Pixel Consistency, K-Tournament Selection, and Darwinian-Based Feature Extraction

In this paper, we present a two-stage process for developing feature extractors (FEs) for facial recognition. In this process, a genetic algorithm is used to evolve a number of local binary patterns (LBP) based FEs with each FE consisting of a number of (possibly) overlapping patches from which features are extracted from an image. These FEs are then overlaid to form what is referred to as a hyper FE. The hyper FE is then used to create a probability distribution function (PDF). The PDF is a two dimensional matrix that records the number of patches within the hyper FE that a particular pixel is contained within. Thus, the PDF matrix records the consistency of pixels contained within patches of the hyper FE. Darwinian-based FEs (DFEs) are then constructed by sampling the PDF via k-tournament selection to determine which pixels of a set of images will be used in extract features from. Our results show that DFEs have a higher recognition rate as well as a lower computational complexity than other LBP-based feature extractors.

[1]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .

[2]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Rabab M. Ramadan,et al.  FACE RECOGNITION USING PARTICLE SWARM OPTIMIZATION-BASED SELECTED FEATURES , 2009 .

[4]  David E. Goldberg,et al.  Genetic Algorithms, Selection Schemes, and the Varying Effects of Noise , 1996, Evolutionary Computation.

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

[6]  Damon L. Woodard,et al.  GEFeS: Genetic & evolutionary feature selection for periocular biometric recognition , 2011, 2011 IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM).

[7]  Damon L. Woodard,et al.  Comparison of Genetic-based Feature Extraction Methods for Facial Recognition , 2011, MAICS.

[8]  John C. Kelly,et al.  A comparison of genetic feature selection and weighting techniques for multi-biometric recognition , 2011, ACM-SE '11.

[9]  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).

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

[11]  Ggs Indraprastha,et al.  Feature selection for face recognition:a memetic algorithmic approach , 2009 .

[12]  Julian Fiérrez,et al.  Feature Selection Based on Genetic Algorithms for On-Line Signature Verification , 2007, 2007 IEEE Workshop on Automatic Identification Advanced Technologies.

[13]  Ioannis Pitas,et al.  Facial feature extraction in frontal views using biometric analogies , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[14]  Gerry V. Dozier,et al.  Permutation-based biometric authentication protocols for mitigating replay attacks , 2012, 2012 IEEE Congress on Evolutionary Computation.

[15]  J. Adams,et al.  Genetic & Evolutionary Biometrics: Feature extraction from a Machine Learning perspective , 2012, 2012 Proceedings of IEEE Southeastcon.

[16]  Karl Ricanek,et al.  Genetic & Evolutionary Biometric Security: Disposable Feature Extractors for Mitigating Biometric Replay Attacks , 2012, CSER.

[17]  G. Dozier,et al.  Genetic & Evolutionary Biometrics: Hybrid feature selection and weighting for a multi-modal biometric system , 2012, 2012 Proceedings of IEEE Southeastcon.

[18]  John C. Kelly,et al.  GEFeWS: A Hybrid Genetic-Based Feature Weighting and Selection Algorithm for Multi-Biometric Recognition , 2011, MAICS.

[19]  Damon L. Woodard,et al.  Genetic-Based Type II Feature Extraction for Periocular Biometric Recognition: Less is More , 2010, 2010 20th International Conference on Pattern Recognition.