基于多颜色空间的不良视频检测

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 283-286.

基于多颜色空间的不良视频检测

秦敏^1,2, 郭玉坤¹, 李金屏^1,2

1. 济南大学信息科学与工程学院,济南 250022;
2. 山东省网络环境智能计算技术重点实验室,济南 250022

收稿日期:2012-05-19 发布日期:2013-06-01
通讯作者: 李金屏(1968-),男,教授,博士,硕士生导师.研究方向:人工智能、模式识别和图像处理.E-mail:ise_lijp@ujn.edu.cn E-mail:ise_lijp@ujn.edu.cn
作者简介:秦敏(1987-),女,硕士研究生.研究方向:视频检索与分类.E-mail:qinmin0807@163.com
基金资助:
国家自然科学基金项目(60873089);山东省教育科学规划课题重点基金项目(2008ZK0007);山东省高等学校科技计划项目(J12LN19).

Ojectionable video detecting based on multiple color space

QIN Min^1,2, GUO Yu-kun¹, LI Jin-ping^1,2

1. School of Information Science and Engineering, University of Jinan, Jinan 250022, China;
2. Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan 250022, China

Received:2012-05-19 Published:2013-06-01

摘要/Abstract

摘要：

针对血腥、暴力、色情等不良视频不可能经常更新的特点,提出了一种新的机器检测和人工参与相结合的不良视频检测方法。首先,人工标定不良视频;其次,计算多颜色空间里各个颜色分量的归一化能量曲线,并建立视频特征库;最后,系统根据视频特征库自动地检测人工所标定的不良视频。实验结果表明,该方法能快速、准确地检测人工标定的不良视频,并进行有效的预警。

关键词: 不良视频, 多颜色空间, 能量曲线, 视频特征库

Abstract:

As videos such as bloody, violent and pornographic could not be updated frequently,a new objectionable videos detection method based on the combination of machine detection and manual intervention was proposed.First,objectionable video was labeled by manual method.Then the normalized energy curve was calculated through the multiple color space and the video character database was set up.Finally,the system can automatical detect the objectionable videos by querying the video character database.Experiments show the method can accurately and quickly realize the detection and early warning of the objectionable videos.

Key words: objectionable videos, multiple color space, energy curve, video character database

中图分类号:

TP391

秦敏, 郭玉坤, 李金屏. 基于多颜色空间的不良视频检测[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 283-286.

QIN Min, GUO Yu-kun, LI Jin-ping. Ojectionable video detecting based on multiple color space[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 283-286.

参考文献

[1] Jeong C Y,Kim J S,Hong K S.Appearance-based nude image detection[C]//Proceedings of the 17th International Conference on Pattern Recognition,2004:467-470.

[2] Lopes Ana P B,Sandra E F,De Avila.A bag- of-visual-features approach based on hue-sift descriptor for nude detection[C]//17th European Signal Processing Conference,2009:1552-1556.

[3] Kim C Y,Kwon O J,Kim W G,et al.Auto- matic system for filtering obscene video [C]//10th International Conference on Advanced Communication Technology,2008:1435-1438.

[4] Rea N,Lacey G,Lambe C,et al.Multi- modal periodicity analysis for illicit content detection in videos[C]//4th European Conferen- ce on Visual Media Production,2006:106-114.

[5] 吕丽,杨树堂.基于光流法的不良视频检测算法[J].计算机工程,2007,33(12):220-221. Lü Li,Yang Shu-tang.Objectionable videos detection algorithm based on optical flow[J].Computer Engineering,2007,33(12):220-221.

[6] 安红心.基于运动特征的不良视频检测算法[J].微计算机应用,2010,31(7):32-37. An Hong-xin.Objectonable video detection algorithm based on motion features [J].Microcomputer Applications,2010,31(7):32-37.

[7] 刘春,谢长生.基于Zernike矩变换与支持向量机的不良视频检测方法[J].武汉理工大学学报,2011,33(7):133-137. Liu Chun,Xie Chang-sheng.Research on adult image detection using zernike transform and support vector machine[J].Journal of Wuhan University of Technology,2011,33(7):133-137.

[8] 刘林,李金屏.基于多颜色空间和场均直方图的视频场景分类[J].中国体视学与图像分析,2011,16(1):67-74. Liu Lin,Li Jin-ping.Video scene classification based on multiple color spaces and average scene histogram[J].Chinese Journal of Stereology and Image Analysis,2011,16(1):67-74.

[9] Wang Li-wei,Zhang Yan,Feng Ju-fu.On the Euclidean distance of images[J].IEEE Transac- tions on Pattern Analysis and Machine Intelli- gence,2005,27(8):1334- 1339.

[10] 陈惠明.图像欧氏距离在人脸识别中的应用研究[J].计算机工程与设计,2008,29(14):3735- 3737. Chen Hui-ming.Application study of image Euclidean distance in face recognition[J].Compu- ter Engineering and Design,2008,29(14):3735- 3737.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed