Coding facial expressions with Gabor wavelets

TLDR

The paper proposes a method to extract facial expression information from images. The method encodes facial images with a topographically ordered set of multi‑orientation, multi‑resolution Gabor filters and compares the resulting similarity space to human semantic ratings. The Gabor‑based representation enables a facial expression classifier and demonstrates psychological plausibility, suggesting usefulness for human‑computer interfaces.

Abstract

A method for extracting information about facial expressions from images is presented. Facial expression images are coded using a multi-orientation multi-resolution set of Gabor filters which are topographically ordered and aligned approximately with the face. The similarity space derived from this representation is compared with one derived from semantic ratings of the images by human observers. The results show that it is possible to construct a facial expression classifier with Gabor coding of the facial images as the input stage. The Gabor representation shows a significant degree of psychological plausibility, a design feature which may be important for human-computer interfaces.