Facial expression recognition with spatiotemporal local descriptors Guoying Zhao, Matti Pietikäinen Machine Vision Group, Infotech Oulu and Department of Electrical and Information Engineering, P. O. Box 4500 FI-90014 University of Oulu, Finland {gyzhao, mkp}@ee.oulu.fi Abstract. This paper reviews our research on facial expression recognition using spatiotemporal descriptors, combining the appearance and motion together and describing the local transition features. Experiments show very promising results. Keywords: facial expression recognition, spatiotemporal descriptors, emotion, local binary patterns. 1 Introduction The human face plays a significant role in verbal and non-verbal communication. Fully automatic and real-time facial expression recognition whose goal is to determine the emotional state of the face, e.g. happiness, sadness, surprise, neutral, anger, fear, and disgust as shown in Fig. 1, regardless of the identity of the face, could find many applications, for example, in human-computer interaction (HCI), biometrics, telecommunications and psychological research. It has been argued that to truly achieve effective human-computer interaction, there is a need for the computer to be able to interact naturally with the user, similar to the way human-human interaction takes place. Therefore, there is a growing need to understand the emotions of the user. The most informative way for machine perception of emotions is through facial expressions in video. Most of the past research on facial expression recognition has been based on static images [1,2]. Psychological studies [3] have shown, however, that facial motion is fundamental for the recognition of facial expressions. Surprise Sadness Fear Disgust Anger Happiness Figure 1. Facial expressions. Some research on using facial dynamics has been carried out; however, reliable segmentation of lips and other moving facial parts in natural environments has turned out to be a major problem. In our earlier studies [4], we proposed a method for facial expression recognition from static images using a novel face representation based on local binary pattern
5
Embed
Facial expression recognition with spatiotemporal local …gyzhao/Papers/2008/Facial expression... · 2008-04-01 · Keywords: facial expression recognition, spatiotemporal descriptors,
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Facial expression recognition with spatiotemporal local
descriptors
Guoying Zhao, Matti Pietikäinen
Machine Vision Group, Infotech Oulu and Department of Electrical and
Information Engineering, P. O. Box 4500 FI-90014 University of Oulu, Finland
{gyzhao, mkp}@ee.oulu.fi
Abstract. This paper reviews our research on facial expression recognition
using spatiotemporal descriptors, combining the appearance and motion
together and describing the local transition features. Experiments show very