Improved skin segmentation for TV image enhancement, using color and texture features

B. Zafarifar; A. Martiniere; P.H.N. With, de

doi:10.1109/ICCE.2010.5418755

Improved skin segmentation for TV image enhancement, using color and texture features

B. Zafarifar, A. Martiniere, P.H.N. With, de

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

12 Citations (Scopus)

191 Downloads (Pure)

Abstract

Maintaining natural appearance for human face and skin areas is essential in TV image enhancement. High-end TV video processing chips include skin detectors for this purpose. This paper presents a technique for improved skin detection, using a trainable color feature and a multi-scale texture feature. Evaluation on a database of 173 manually annotated natural images shows that at a true positive rate of 90%, the proposed technique yields a false positive rate of 12%, as compared to 19% and 20% of two color-only skin detectors.

Original language	English
Title of host publication	Proceedings International Conference on Consumer Electronics (ICCE2010), 9-13 January 2010, Las Vegas, Nevada
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	373-374
ISBN (Print)	978-1-4244-4314-7
DOIs	https://doi.org/10.1109/ICCE.2010.5418755
Publication status	Published - 2010

Access to Document

10.1109/ICCE.2010.5418755

Metis234223Final published version, 1.73 MB

Cite this

@inproceedings{d313ea85d7e143a78961104e921afc1c,

title = "Improved skin segmentation for TV image enhancement, using color and texture features",

abstract = "Maintaining natural appearance for human face and skin areas is essential in TV image enhancement. High-end TV video processing chips include skin detectors for this purpose. This paper presents a technique for improved skin detection, using a trainable color feature and a multi-scale texture feature. Evaluation on a database of 173 manually annotated natural images shows that at a true positive rate of 90%, the proposed technique yields a false positive rate of 12%, as compared to 19% and 20% of two color-only skin detectors.",

author = "B. Zafarifar and A. Martiniere and {With, de}, P.H.N.",

year = "2010",

doi = "10.1109/ICCE.2010.5418755",

language = "English",

isbn = "978-1-4244-4314-7",

pages = "373--374",

booktitle = "Proceedings International Conference on Consumer Electronics (ICCE2010), 9-13 January 2010, Las Vegas, Nevada",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Improved skin segmentation for TV image enhancement, using color and texture features. / Zafarifar, B.; Martiniere, A.; With, de, P.H.N.
Proceedings International Conference on Consumer Electronics (ICCE2010), 9-13 January 2010, Las Vegas, Nevada. Piscataway: Institute of Electrical and Electronics Engineers, 2010. p. 373-374.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Improved skin segmentation for TV image enhancement, using color and texture features

AU - Zafarifar, B.

AU - Martiniere, A.

AU - With, de, P.H.N.

PY - 2010

Y1 - 2010

N2 - Maintaining natural appearance for human face and skin areas is essential in TV image enhancement. High-end TV video processing chips include skin detectors for this purpose. This paper presents a technique for improved skin detection, using a trainable color feature and a multi-scale texture feature. Evaluation on a database of 173 manually annotated natural images shows that at a true positive rate of 90%, the proposed technique yields a false positive rate of 12%, as compared to 19% and 20% of two color-only skin detectors.

AB - Maintaining natural appearance for human face and skin areas is essential in TV image enhancement. High-end TV video processing chips include skin detectors for this purpose. This paper presents a technique for improved skin detection, using a trainable color feature and a multi-scale texture feature. Evaluation on a database of 173 manually annotated natural images shows that at a true positive rate of 90%, the proposed technique yields a false positive rate of 12%, as compared to 19% and 20% of two color-only skin detectors.

U2 - 10.1109/ICCE.2010.5418755

DO - 10.1109/ICCE.2010.5418755

M3 - Conference contribution

SN - 978-1-4244-4314-7

SP - 373

EP - 374

BT - Proceedings International Conference on Consumer Electronics (ICCE2010), 9-13 January 2010, Las Vegas, Nevada

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Improved skin segmentation for TV image enhancement, using color and texture features

Abstract

Access to Document

Fingerprint

Cite this