Range Image Derivatives for GRCM on 2.5D Face Recognition

2.5D face recognition, which leverages both texture and range facial images often outperform sole texture 2D face recognition as the former provides additional unique information than the latter. The 2.5D face recognition naturally incurs higher computational load since two types of data are involved. In this paper, we investigate the possibility of just using range facial image alone for recognition. Gabor-based region covariance matrix (GRCM) is a flexible face feature descriptor that is capable to capture the geometrical and statistical properties of a facial image by fusing the diverse facial features into a covariance matrix. Here, we attempt to extract several feature derivatives from the range facial image for GRCM. Since GRCM resides on the Tensor manifold, geodesic and re-parameterized distances of Tensor manifold are used as dissimilarity measures of two GRCMs. Thus, the accuracy performance of range image derivatives with several distance metrics on Tensor manifold is explored. Experimental results show the effectiveness of the range image derivatives and the flexibility of the GRCM in 2.5D face recognition.

[1]  Andrew Beng Jin Teoh,et al.  2.5D Face Recognition under Tensor Manifold Metrics , 2014, ICONIP.

[2]  Fatih Murat Porikli,et al.  Human Detection via Classification on Riemannian Manifolds , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Fatih Murat Porikli,et al.  Fast Construction of Covariance Matrices for Arbitrary Size Image Windows , 2006, 2006 International Conference on Image Processing.

[4]  Yantao Li,et al.  A Kernel Gabor-Based Weighted Region Covariance Matrix for Face Recognition , 2012, Sensors.

[5]  Xuelong Li,et al.  Gabor-Based Region Covariance Matrices for Face Recognition , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Xuelong Li,et al.  Effective Feature Extraction in High-Dimensional Space , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  Andrew Beng Jin Teoh,et al.  A study on distance measures of tensor manifold for face recognition , 2014, 2014 International Conference on Electronics, Information and Communications (ICEIC).

[9]  Fatih Murat Porikli,et al.  Concentric ring signature descriptor for 3D objects , 2011, 2011 18th IEEE International Conference on Image Processing.

[10]  Anuj Srivastava,et al.  Face recognition using optimal linear components of range images , 2006, Image Vis. Comput..

[11]  Patricio A. Vela,et al.  Kernel covariance image region description for object tracking , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[12]  Simon Dobrisek,et al.  Combining 3D face representations using region covariance descriptors and statistical models , 2013, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).

[13]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Hongdong Li,et al.  Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Tai Sing Lee,et al.  Image Representation Using 2D Gabor Wavelets , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Fatih Murat Porikli,et al.  Region Covariance: A Fast Descriptor for Detection and Classification , 2006, ECCV.

[17]  Fatih Murat Porikli,et al.  Robust License Plate Detection Using Covariance Descriptor in a Neural Network Framework , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.