Shape and texture based facial action and emotion recognition

Li Zhang; Kamlesh Mistry; Alamgir Hossain

Shape and texture based facial action and emotion recognition

Li Zhang, Kamlesh Mistry, Alamgir Hossain

Computer Information Sciences Department

Research output: Contribution to conference › Paper › peer-review

5 Citations (Scopus)

Abstract

In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees of pose variations. We employ the Active Appearance Model to perform real-time face tracking and extract both texture and geometric representations of images. A POSIT algorithm is also used to identify head rotations. The extracted texture and shape features are employed to detect 18 facial actions and seven basic emotions. The overall system is integrated with a humanoid robot platform to further extend its vision APIs. The system proved to be able to deal with challenging facial emotion recognition tasks with various pose variations.

Original language	English
Publication status	Published - 5 May 2014
Event	13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014) - Paris, France Duration: 5 May 2014 → …

Conference

Conference	13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)
Period	5/05/14 → …

Keywords

Active Appearance model
Facial emotion recognition
POSIT

Access to Document

http://delivery.acm.org/10.1145/2620000/2616112/p1659-zhang.pdf?ip=193.63.36.41&id=2616112&acc=ACTIVE%20SERVICE&key=BF07A2EE685417C5%2E3459FC42C4D3CA19%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=605226408&CFTOKEN=57072197&__acm__=1417710505_616e7c5141171e

Cite this

Zhang, L., Mistry, K., & Hossain, A. (2014). Shape and texture based facial action and emotion recognition. Paper presented at 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014). http://delivery.acm.org/10.1145/2620000/2616112/p1659-zhang.pdf?ip=193.63.36.41&id=2616112&acc=ACTIVE%20SERVICE&key=BF07A2EE685417C5%2E3459FC42C4D3CA19%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=605226408&CFTOKEN=57072197&__acm__=1417710505_616e7c5141171e

@conference{23fc61dcc1194eceaba106c79f76be43,

title = "Shape and texture based facial action and emotion recognition",

abstract = "In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees of pose variations. We employ the Active Appearance Model to perform real-time face tracking and extract both texture and geometric representations of images. A POSIT algorithm is also used to identify head rotations. The extracted texture and shape features are employed to detect 18 facial actions and seven basic emotions. The overall system is integrated with a humanoid robot platform to further extend its vision APIs. The system proved to be able to deal with challenging facial emotion recognition tasks with various pose variations.",

keywords = "Active Appearance model, Facial emotion recognition, POSIT",

author = "Li Zhang and Kamlesh Mistry and Alamgir Hossain",

year = "2014",

month = may,

day = "5",

language = "English",

note = "13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014) ; Conference date: 05-05-2014",

}

Zhang, L, Mistry, K & Hossain, A 2014, 'Shape and texture based facial action and emotion recognition', Paper presented at 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), 5/05/14. <http://delivery.acm.org/10.1145/2620000/2616112/p1659-zhang.pdf?ip=193.63.36.41&id=2616112&acc=ACTIVE%20SERVICE&key=BF07A2EE685417C5%2E3459FC42C4D3CA19%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=605226408&CFTOKEN=57072197&__acm__=1417710505_616e7c5141171e>

TY - CONF

T1 - Shape and texture based facial action and emotion recognition

AU - Zhang, Li

AU - Mistry, Kamlesh

AU - Hossain, Alamgir

PY - 2014/5/5

Y1 - 2014/5/5

N2 - In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees of pose variations. We employ the Active Appearance Model to perform real-time face tracking and extract both texture and geometric representations of images. A POSIT algorithm is also used to identify head rotations. The extracted texture and shape features are employed to detect 18 facial actions and seven basic emotions. The overall system is integrated with a humanoid robot platform to further extend its vision APIs. The system proved to be able to deal with challenging facial emotion recognition tasks with various pose variations.

AB - In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees of pose variations. We employ the Active Appearance Model to perform real-time face tracking and extract both texture and geometric representations of images. A POSIT algorithm is also used to identify head rotations. The extracted texture and shape features are employed to detect 18 facial actions and seven basic emotions. The overall system is integrated with a humanoid robot platform to further extend its vision APIs. The system proved to be able to deal with challenging facial emotion recognition tasks with various pose variations.

KW - Active Appearance model

KW - Facial emotion recognition

KW - POSIT

M3 - Paper

T2 - 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)

Y2 - 5 May 2014

ER -

Shape and texture based facial action and emotion recognition

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this