Parts Categorization by Learning and Combining Object Parts Bernd Heisele yz Thomas Serre y Massimiliano Pontil x Thomas Vetter Λ Tomaso Poggio y y Center for Biological and Computational Learning, M.I.T., Cambridge,

More information

Exploring Facial Expression Effects in 3D Face Recognition Using Partial ICP

Exploring Facial Expression Effects in 3D Face Recognition Using Partial ICP Exploring Facial Expression Effects in 3D Face Recognition Using Partial ICP Yueming Wang 1, Gang Pan 1,, Zhaohui Wu 1, and Yigang Wang 2 1 Dept. of Computer Science, Zhejiang University, Hangzhou, 310027,

More information

Automatic 3D Face Recognition Using Shapes of Facial Curves

Automatic 3D Face Recognition Using Shapes of Facial Curves Automatic 3D Face Recognition Using Shapes of Facial Curves Chafik Samir, Anuj Srivastava, and Mohamed Daoudi Abstract In addition to facial textures, manifested in facial images, shapes of facial surfaces

More information

Face Recognition by 3D Registration for the Visually Impaired Using a RGB-D Sensor

Face Recognition by 3D Registration for the Visually Impaired Using a RGB-D Sensor Face Recognition by 3D Registration for the Visually Impaired Using a RGB-D Sensor Wei Li 1, Xudong Li 2, Martin Goldberg 3 and Zhigang Zhu 1,3 1 The City College of New York, New York, NY 10031, USA 2

More information

FITTING AND TRACKING 3D/4D FACIAL DATA USING A TEMPORAL DEFORMABLE SHAPE MODEL. Shaun Canavan, Xing Zhang, and Lijun Yin

FITTING AND TRACKING 3D/4D FACIAL DATA USING A TEMPORAL DEFORMABLE SHAPE MODEL. Shaun Canavan, Xing Zhang, and Lijun Yin FITTING AND TRACKING 3D/4D FACIAL DATA USING A TEMPORAL DEFORMABLE SHAPE MODEL Shaun Canavan, Xing Zhang, and Lijun Yin Department of Computer Science State University of New York at Binghamton ABSTRACT

More information

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

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

More information

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

Linear Discriminant Analysis for 3D Face Recognition System

Linear Discriminant Analysis for 3D Face Recognition System Linear Discriminant Analysis for 3D Face Recognition System 3.1 Introduction Face recognition and verification have been at the top of the research agenda of the computer vision community in recent times.

More information

Keypoint Detection and Local Feature Matching for Textured 3D

Keypoint Detection and Local Feature Matching for Textured 3D Int J Comput Vis (2008) 79: 1 12 DOI 10.1007/s11263-007-0085-5 Keypoint Detection and Local Feature Matching for Textured 3D Face Recognition Ajmal S. Mian Mohammed Bennamoun Robyn Owens Received: 6 March

More information

Chapter 17 Face Recognition Using 3D Images

Chapter 17 Face Recognition Using 3D Images Chapter 17 Face Recognition Using 3D Images I.A. Kakadiaris, G. Passalis, G. Toderici, E. Efraty, P. Perakis, D. Chu, S. Shah, and T. Theoharis 17.1 Introduction Our face is our password face recognition

More information

Correspondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov

Correspondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov Shape Matching & Correspondence CS 468 Geometry Processing Algorithms Maks Ovsjanikov Wednesday, October 27 th 2010 Overall Goal Given two shapes, find correspondences between them. Overall Goal Given

More information

Better than best: matching score based face registration

Better than best: matching score based face registration Better than best: based face registration Luuk Spreeuwers University of Twente Fac. EEMCS, Signals and Systems Group Hogekamp Building, 7522 NB Enschede The Netherlands l.j.spreeuwers@ewi.utwente.nl Bas

More information

Training Algorithms for Robust Face Recognition using a Template-matching Approach

Training Algorithms for Robust Face Recognition using a Template-matching Approach Training Algorithms for Robust Face Recognition using a Template-matching Approach Xiaoyan Mu, Mehmet Artiklar, Metin Artiklar, and Mohamad H. Hassoun Department of Electrical and Computer Engineering

More information

In Between 3D Active Appearance Models and 3D Morphable Models

In Between 3D Active Appearance Models and 3D Morphable Models In Between 3D Active Appearance Models and 3D Morphable Models Jingu Heo and Marios Savvides Biometrics Lab, CyLab Carnegie Mellon University Pittsburgh, PA 15213 jheo@cmu.edu, msavvid@ri.cmu.edu Abstract

More information

Clustering. Robert M. Haralick. Computer Science, Graduate Center City University of New York

Clustering. Robert M. Haralick. Computer Science, Graduate Center City University of New York Clustering Robert M. Haralick Computer Science, Graduate Center City University of New York Outline K-means 1 K-means 2 3 4 5 Clustering K-means The purpose of clustering is to determine the similarity

More information

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information Mustafa Berkay Yilmaz, Hakan Erdogan, Mustafa Unel Sabanci University, Faculty of Engineering and Natural

More information

Image-Based Face Recognition using Global Features

Image-Based Face Recognition using Global Features Image-Based Face Recognition using Global Features Xiaoyin xu Research Centre for Integrated Microsystems Electrical and Computer Engineering University of Windsor Supervisors: Dr. Ahmadi May 13, 2005

More information

Computer Animation Visualization. Lecture 5. Facial animation

Computer Animation Visualization. Lecture 5. Facial animation Computer Animation Visualization Lecture 5 Facial animation Taku Komura Facial Animation The face is deformable Need to decide how all the vertices on the surface shall move Manually create them Muscle-based

More information

Preparation Meeting. Recent Advances in the Analysis of 3D Shapes. Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers

Preparation Meeting. Recent Advances in the Analysis of 3D Shapes. Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers Preparation Meeting Recent Advances in the Analysis of 3D Shapes Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers What You Will Learn in the Seminar Get an overview on state of the art

More information

FACE recognition in 3-D has been addressed using a variety

FACE recognition in 3-D has been addressed using a variety 62 IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, VOL. 3, NO. 1, MARCH 2008 A Region Ensemble for 3-D Face Recognition Timothy C. Faltemier, Kevin W. Bowyer, and Patrick J. Flynn, Senior Member,

More information

Face Recognition based Only on Eyes Information and Local Binary Pattern

Face Recognition based Only on Eyes Information and Local Binary Pattern Face Recognition based Only on Eyes Information and Local Binary Pattern Francisco Rosario-Verde, Joel Perez-Siles, Luis Aviles-Brito, Jesus Olivares-Mercado, Karina Toscano-Medina, and Hector Perez-Meana

More information

2. LITERATURE REVIEW

2. LITERATURE REVIEW 2. LITERATURE REVIEW CBIR has come long way before 1990 and very little papers have been published at that time, however the number of papers published since 1997 is increasing. There are many CBIR algorithms

More information

Range Image Registration with Edge Detection in Spherical Coordinates

Range Image Registration with Edge Detection in Spherical Coordinates Range Image Registration with Edge Detection in Spherical Coordinates Olcay Sertel 1 and Cem Ünsalan2 Computer Vision Research Laboratory 1 Department of Computer Engineering 2 Department of Electrical

More information

Using Geometric Blur for Point Correspondence

Using Geometric Blur for Point Correspondence 1 Using Geometric Blur for Point Correspondence Nisarg Vyas Electrical and Computer Engineering Department, Carnegie Mellon University, Pittsburgh, PA Abstract In computer vision applications, point correspondence

More information

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes International Journal of Computer Vision manuscript No. (will be inserted by the editor) On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

More information

Shape Matching. Michael Kazhdan ( /657)

Shape Matching. Michael Kazhdan ( /657) Shape Matching Michael Kazhdan (601.457/657) Overview Intro General Approach Minimum SSD Descriptor Goal Given a database of 3D models, and given a query shape, find the database models that are most similar

More information

Exploring Bag of Words Architectures in the Facial Expression Domain

Exploring Bag of Words Architectures in the Facial Expression Domain Exploring Bag of Words Architectures in the Facial Expression Domain Karan Sikka, Tingfan Wu, Josh Susskind, and Marian Bartlett Machine Perception Laboratory, University of California San Diego {ksikka,ting,josh,marni}@mplab.ucsd.edu

More information

AN EXAMINING FACE RECOGNITION BY LOCAL DIRECTIONAL NUMBER PATTERN (Image Processing)

AN EXAMINING FACE RECOGNITION BY LOCAL DIRECTIONAL NUMBER PATTERN (Image Processing) AN EXAMINING FACE RECOGNITION BY LOCAL DIRECTIONAL NUMBER PATTERN (Image Processing) J.Nithya 1, P.Sathyasutha2 1,2 Assistant Professor,Gnanamani College of Engineering, Namakkal, Tamil Nadu, India ABSTRACT

More information

Facial Animation System Design based on Image Processing DU Xueyan1, a

Facial Animation System Design based on Image Processing DU Xueyan1, a 4th International Conference on Machinery, Materials and Computing Technology (ICMMCT 206) Facial Animation System Design based on Image Processing DU Xueyan, a Foreign Language School, Wuhan Polytechnic,

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

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

Selection of Location, Frequency and Orientation Parameters of 2D Gabor Wavelets for Face Recognition

Selection of Location, Frequency and Orientation Parameters of 2D Gabor Wavelets for Face Recognition Selection of Location, Frequency and Orientation Parameters of 2D Gabor Wavelets for Face Recognition Berk Gökberk, M.O. İrfanoğlu, Lale Akarun, and Ethem Alpaydın Boğaziçi University, Department of Computer

More information

Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge

Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge Partial Face Matching between Near Infrared and Visual Images in MBGC Portal Challenge Dong Yi, Shengcai Liao, Zhen Lei, Jitao Sang, and Stan Z. Li Center for Biometrics and Security Research, Institute

More information

An Evaluation of Multimodal 2D+3D Face Biometrics

An Evaluation of Multimodal 2D+3D Face Biometrics IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 4, APRIL 2005 619 An Evaluation of Multimodal 2D+3D Face Biometrics Kyong I. Chang, Kevin W. Bowyer, and Patrick J. Flynn Abstract

More information

Face Recognition by Multi-Frame Fusion of Rotating Heads in Videos

Face Recognition by Multi-Frame Fusion of Rotating Heads in Videos Face Recognition by Multi-Frame Fusion of Rotating Heads in Videos Shaun J. Canavan, Michael P. Kozak, Yong Zhang, John R. Sullins, Matthew A. Shreve and Dmitry B. Goldgof Abstract This paper presents

More information

CHAPTER 4 FACE RECOGNITION DESIGN AND ANALYSIS

CHAPTER 4 FACE RECOGNITION DESIGN AND ANALYSIS CHAPTER 4 FACE RECOGNITION DESIGN AND ANALYSIS As explained previously in the scope, this thesis will also create a prototype about face recognition system. The face recognition system itself has several

More information

Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material

Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material Ayush Tewari 1,2 Michael Zollhöfer 1,2,3 Pablo Garrido 1,2 Florian Bernard 1,2 Hyeongwoo

More information

Learning to Recognize Faces in Realistic Conditions

Learning to Recognize Faces in Realistic Conditions 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

Topology-Invariant Similarity and Diffusion Geometry

Topology-Invariant Similarity and Diffusion Geometry 1 Topology-Invariant Similarity and Diffusion Geometry Lecture 7 Alexander & Michael Bronstein tosca.cs.technion.ac.il/book Numerical geometry of non-rigid shapes Stanford University, Winter 2009 Intrinsic

More information

AAM Based Facial Feature Tracking with Kinect

AAM Based Facial Feature Tracking with Kinect BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 15, No 3 Sofia 2015 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.1515/cait-2015-0046 AAM Based Facial Feature Tracking

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

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm Group 1: Mina A. Makar Stanford University mamakar@stanford.edu Abstract In this report, we investigate the application of the Scale-Invariant

More information

PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO

PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO Stefan Krauß, Juliane Hüttl SE, SoSe 2011, HU-Berlin PERFORMANCE CAPTURE FROM SPARSE MULTI-VIEW VIDEO 1 Uses of Motion/Performance Capture movies games, virtual environments biomechanics, sports science,

More information

IN a wide variety of disciplines, it is of great practical

IN a wide variety of disciplines, it is of great practical 1552 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 35, NO. 7, JULY 2013 3D Facial Landmark Detection under Large Yaw and Expression Variations Panagiotis Perakis, Member, IEEE Computer

More information

A Study on Similarity Computations in Template Matching Technique for Identity Verification

A Study on Similarity Computations in Template Matching Technique for Identity Verification A Study on Similarity Computations in Template Matching Technique for Identity Verification Lam, S. K., Yeong, C. Y., Yew, C. T., Chai, W. S., Suandi, S. A. Intelligent Biometric Group, School of Electrical

More information