A novel feature extraction method using Pyramid Histogram of Orientation Gradients for smile recognition

Recognizing smiles is of much importance for detecting happy moods. Gabor features are conventionally widely applied to facial expression recognition, but the number of Gabor features is usually too large. We proposed to use Pyramid Histogram of Oriented Gradients (PHOG) as the features extracted for smile recognition in this paper. The comparisons between the PHOG and Gabor features using a publicly available dataset demonstrated that the PHOG with a significantly shorter vector length could achieve as high a recognition rate as the Gabor features did. Furthermore, the feature selection conducted by an AdaBoost algorithm was not needed when using the PHOG features. To further improve the recognition performance, we combined these two feature extraction methods and achieved the best smile recognition rate, indicating a good value of the PHOG features for smile recognitions.

[1]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

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

[4]  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).

[5]  Gwen Littlewort,et al.  Dynamics of Facial Expression Extracted Automatically from Video , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[6]  Zhi-Jie He,et al.  A new fast training algorithm for SVM , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[7]  Chengjun Liu,et al.  Independent component analysis of Gabor features for face recognition , 2003, IEEE Trans. Neural Networks.

[8]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[9]  David J. Kriegman,et al.  Recognition using class specific linear projection , 1997 .

[10]  Andrew J. Calder,et al.  PII: S0042-6989(01)00002-5 , 2001 .

[11]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

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

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).