Dynamic facial expression recognition using local patch and LBP-TOP

Yiming Wang; Hui Yu; Brett Stevens; Honghai Liu

doi:10.1109/HSI.2015.7170694

Dynamic facial expression recognition using local patch and LBP-TOP

Yiming Wang, Hui Yu, Brett Stevens, Honghai Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

405 Downloads (Pure)

Abstract

Local binary pattern on three orthogonal planes (LBP-TOP) is one of the most popular method for dynamic texture analysis and has been successfully applied to facial expression analysis. Yet an effective LBP-TOP operator highly relies on preprocessing. And, like many appearance-based approaches, this approach reserves more identity-related cues rather than expression. In this work, we propose a fully automatic approach for facial expression recognition based on points registration, localized patch extraction and LBP-TOP feature representation. The efficiency of this method is evaluated on CK+ database. Results show that the proposed method has achieved a better performance compared with existing methods.

Original language	English
Title of host publication	2015 8th International Conference on Human System Interactions (HSI)
Pages	362-367
Number of pages	6
DOIs	https://doi.org/10.1109/HSI.2015.7170694
Publication status	Published - 30 Jul 2015
Event	Human System Interactions (HSI), 2015, 8th International Conference - Warsaw, United Kingdom Duration: 25 Jun 2015 → 27 Oct 2015

Conference

Conference	Human System Interactions (HSI), 2015, 8th International Conference
Country/Territory	United Kingdom
City	Warsaw
Period	25/06/15 → 27/10/15

Access to Document

10.1109/HSI.2015.7170694

Dynamic facial expression recognition using local patch and LBP-TOPAccepted author manuscript (Post-print), 411 KB

Cite this

@inproceedings{4e14e70cab874e55b46d0c3e6e9a7d0a,

title = "Dynamic facial expression recognition using local patch and LBP-TOP",

abstract = "Local binary pattern on three orthogonal planes (LBP-TOP) is one of the most popular method for dynamic texture analysis and has been successfully applied to facial expression analysis. Yet an effective LBP-TOP operator highly relies on preprocessing. And, like many appearance-based approaches, this approach reserves more identity-related cues rather than expression. In this work, we propose a fully automatic approach for facial expression recognition based on points registration, localized patch extraction and LBP-TOP feature representation. The efficiency of this method is evaluated on CK+ database. Results show that the proposed method has achieved a better performance compared with existing methods.",

author = "Yiming Wang and Hui Yu and Brett Stevens and Honghai Liu",

year = "2015",

month = jul,

day = "30",

doi = "10.1109/HSI.2015.7170694",

language = "English",

pages = "362--367",

booktitle = "2015 8th International Conference on Human System Interactions (HSI)",

note = "Human System Interactions (HSI), 2015, 8th International Conference ; Conference date: 25-06-2015 Through 27-10-2015",

}

TY - GEN

T1 - Dynamic facial expression recognition using local patch and LBP-TOP

AU - Wang, Yiming

AU - Yu, Hui

AU - Stevens, Brett

AU - Liu, Honghai

PY - 2015/7/30

Y1 - 2015/7/30

N2 - Local binary pattern on three orthogonal planes (LBP-TOP) is one of the most popular method for dynamic texture analysis and has been successfully applied to facial expression analysis. Yet an effective LBP-TOP operator highly relies on preprocessing. And, like many appearance-based approaches, this approach reserves more identity-related cues rather than expression. In this work, we propose a fully automatic approach for facial expression recognition based on points registration, localized patch extraction and LBP-TOP feature representation. The efficiency of this method is evaluated on CK+ database. Results show that the proposed method has achieved a better performance compared with existing methods.

AB - Local binary pattern on three orthogonal planes (LBP-TOP) is one of the most popular method for dynamic texture analysis and has been successfully applied to facial expression analysis. Yet an effective LBP-TOP operator highly relies on preprocessing. And, like many appearance-based approaches, this approach reserves more identity-related cues rather than expression. In this work, we propose a fully automatic approach for facial expression recognition based on points registration, localized patch extraction and LBP-TOP feature representation. The efficiency of this method is evaluated on CK+ database. Results show that the proposed method has achieved a better performance compared with existing methods.

U2 - 10.1109/HSI.2015.7170694

DO - 10.1109/HSI.2015.7170694

M3 - Conference contribution

SP - 362

EP - 367

BT - 2015 8th International Conference on Human System Interactions (HSI)

T2 - Human System Interactions (HSI), 2015, 8th International Conference

Y2 - 25 June 2015 through 27 October 2015

ER -

Dynamic facial expression recognition using local patch and LBP-TOP

Abstract

Conference

Access to Document

Fingerprint

Cite this