5 March 2018 iFER: facial expression recognition using automatically selected geometric eye and eyebrow features
Author Affiliations +
Abstract
Facial expressions have an important role in interpersonal communications and estimation of emotional states or intentions. Automatic recognition of facial expressions has led to many practical applications and became one of the important topics in computer vision. We present a facial expression recognition system that relies on geometry-based features extracted from eye and eyebrow regions of the face. The proposed system detects keypoints on frontal face images and forms a feature set using geometric relationships among groups of detected keypoints. Obtained feature set is refined and reduced using the sequential forward selection (SFS) algorithm and fed to a support vector machine classifier to recognize five facial expression classes. The proposed system, iFER (eye–eyebrow only facial expression recognition), is robust to lower face occlusions that may be caused by beards, mustaches, scarves, etc. and lower face motion during speech production. Preliminary experiments on benchmark datasets produced promising results outperforming previous facial expression recognition studies using partial face features, and comparable results to studies using whole face information, only slightly lower by   ∼  2.5  %   compared to the best whole face facial recognition system while using only   ∼  1  /  3 of the facial region.
© 2018 SPIE and IS&T
Ismail Oztel, Ismail Oztel, Gozde Yolcu, Gozde Yolcu, Cemil Öz, Cemil Öz, Serap Kazan, Serap Kazan, Filiz Bunyak, Filiz Bunyak, } "iFER: facial expression recognition using automatically selected geometric eye and eyebrow features," Journal of Electronic Imaging 27(2), 023003 (5 March 2018). https://doi.org/10.1117/1.JEI.27.2.023003 . Submission: Received: 19 September 2017; Accepted: 9 February 2018
Received: 19 September 2017; Accepted: 9 February 2018; Published: 5 March 2018
JOURNAL ARTICLE
9 PAGES


SHARE
RELATED CONTENT


Back to Top