Facial expression recognition using facial features andmanifold learning

Authors:
Raymond Ptucha;Andreas Savakis
Affiliations:
Computing and Information Sciences and Computer Engineering, Rochester Institute of Technology, Rochester, NY;Computing and Information Sciences and Computer Engineering, Rochester Institute of Technology, Rochester, NY
Venue:
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
Year:
2010

Citing 9
Cited 0

Active shape models—their training and application

Computer Vision and Image Understanding
Detecting Faces in Images: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Comprehensive Database for Facial Expression Analysis

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Facial features localization in front view head and shoulders images

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 06
Locating Facial Features with an Extended Active Shape Model

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Head Pose Estimation in Computer Vision: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Natural facial expression recognition using differential-AAM and manifold learning

Pattern Recognition
Appearance manifold of facial expression

ICCV'05 Proceedings of the 2005 international conference on Computer Vision in Human-Computer Interaction
Facial Expression Recognition in Image Sequences Using Geometric Deformation Features and Support Vector Machines

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper explores robust facial expression recognition techniques based on the underlying low dimensional manifolds embedded in facial images of varying expression. Faces are automatically detected and facial features are extracted, normalized and mapped onto a low dimensional projection surface using Locality Preserving Projections. Alternatively, processed image pixels are used for manifold construction. Classification models robustly estimate expression from the low dimensional projections in manifold space. This method performs robustly in natural settings, enabling more engaging human computer interfaces.