Conference Proceeding

Facial expression recognition based on diffeomorphic matching

Dept. of Electr. Eng., Univ. of Texas at Dallas, Dallas, TX, USA
Proceedings / ICIP ... International Conference on Image Processing 10/2010; DOI:10.1109/ICIP.2010.5650670 pp.4549 - 4552 In proceeding of: Image Processing (ICIP), 2010 17th IEEE International Conference on
Source: IEEE Xplore

ABSTRACT This paper presents a new framework for facial expression recognition based on diffeomorphic matching. First landmarks are selected based on a manual or automatic method. All of the landmarks from different images are registered to a reference landmark set using a rigid registration algorithm. The pair-wise geodesic distance between all sets of landmarks are then computed using diffeomorphic matching. Finally, a K-Nearest Neighbor classifier (KNN) is used to classify a query image using the geodesic distances. Both the classification and classical MultiDimensional Scaling results show that geodesic distance is more effective than Euclidean distance on capturing the face shape variation.

0 0
 · 
0 Bookmarks
 · 
22 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

automatic method
 
different images
 
face shape variation
 
facial expression recognition
 
First landmarks
 
geodesic distance
 
geodesic distances
 
K-Nearest Neighbor classifier
 
landmarks
 
pair-wise geodesic distance
 
paper presents
 
query image
 
reference landmark
 
rigid registration algorithm