Naked image detection based on adaptive and extensible skin color model

Jiann Shu Lee; Yung Ming Kuo; Pau Choo Chung; E. Liang Chen

doi:10.1016/j.patcog.2006.11.016

Naked image detection based on adaptive and extensible skin color model

Jiann Shu Lee, Yung Ming Kuo, Pau Choo Chung, E. Liang Chen

Institute of Computer and Communication Engineering

Research output: Contribution to journal › Article › peer-review

148 Citations (Scopus)

Abstract

The paper presents a new naked image detection algorithm. A learning-based chromatic distribution-matching scheme is proposed to determine the image's skin chroma distribution online such that it can tolerate the chromatic deviation coming from special lighting without increasing false alarm. The texture feature, namely coarseness, is used to acquire accurate skin segmentation. The low-level but reliable geometrical constraints and the mug shot exclusion procedure are employed to further examine the skin regions. Experimental results show our method can achieve satisfactory performance for detecting naked images under special lighting conditions.

Original language	English
Pages (from-to)	2261-2270
Number of pages	10
Journal	Pattern Recognition
Volume	40
Issue number	8
DOIs	https://doi.org/10.1016/j.patcog.2006.11.016
Publication status	Published - 2007 Aug

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/j.patcog.2006.11.016

Cite this

@article{b54dc8099b7e4672a80a0dae803b502e,

title = "Naked image detection based on adaptive and extensible skin color model",

abstract = "The paper presents a new naked image detection algorithm. A learning-based chromatic distribution-matching scheme is proposed to determine the image's skin chroma distribution online such that it can tolerate the chromatic deviation coming from special lighting without increasing false alarm. The texture feature, namely coarseness, is used to acquire accurate skin segmentation. The low-level but reliable geometrical constraints and the mug shot exclusion procedure are employed to further examine the skin regions. Experimental results show our method can achieve satisfactory performance for detecting naked images under special lighting conditions.",

author = "Lee, {Jiann Shu} and Kuo, {Yung Ming} and Chung, {Pau Choo} and Chen, {E. Liang}",

note = "Funding Information: Authors would like to express their deep appreciation for the support of the National Science Council under Grant number NSC-92-2213-E-150-022. ",

year = "2007",

month = aug,

doi = "10.1016/j.patcog.2006.11.016",

language = "English",

volume = "40",

pages = "2261--2270",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier Limited",

number = "8",

}

TY - JOUR

T1 - Naked image detection based on adaptive and extensible skin color model

AU - Lee, Jiann Shu

AU - Kuo, Yung Ming

AU - Chung, Pau Choo

AU - Chen, E. Liang

N1 - Funding Information: Authors would like to express their deep appreciation for the support of the National Science Council under Grant number NSC-92-2213-E-150-022.

PY - 2007/8

Y1 - 2007/8

N2 - The paper presents a new naked image detection algorithm. A learning-based chromatic distribution-matching scheme is proposed to determine the image's skin chroma distribution online such that it can tolerate the chromatic deviation coming from special lighting without increasing false alarm. The texture feature, namely coarseness, is used to acquire accurate skin segmentation. The low-level but reliable geometrical constraints and the mug shot exclusion procedure are employed to further examine the skin regions. Experimental results show our method can achieve satisfactory performance for detecting naked images under special lighting conditions.

AB - The paper presents a new naked image detection algorithm. A learning-based chromatic distribution-matching scheme is proposed to determine the image's skin chroma distribution online such that it can tolerate the chromatic deviation coming from special lighting without increasing false alarm. The texture feature, namely coarseness, is used to acquire accurate skin segmentation. The low-level but reliable geometrical constraints and the mug shot exclusion procedure are employed to further examine the skin regions. Experimental results show our method can achieve satisfactory performance for detecting naked images under special lighting conditions.

UR - http://www.scopus.com/inward/record.url?scp=34247152836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34247152836&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2006.11.016

DO - 10.1016/j.patcog.2006.11.016

M3 - Article

AN - SCOPUS:34247152836

SN - 0031-3203

VL - 40

SP - 2261

EP - 2270

JO - Pattern Recognition

JF - Pattern Recognition

IS - 8

ER -

Naked image detection based on adaptive and extensible skin color model

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this