Automatic skin segmentation for gesture recognition combining region and support vector machine active learning

Junwei Han; George M. Award; Alistair Sutherland; Hai Wu

doi:10.1109/FGR.2006.27

Automatic skin segmentation for gesture recognition combining region and support vector machine active learning

Junwei Han, George M. Award, Alistair Sutherland, Hai Wu

Dublin City University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

39 引用（Scopus）

摘要

Skin segmentation is the cornerstone of many applications such as gesture recognition, face detection, and objectionable image filtering. In this paper, we attempt to address the skin segmentation problem for gesture recognition. Initially, given a gesture video sequence, a generic skin model is applied to the first couple of frames to automatically collect the training data. Then, an SVM classifier based on active learning is used to identify the skin pixels. Finally, the results are improved by incorporating region segmentation. The proposed algorithm is fully automatic and adaptive to different signers. We have tested our approach on the ECHO database. Comparing with other existing algorithms, our method could achieve better performance.

源语言	英语
主期刊名	FGR 2006
主期刊副标题	Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
页	237-242
页数	6
DOI	https://doi.org/10.1109/FGR.2006.27
出版状态	已出版 - 2006
已对外发布	是
活动	FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition - Southampton, 英国期限: 10 4月 2006 → 12 4月 2006

出版系列

姓名	FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
卷	2006

会议

会议	FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition
国家/地区	英国
市	Southampton
时期	10/04/06 → 12/04/06

访问文件

10.1109/FGR.2006.27

其它文件与链接

链接到 Scopus 的出版物

引用此

Han, J., Award, G. M., Sutherland, A., & Wu, H. (2006). Automatic skin segmentation for gesture recognition combining region and support vector machine active learning. 在 FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (页码 237-242). 文章 1613026 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition; 卷 2006). https://doi.org/10.1109/FGR.2006.27

Han, Junwei ; Award, George M. ; Sutherland, Alistair 等. / Automatic skin segmentation for gesture recognition combining region and support vector machine active learning. FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. 2006. 页码 237-242 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition).

@inproceedings{f5c5503c5a844783b202f8cd241fe502,

title = "Automatic skin segmentation for gesture recognition combining region and support vector machine active learning",

abstract = "Skin segmentation is the cornerstone of many applications such as gesture recognition, face detection, and objectionable image filtering. In this paper, we attempt to address the skin segmentation problem for gesture recognition. Initially, given a gesture video sequence, a generic skin model is applied to the first couple of frames to automatically collect the training data. Then, an SVM classifier based on active learning is used to identify the skin pixels. Finally, the results are improved by incorporating region segmentation. The proposed algorithm is fully automatic and adaptive to different signers. We have tested our approach on the ECHO database. Comparing with other existing algorithms, our method could achieve better performance.",

author = "Junwei Han and Award, {George M.} and Alistair Sutherland and Hai Wu",

year = "2006",

doi = "10.1109/FGR.2006.27",

language = "英语",

isbn = "0769525032",

series = "FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition",

pages = "237--242",

booktitle = "FGR 2006",

note = "FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition ; Conference date: 10-04-2006 Through 12-04-2006",

}

Han, J, Award, GM, Sutherland, A & Wu, H 2006, Automatic skin segmentation for gesture recognition combining region and support vector machine active learning. 在 FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition., 1613026, FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition, 卷 2006, 页码 237-242, FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition, Southampton, 英国, 10/04/06. https://doi.org/10.1109/FGR.2006.27

Automatic skin segmentation for gesture recognition combining region and support vector machine active learning. / Han, Junwei; Award, George M.; Sutherland, Alistair 等.
FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. 2006. 页码 237-242 1613026 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition; 卷 2006).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Automatic skin segmentation for gesture recognition combining region and support vector machine active learning

AU - Han, Junwei

AU - Award, George M.

AU - Sutherland, Alistair

AU - Wu, Hai

PY - 2006

Y1 - 2006

N2 - Skin segmentation is the cornerstone of many applications such as gesture recognition, face detection, and objectionable image filtering. In this paper, we attempt to address the skin segmentation problem for gesture recognition. Initially, given a gesture video sequence, a generic skin model is applied to the first couple of frames to automatically collect the training data. Then, an SVM classifier based on active learning is used to identify the skin pixels. Finally, the results are improved by incorporating region segmentation. The proposed algorithm is fully automatic and adaptive to different signers. We have tested our approach on the ECHO database. Comparing with other existing algorithms, our method could achieve better performance.

AB - Skin segmentation is the cornerstone of many applications such as gesture recognition, face detection, and objectionable image filtering. In this paper, we attempt to address the skin segmentation problem for gesture recognition. Initially, given a gesture video sequence, a generic skin model is applied to the first couple of frames to automatically collect the training data. Then, an SVM classifier based on active learning is used to identify the skin pixels. Finally, the results are improved by incorporating region segmentation. The proposed algorithm is fully automatic and adaptive to different signers. We have tested our approach on the ECHO database. Comparing with other existing algorithms, our method could achieve better performance.

UR - http://www.scopus.com/inward/record.url?scp=33750796086&partnerID=8YFLogxK

U2 - 10.1109/FGR.2006.27

DO - 10.1109/FGR.2006.27

M3 - 会议稿件

AN - SCOPUS:33750796086

SN - 0769525032

SN - 9780769525037

T3 - FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition

SP - 237

EP - 242

BT - FGR 2006

T2 - FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition

Y2 - 10 April 2006 through 12 April 2006

ER -

Han J, Award GM, Sutherland A, Wu H. Automatic skin segmentation for gesture recognition combining region and support vector machine active learning. 在 FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. 2006. 页码 237-242. 1613026. (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition). doi: 10.1109/FGR.2006.27

Automatic skin segmentation for gesture recognition combining region and support vector machine active learning

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此