Haar features for FACS AU recognition

We examined the effectiveness of using Haar features and the Adaboost boosting algorithm for FACS action unit (AU) recognition. We evaluated both recognition accuracy and processing time of this new approach compared to the state-of-the-art method of classifying Gabor responses with support vector m...

Full description

Saved in:
Bibliographic Details
Main Authors: Whitehill, J., Omlin, C.W.
Format: Conference Proceeding
Language:English
Subjects:
Boosting
Computer vision
Face detection
Face recognition
Feature extraction
Gold
Object recognition
Pixel
Support vector machine classification
Support vector machines
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We examined the effectiveness of using Haar features and the Adaboost boosting algorithm for FACS action unit (AU) recognition. We evaluated both recognition accuracy and processing time of this new approach compared to the state-of-the-art method of classifying Gabor responses with support vector machines. Empirical results on the Cohn-Kanade facial expression database showed that the Haar+Adaboost method yields AU recognition rates comparable to those of the Gabor+SVM method but operates at least two orders of magnitude more quickly
DOI:10.1109/FGR.2006.61