An Augmented Linear Discriminant Analysis Approach for Identifying Identical Twins with the Aid of Facial Asymmetry Features

In this work, we have proposed an Augmented Linear Discriminant Analysis (ALDA) approach to identify identical twins. It learns a common subspace that not only can identify from which family the individual comes, but also can distinguish between individuals within the same family. We evaluate the ALDA against the traditional LDA approach for subspace learning on the Notre Dame twin database. We have shown that the proposed ALDA method with the aid of facial asymmetry features significantly outperforms other well-established facial descriptors (LBP, LTP, LTrP), and the ALDA subspace method does a much better job in distinguishing identical twins than LDA. We are able to achieve 48.50% VR at 0.1% FAR for identifying family membership of identical twin individuals in the crowd and an averaged 82.58% VR at 0.1% FAR for verifying identical twin individuals within the same family, a significant improvement over traditional descriptors and traditional LDA method.

[1]  Anil K. Jain,et al.  Analysis of facial features in identical twins , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[2]  Marios Savvides,et al.  Robust modified Active Shape Model for automatic facial landmark annotation of frontal faces , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[3]  George W. Quinn,et al.  Report on the Evaluation of 2D Still-Image Face Recognition Algorithms , 2011 .

[4]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[5]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  George W. Quinn,et al.  Distinguishing identical twins by face recognition , 2011, Face and Gesture 2011.

[7]  Tieniu Tan,et al.  A study of multibiometric traits of identical twins , 2010, Defense + Commercial Sensing.

[8]  Patrick J. Flynn,et al.  A study of face recognition of identical twins by humans , 2011, 2011 IEEE International Workshop on Information Forensics and Security.

[9]  Yanxi Liu,et al.  Facial asymmetry quantification for expression invariant human identification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[10]  Subrahmanyam Murala,et al.  Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval , 2012, IEEE Transactions on Image Processing.

[11]  B. V. K. Vijaya Kumar,et al.  Face identification using novel frequency-domain representation of facial asymmetry , 2006, IEEE Transactions on Information Forensics and Security.

[12]  Xiaoyang Tan,et al.  Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions , 2007, IEEE Transactions on Image Processing.

[13]  Patrick J. Flynn,et al.  Facial recognition of identical twins , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[14]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[15]  M. Hayes.  The reconstruction of a multidimensional sequence from the phase or magnitude of its Fourier transform , 1982 .

[16]  B. V. K. Vijaya Kumar,et al.  Eigenphases vs eigenfaces , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[17]  Patrick J. Flynn,et al.  Facial marks as biometric signatures to distinguish between identical twins , 2011, CVPR 2011 WORKSHOPS.