Gaussian Conditional Random Fields for Face Recognition

We propose a Gaussian Conditional Random Field (GCRF) approach to modeling the non-stationary distortions that are introduced from changing facial expressions during acquisition. While previous work employed a Gaussian Markov Random Field (GMRF) to perform deformation tolerant matching of periocular images, we show that the approach is not well-suited for facial images, which can contain significantly larger and more complex deformations across the image. Like the GMRF, the GCRF tries to find the maximum scoring assignment between a match pair in the presence of non-stationary deformations. However, unlike the GMRF, the GCRF directly computes the posterior probability that the observed deformation is consistent with the distortions exhibited in other authentic match pairs. The difference is the inclusion of a derived mapping between an input comparison and output deformation score. We evaluate performance on the CMU Multi-PIE facial dataset across all sessions and expressions, finding that the GCRF is significantly more effective at capturing naturally occurring large deformations than the previous GMRF approach.

[1]  Hugo Proença,et al.  Periocular recognition: how much facial expressions affect performance? , 2016, Pattern Analysis and Applications.

[2]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[3]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[4]  Shu Liao,et al.  A novel Markov random field based deformable model for face recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Z. Obradovic,et al.  Gaussian Conditional Random Fields for Modeling Patients ’ Response to Acute Inflammation Treatment Multivariate Medications Healthy Patient State Predicted Patient State Multivariate Measured Patient State CLINICIAN ’ S DECISION PREDICTIVE MODEL MEDICATIONS , 2013 .

[6]  Abhishek Dutta,et al.  A Bayesian model for predicting face recognition performance using image quality , 2014, IEEE International Joint Conference on Biometrics.

[7]  Sébastien Marcel,et al.  A Scalable Formulation of Probabilistic Linear Discriminant Analysis: Applied to Face Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  J. Beveridge,et al.  Parametric and Nonparametric Methods for the Statistical Evaluation of Human ID Algorithms , 2001 .

[9]  Alexander M. Bronstein,et al.  Expression-Invariant Representations of Faces , 2007, IEEE Transactions on Image Processing.

[10]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[11]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[12]  Steffen L. Lauritzen,et al.  Graphical models in R , 1996 .

[13]  Minjie Zhang,et al.  Sparse Gaussian Conditional Random Fields on Top of Recurrent Neural Networks , 2018, AAAI.

[14]  Rama Chellappa,et al.  Face Association for Videos Using Conditional Random Fields and Max-Margin Markov Networks , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[16]  Pawan Sinha,et al.  Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About , 2006, Proceedings of the IEEE.

[17]  Xiao-Tong Yuan,et al.  Partial Gaussian Graphical Model Estimation , 2012, IEEE Transactions on Information Theory.

[18]  Shaohua Zhou,et al.  Unconstrained Face Recognition , 2005 .

[19]  Andrea Cavallaro,et al.  Automatic Analysis of Facial Affect: A Survey of Registration, Representation, and Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Zoran Obradovic,et al.  Neural Gaussian Conditional Random Fields , 2014, ECML/PKDD.

[21]  L. Held,et al.  Gaussian Markov Random Fields: Theory And Applications (Monographs on Statistics and Applied Probability) , 2005 .

[22]  Odobez Jean-Marc,et al.  A conditional random field approach for face identification in broadcast news using overlaid text , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[23]  Richard Szeliski,et al.  A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Pradeep Ravikumar,et al.  Sparse inverse covariance matrix estimation using quadratic approximation , 2011, MLSLP.

[25]  Hermann Ney,et al.  Warp that smile on your face: Optimal and smooth deformations for face recognition , 2011, Face and Gesture 2011.

[26]  B. V. K. Vijaya Kumar,et al.  A Bayesian Approach to Deformed Pattern Matching of Iris Images , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Zoran Obradovic,et al.  Gaussian Conditional Random Fields for Aggregation of Operational Aerosol Retrievals , 2015, IEEE Geoscience and Remote Sensing Letters.

[28]  Ira Kemelmacher-Shlizerman,et al.  Face Reconstruction from a Single Image using a Single Reference Face Shape , 2009 .

[29]  Alberto Del Bimbo,et al.  Pose Independent Face Recognition by Localizing Local Binary Patterns via Deformation Components , 2014, 2014 22nd International Conference on Pattern Recognition.

[30]  Kyung-Ah Sohn,et al.  Joint Estimation of Structured Sparsity and Output Structure in Multiple-Output Regression via Inverse-Covariance Regularization , 2012, AISTATS.

[31]  Luc Van Gool,et al.  Using a Deformation Field Model for Localizing Faces and Facial Points under Weak Supervision , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Edward H. Adelson,et al.  Learning Gaussian Conditional Random Fields for Low-Level Vision , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Tristan Mary-Huard,et al.  Structured regularization for conditional Gaussian graphical models , 2014, Statistics and Computing.

[34]  Edmondo Trentin,et al.  Techniques for dealing with incomplete data: a tutorial and survey , 2014, Pattern Analysis and Applications.

[35]  Danny Bickson,et al.  Gaussian Belief Propagation: Theory and Aplication , 2008, 0811.2518.

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

[37]  Vishnu Naresh Boddeti,et al.  Probabilistic Deformation Models for Challenging Periocular Image Verification , 2015, IEEE Transactions on Information Forensics and Security.

[38]  Paul H. Siegel,et al.  Solving Systems of Linear Equations: Theory and Application , 2022 .

[39]  Dan Roth,et al.  On the Hardness of Approximate Reasoning , 1993, IJCAI.

[40]  J. Zico Kolter,et al.  Sparse Gaussian Conditional Random Fields: Algorithms, Theory, and Application to Energy Forecasting , 2013, ICML.

[41]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[42]  Pradeep Ravikumar,et al.  Conditional Random Fields via Univariate Exponential Families , 2013, NIPS.