Two-Stage Metric Learning Procedure for Facial Signature Authentication

We present the two-stage adaptive metric learning procedure with improved generalization of missing training data for facial signature authentication. The conventional learning models suffer from degraded recognition rates due to poor estimation of decision boundary to classify impostor patterns. The two-stage networks combine multiple image synthesis methods to assume mixture patterns of training classes and facilitate threshold setting of false acceptance/rejection rates. The margin size of a decision boundary is adjusted to input patterns obtained from synthesized images and depends on the choice of the mixing factor. The present method effectively reduces the margin of a class with an improved recognition rate to classify impostor patterns from 82.2% to 98.8%. Furthermore, we examine the margin structure of the mixture distributions by using the Support Vector Machines.

[1]  Anil K. Jain,et al.  Combining classifiers for face recognition , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[2]  Tomer Hertz,et al.  Learning a Mahalanobis Metric with Side Information , 2004 .

[3]  Sanja Fidler,et al.  Robust LDA Classification by Subsampling , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[4]  Tao Jiang,et al.  Efficient and robust feature extraction by maximum margin criterion , 2003, IEEE Transactions on Neural Networks.

[5]  Hakan Cevikalp,et al.  Discriminative common vectors for face recognition , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  H.M. El-Bakry,et al.  Human face recognition using neural networks , 1999, Proceedings of the Sixteenth National Radio Science Conference. NRSC'99 (IEEE Cat. No.99EX249).

[7]  Henry Schneiderman,et al.  A histogram-based method for detection of faces and cars , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[8]  Kuldip K. Paliwal,et al.  Class-dependent PCA, MDC and LDA: A combined classifier for pattern classification , 2006, Pattern Recognit..

[9]  Sun-Yuan Kung,et al.  Face recognition/detection by probabilistic decision-based neural network , 1997, IEEE Trans. Neural Networks.

[10]  Martin D. Levine,et al.  Face Recognition Using the Discrete Cosine Transform , 2001, International Journal of Computer Vision.

[11]  Tsuhan Chen,et al.  Personal authentication based on generalized symmetric max minimal distance in subspace , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[12]  Tieniu Tan,et al.  Nearest intra-class space classifier for face recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[13]  Rajat Raina,et al.  Classification with Hybrid Generative/Discriminative Models , 2003, NIPS.

[14]  Jieping Ye,et al.  Efficient Kernel Discriminant Analysis via QR Decomposition , 2004, NIPS.

[15]  T. Otsuki,et al.  An adaptive metric learning procedure for reconfigurable facial signature authentication , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[16]  Carlos E. Thomaz,et al.  A New Quadratic Classifier Applied to Biometric Recognition , 2002, Biometric Authentication.

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

[18]  M. Younus Javed,et al.  A New Approach to Face Recognition Using Dual Dimension Reduction , 2008 .

[19]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[20]  Misha Pavel,et al.  Adjustment Learning and Relevant Component Analysis , 2002, ECCV.

[21]  Zhencheng Hu,et al.  Face Recognition Based on Dominant Frequency Features and Multiresolution Metric , 2007, Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007).

[22]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Samy Bengio,et al.  Database, protocols and tools for evaluating score-level fusion algorithms in biometric authentication , 2006, Pattern Recognit..

[24]  Jakob Sternby.  On-Line Signature Verification by Explicit Solution to the Point Correspondence Problem , 2004 .

[25]  Duncan Fyfe Gillies,et al.  A Maximum Uncertainty LDA-Based Approach for Limited Sample Size Problems : With Application to Face Recognition , 2005, SIBGRAPI.

[26]  Ah Chung Tsoi,et al.  On the distribution of performance from multiple neural-network trials , 1997, IEEE Trans. Neural Networks.

[27]  Wen Gao,et al.  Information fusion in face identification , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[28]  Robert M. Gray,et al.  Lloyd clustering of Gauss mixture models for image compression and classification , 2005, Signal Process. Image Commun..

[29]  Wen Gao,et al.  Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[30]  M.A. Ferrer,et al.  Facial identification using transformed domain by SVM , 2004, 38th Annual 2004 International Carnahan Conference on Security Technology, 2004..

[31]  Teresa H. Meng,et al.  A DCT-based adaptive metric learning model using asymptotic local information measure , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[32]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[33]  Loris Nanni,et al.  Combining classifiers to obtain a reliable method for face recognition , 2005 .

[34]  Teresa H. Y. Meng,et al.  Object recognition with luminance, rotation and location invariance , 1997, Proceedings of International Conference on Image Processing.

[35]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[36]  Zhi-Hua Zhou,et al.  Unified Locally Linear Embedding and Linear Discriminant Analysis Algorithm (ULLELDA) for Face Recognition , 2004, SINOBIOMETRICS.

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

[38]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[39]  T. Satonaka.  Biometric watermark authentication with multiple verification rule , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[40]  Rahul Sukthankar,et al.  Memory-based face recognition for visitor identification , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[41]  Alistair G. Rust,et al.  Image redundancy reduction for neural network classification using discrete cosine transforms , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[42]  Tieniu Tan,et al.  Nearest intra-class space classifier for face recognition , 2004, ICPR 2004.

[43]  Koby Crammer,et al.  Margin Analysis of the LVQ Algorithm , 2002, NIPS.

[44]  R. Tibshirani,et al.  Discriminant Analysis by Gaussian Mixtures , 1996 .

[45]  Gian Luca Marcialis,et al.  Fusion of LDA and PCA for Face Verification , 2002, Biometric Authentication.

[46]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[47]  Sun-Yuan Kung,et al.  Estimation of elliptical basis function parameters by the EM algorithm with application to speaker verification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[48]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[49]  Rama Chellappa,et al.  Intra-personal Kernel Space for Face Recognition Intra-personal Kernel Space for Face Recognition , 2004 .

[50]  Stan Z. Li,et al.  Manifold Learning and Applications in Recognition , 2005 .

[51]  Jorma Rissanen,et al.  Hypothesis Selection and Testing by the MDL Principle , 1999, Comput. J..

[52]  K. Uchimura,et al.  A Hybrid Metric Estimation/Learning Model for K-NN Classifier , 2006, 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing.

[53]  Michael J. Black,et al.  Robust Parameterized Component Analysis , 2002, ECCV.

[54]  Tomer Hertz,et al.  Learning a Mahalanobis Metric from Equivalence Constraints , 2005, J. Mach. Learn. Res..

[55]  Juwei Lu,et al.  Face recognition using feature optimization and /spl nu/-support vector learning , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[56]  Babak Nadjar Araabi,et al.  A SVM-based method for face recognition using a wavelet PCA representation of faces , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[57]  Svetha Venkatesh,et al.  Application of the DCT energy histogram for face recognition , 2004 .

[58]  Kwang In Kim,et al.  Face recognition using kernel principal component analysis , 2002, IEEE Signal Processing Letters.

[59]  Jin Hyung Kim,et al.  Face Recognition using Support Vector Machines with Local Correlation Kernels , 2002, Int. J. Pattern Recognit. Artif. Intell..

[60]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.