Multi-feature fusion in advanced robotics applications

This paper describes a feature extraction technique from human face image sequences using model based approach. We study two different models with our proposed approach towards multifeature extraction. These features are efficiently used for human face information extraction for different applications. The approach follows in fitting a model to face image using robust objective function and extracting textural and temporal features for three major applications naming 1) face recognition, 2) facial expressions recognition and 3) gender classification. For experimentation and comparative study of our multi-features over two models, we use same set of features with two different classifiers generating promising results to explain that extracted features are strong enough to be used for face image analysis. Features goodness has been investigated on Cohn Kanade Facial Expressions Database (CKFED). The proposed multi-features approach is automatic and real time.

[1]  Takeo Kanade,et al.  Feature-point tracking by optical flow discriminates subtle differences in facial expression , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[2]  Ian Witten,et al.  Data Mining , 2000 .

[3]  Mikkel B. Stegmann,et al.  Active appearance models: Theory and cases , 2000 .

[4]  Takeo Kanade,et al.  Real-time combined 2D+3D active appearance models , 2004, CVPR 2004.

[5]  Jörgen Ahlberg.  An Experiment on 3D Face Model Adaptation using the Active Appearance Algorithm , 2001 .

[6]  A. Bronstein,et al.  3D Face Recognition without Facial Surface Reconstruction , 2003 .

[7]  M. Saquib Sarfraz,et al.  Probabilistic learning for fully automatic face recognition across pose , 2010, Image Vis. Comput..

[8]  Timothy F. Cootes,et al.  Active Shape Models - 'smart snakes' , 1992, BMVC.

[9]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[10]  C. Taylor,et al.  Active shape models - 'Smart Snakes'. , 1992 .

[11]  Anil K. Jain,et al.  Handbook of Face Recognition, 2nd Edition , 2011 .

[12]  Takeo Kanade,et al.  Comprehensive database for facial expression analysis , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[13]  Michael Beetz,et al.  A Model Based Approach for Expressions Invariant Face Recognition , 2009, ICB.

[14]  Ioannis Pitas,et al.  Facial Expression Recognition in Image Sequences Using Geometric Deformation Features and Support Vector Machines , 2007, IEEE Transactions on Image Processing.

[15]  Alejandro F. Frangi,et al.  Active shape model segmentation with optimal features , 2002, IEEE Transactions on Medical Imaging.

[16]  Sami Romdhani,et al.  Face image analysis using a multiple features fitting strategy , 2005 .

[17]  Rama Chellappa,et al.  Face Processing: Advanced Modeling and Methods , 2006, J. Electronic Imaging.

[18]  Timothy F. Cootes,et al.  Face Recognition Using Active Appearance Models , 1998, ECCV.

[19]  Stephan Tschechne,et al.  Learning Robust Objective Functions for Model Fitting in Image Understanding Applications , 2006, BMVC.

[20]  P. Ekman,et al.  Facial action coding system: a technique for the measurement of facial movement , 1978 .

[21]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

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

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