ICIP 2006, Atlanta, GA

Slide Show

Atlanta Conv. & Vis. Bureau


Technical Program

Paper Detail

Session:Face Recognition
Time:Tuesday, October 10, 14:20 - 17:00
Presentation: Poster
Authors: Shuang Xu; Beijing Institute of Technology 
 Yun-De Jia; Beijing Institute of Technology 
 Xiaoxun Zhang; Beijing Institute of Technology 
Abstract: In this paper, facial expression is coded by steerable filters which are rotated very efficiently by taking a suitable linear combination of basis filters and allow adaptive control over phase as well as orientations. Local features extracted by steerable filters are locally stable with respect to scale, noise, and brightness changes, and are distinctive enough to capture subtle facial expression cues. Further more, steerable filters are implemented within a Gaussian pyramid to make use of discriminative power in scale-space. Responses of the filters are concatenated to an augmented feature vector to evaluate similarity between different facial expression images with the nearest-neighbor rule for the final decision. In Comparison with Gabor filters, steerable filters save much computational cost and obtain comparable performance with fewer features. Experiments on the JAFFE database demonstrate the effectiveness of steerable filters for coding facial expression.