A dynamic threshold approach for skin segmentation in color images

P Yogarajah, J Condell, K Curran, A Cheddad, P McKevitt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

49 Citations (Scopus)

Abstract

This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images.Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin.These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects’s color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks.The experimental results show that our method is robust in overcoming these drawbacks.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages2225-2228
Number of pages4
DOIs
Publication statusPublished - 3 Dec 2010
EventProc. of the IEEE 17th International Conference on Image Processing (ICIP-10) - Hong Kong Convention and Exhibition Centre, Hong Kong, China
Duration: 3 Dec 2010 → …

Conference

ConferenceProc. of the IEEE 17th International Conference on Image Processing (ICIP-10)
Period3/12/10 → …

Fingerprint

Skin
Color
Pixels

Cite this

Yogarajah, P ; Condell, J ; Curran, K ; Cheddad, A ; McKevitt, P. / A dynamic threshold approach for skin segmentation in color images. Unknown Host Publication. 2010. pp. 2225-2228
@inproceedings{1903f41f011b4551a553d15815ef8686,
title = "A dynamic threshold approach for skin segmentation in color images",
abstract = "This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images.Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin.These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects’s color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks.The experimental results show that our method is robust in overcoming these drawbacks.",
author = "P Yogarajah and J Condell and K Curran and A Cheddad and P McKevitt",
year = "2010",
month = "12",
day = "3",
doi = "10.1109/ICIP.2010.5652798",
language = "English",
isbn = "978-1-4244-7994-8",
pages = "2225--2228",
booktitle = "Unknown Host Publication",

}

Yogarajah, P, Condell, J, Curran, K, Cheddad, A & McKevitt, P 2010, A dynamic threshold approach for skin segmentation in color images. in Unknown Host Publication. pp. 2225-2228, Proc. of the IEEE 17th International Conference on Image Processing (ICIP-10), 3/12/10. https://doi.org/10.1109/ICIP.2010.5652798

A dynamic threshold approach for skin segmentation in color images. / Yogarajah, P; Condell, J; Curran, K; Cheddad, A; McKevitt, P.

Unknown Host Publication. 2010. p. 2225-2228.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A dynamic threshold approach for skin segmentation in color images

AU - Yogarajah, P

AU - Condell, J

AU - Curran, K

AU - Cheddad, A

AU - McKevitt, P

PY - 2010/12/3

Y1 - 2010/12/3

N2 - This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images.Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin.These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects’s color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks.The experimental results show that our method is robust in overcoming these drawbacks.

AB - This paper presents a novel dynamic threshold approach to discriminate skin pixels and non-skin pixels in color images.Fixed decision boundaries (or fixed threshold) classification approaches are successfully applied to segment human skin.These fixed thresholds mostly failed in two situations as they only search for a certain skin color range: 1) any non-skin object may be classified as skin if non-skin objects’s color values belong to fixed threshold range. 2) any true skin may be mistakenly classified as non-skin if that skin color values do not belong to fixed threshold range. Therefore in this paper, instead of predefined fixed thresholds, novel online learned dynamic thresholds are used to overcome the above drawbacks.The experimental results show that our method is robust in overcoming these drawbacks.

U2 - 10.1109/ICIP.2010.5652798

DO - 10.1109/ICIP.2010.5652798

M3 - Conference contribution

SN - 978-1-4244-7994-8

SP - 2225

EP - 2228

BT - Unknown Host Publication

ER -