The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo descreve uma nova segmentação de cores baseada em um diagrama de cromaticidade RGB normalizado para detecção de rosto. A pele do rosto é extraída de imagens coloridas usando uma região de pele grossa com limites fixos seguida por uma região de pele fina com limites variáveis. Dois histogramas recentemente desenvolvidos que apresentam picos proeminentes de cor da pele e cores não-pele são empregados para ajustar os limites da região da pele. A abordagem proposta não necessita de um modelo de cor de pele, que depende de um parâmetro específico da câmera e geralmente é limitado a uma condição ambiental específica, e não são necessárias imagens de amostra. Os resultados experimentais usando imagens coloridas de rostos de várias raças sob diversas condições de iluminação e fundos complexos, obtidos de quatro recursos diferentes na Internet, mostram uma alta taxa de detecção de 87%. Os resultados da taxa de detecção e do tempo de cálculo são comparáveis ao conhecido método de detecção de faces em tempo real proposto por Viola-Jones [11],[12].
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Aryuanto SOETEDJO, Koichi YAMADA, "Skin Color Segmentation Using Coarse-to-Fine Region on Normalized RGB Chromaticity Diagram for Face Detection" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 10, pp. 2493-2502, October 2008, doi: 10.1093/ietisy/e91-d.10.2493.
Abstract: This paper describes a new color segmentation based on a normalized RGB chromaticity diagram for face detection. Face skin is extracted from color images using a coarse skin region with fixed boundaries followed by a fine skin region with variable boundaries. Two newly developed histograms that have prominent peaks of skin color and non-skin colors are employed to adjust the boundaries of the skin region. The proposed approach does not need a skin color model, which depends on a specific camera parameter and is usually limited to a particular environment condition, and no sample images are required. The experimental results using color face images of various races under varying lighting conditions and complex backgrounds, obtained from four different resources on the Internet, show a high detection rate of 87%. The results of the detection rate and computation time are comparable to the well known real-time face detection method proposed by Viola-Jones [11],[12].
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.10.2493/_p
Copiar
@ARTICLE{e91-d_10_2493,
author={Aryuanto SOETEDJO, Koichi YAMADA, },
journal={IEICE TRANSACTIONS on Information},
title={Skin Color Segmentation Using Coarse-to-Fine Region on Normalized RGB Chromaticity Diagram for Face Detection},
year={2008},
volume={E91-D},
number={10},
pages={2493-2502},
abstract={This paper describes a new color segmentation based on a normalized RGB chromaticity diagram for face detection. Face skin is extracted from color images using a coarse skin region with fixed boundaries followed by a fine skin region with variable boundaries. Two newly developed histograms that have prominent peaks of skin color and non-skin colors are employed to adjust the boundaries of the skin region. The proposed approach does not need a skin color model, which depends on a specific camera parameter and is usually limited to a particular environment condition, and no sample images are required. The experimental results using color face images of various races under varying lighting conditions and complex backgrounds, obtained from four different resources on the Internet, show a high detection rate of 87%. The results of the detection rate and computation time are comparable to the well known real-time face detection method proposed by Viola-Jones [11],[12].},
keywords={},
doi={10.1093/ietisy/e91-d.10.2493},
ISSN={1745-1361},
month={October},}
Copiar
TY - JOUR
TI - Skin Color Segmentation Using Coarse-to-Fine Region on Normalized RGB Chromaticity Diagram for Face Detection
T2 - IEICE TRANSACTIONS on Information
SP - 2493
EP - 2502
AU - Aryuanto SOETEDJO
AU - Koichi YAMADA
PY - 2008
DO - 10.1093/ietisy/e91-d.10.2493
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2008
AB - This paper describes a new color segmentation based on a normalized RGB chromaticity diagram for face detection. Face skin is extracted from color images using a coarse skin region with fixed boundaries followed by a fine skin region with variable boundaries. Two newly developed histograms that have prominent peaks of skin color and non-skin colors are employed to adjust the boundaries of the skin region. The proposed approach does not need a skin color model, which depends on a specific camera parameter and is usually limited to a particular environment condition, and no sample images are required. The experimental results using color face images of various races under varying lighting conditions and complex backgrounds, obtained from four different resources on the Internet, show a high detection rate of 87%. The results of the detection rate and computation time are comparable to the well known real-time face detection method proposed by Viola-Jones [11],[12].
ER -