Skin Information Combined Saliency Detection for Classifying Objectionable Images

被引：0

作者：

Jeong, Chi Yoon ^{[1
]}

Han, Seungwan ^{[1
]}

机构：

[1] Elect & Telecommun Res Inst, Video Surveillance Res Sect, Taejon 305606, South Korea

来源：

2013 INTERNATIONAL CONFERENCE ON ICT CONVERGENCE (ICTC 2013): FUTURE CREATIVE CONVERGENCE TECHNOLOGIES FOR NEW ICT ECOSYSTEMS | 2013年

关键词：

Saliency Detection; Skin Color; Region of Interest; Objectioable Image Classification; Visual Descriptors;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Although visual attention models have shown good performance in general environments, applying it for filtering objectionable image needs consideration for skin information. Therefore, in this paper, we proposed the saliency detection method specialized in adult image classification using the skin color and the contrast information. Skin information combined saliency map is generated by merging the saliency map of visual attention model and the skin probability map. In order to prove the effectiveness of the proposed method, we consider the use of a saliency map in objectionable image classification.

引用

页码：738 / 739

页数：2

共 11 条

[1]

Achanta R., 2010, P F IEEE INT C IM PR

[2]

[Anonymous], 2002, Introduction to MPEG-7: Multimedia Content Description Interface

[3]

[Anonymous], MULTIMEDIA TOOLS APP

[4]

[Anonymous], 1999, Advances in kernel methods: Support vector learning

[5]

[Anonymous], P IEEE INT C COMP VI

[6]

[Anonymous], 2009, P IEEE C COMP VIS PA

[7]

Jeong C. Y., 2006, P IEEE INT C IM PROC

[8]

Jones M. J., 1998, 9811112 CRL

[9]

Lopes Ana P. B., 2009, 2009 17th European Signal Processing Conference (EUSIPCO 2009), P1552

[10]

Ulges A, P 2011 IEEE INT C MU

← 1 2 →