基于高层语义视觉词袋的色情图像过滤模型

doi:10.3724/SP.J.1087.2011.01847

计算机应用 ›› 2011, Vol. 31 ›› Issue (07): 1847-1849.DOI: 10.3724/SP.J.1087.2011.01847

基于高层语义视觉词袋的色情图像过滤模型

吕林涛¹,赵呈轩¹,尚进¹,杨宇祥²

1. 西安理工大学计算机科学与工程学院，西安 710048
2. 西安理工大学机械与精密仪器工程学院，西安 710048

收稿日期:2010-12-17 修回日期:2011-02-09 发布日期:2011-07-01 出版日期:2011-07-01
通讯作者: 吕林涛
作者简介:吕林涛(1955-),男,陕西西安人,教授,主要研究方向:网络与信息安全、数据挖掘;
赵呈轩(1982-),男,河南新乡人,硕士研究生,主要研究方向:网络与信息安全;
尚进(1984-),男,河南郑州人,硕士研究生,主要研究方向:网络与信息安全;
杨宇祥(1974-),男,湖南湘潭人,副教授,博士,主要研究方向:生物医学信号检测与处理。
基金资助:
陕西省自然科学研究计划项目;陕西省自然科学研究计划项目;西安理工大学学科联合研究项目

Pornographic images filtering model based on high-level semantic bag-of-visual-words

Lin-tao LV¹,Cheng-xuan ZHAO¹,Jin SHANG¹,Yu-xiang YANG²

1. School of Computer Science and Engineering, Xian University of Technology, Xian Shaanxi 710048,China
2. School of Mechanical and Precision Instrument Engineering, Xian University of Technology, Xian Shaanxi 710048, China

Received:2010-12-17 Revised:2011-02-09 Online:2011-07-01 Published:2011-07-01
Contact: Lin-tao LV

摘要/Abstract

摘要： 针对目前色情图像过滤算法对比基尼图像和类肤色图像误检率过高，且不能有效过滤带有淫秽动作的多人色情图像的缺点，提出一种基于高层语义视觉词袋的色情图像过滤模型。该模型首先通过改进的SURF算法提取色情场景局部特征点，然后融合视觉单词的上下文和空间相关高层语义特征，从而构建色情图像的高层语义词典。实验结果表明，该模型检测带有淫秽动作的多人色情图像准确率可达87.6%，明显高于现有的视觉词袋色情图像过滤算法。

关键词: 色情图像过滤, 图像高层语义, 语义树, 视觉词袋, SURF

Abstract: Current Pornographic images filtering algorithms have some problems, such as the high false positive rate toward the bikinis images and insufficiency of filtering pornographic images with pornographic actions. The paper proposes a novel pornographic image filtering model based on High-level Semantic Bag-Of-Visual-Words. Firstly, local feature points in sex scene are detected using the SURF algorithm and then high-level semantic dictionary is constructed by fusing the context of the visual vocabularies and spatial-related high-level semantic features of pornographic images. Experimental results show that the model has an accuracy up to 87.6% when testing the multi-person pornographic images, which is significantly higher than the existing pornographic image filtering algorithm based on Bag-Of-Visual-Words.

Key words: adult images filtering, image high-level semantic, semantic tree, Bag-Of-Visual-Words, SURF

中图分类号:

吕林涛赵呈轩尚进杨宇祥. 基于高层语义视觉词袋的色情图像过滤模型[J]. 计算机应用, 2011, 31(07): 1847-1849.

Lin-tao LV Cheng-xuan ZHAO Jin SHANG Yu-xiang YANG. Pornographic images filtering model based on high-level semantic bag-of-visual-words[J]. Journal of Computer Applications, 2011, 31(07): 1847-1849.

参考文献

[1]UIJLINGS J R R, SMEULDERS A W H, SCHA R J H. Real-time visual concept classification [J]. IEEE Transactions on Multimedia, 2010,12(7):665-681.

[2]WU LEI, HOI S C H, YU NENGHAI. Semantics-preserving bag-of-words models and applications [J]. IEEE Transactions on Image Processing, 2010,19(7):1908-1920.

[3]DESELAERS T, PIMENIDIS L, NRY H. Bag-of-visual-words models for adult image classification and filtering [C]// ICPR 2008: 19th International Conference on Pattern Recognition. Washington, DC: IEEE Computer Society, 2008: 1-4.

[4]LOPES A P B, de AVILA S E F, PEIXOTO A N A, et al. A bag-of-features approach based on HUE-SIFT descriptor for nude detection [C]// EUSIPCO 2009: Proceedings of the 17th European Signal Processing Conference. Glasgow,Scotland: Mendeley, 2009:1552-1556.

[5]LOPES A P B, de AVILA S E F, PEIXOTO A N A, et al. Nude detection in video using bag-of-visual-features [C]// SIBGRAPI09: Proceedings of the 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing. Washington, DC: IEEE Computer Society, 2009: 224-231.

[6]LIU YIZHI, XIE HONGTAO. Constructing SURF visual-words for pornographic images detection [C]// ICCIT09: 12th International Conference on Computers and Information Technology. Washington, DC: IEEE, 2009:404-407.

[7]LUO JUAN, GWON O. A comparison of SIFT, PCA-SIFT and SURF [J]. International Journal of Image Processing, 2009,3(4):143-152.

[8]王宇石,李远宁,高文.基于局部视觉单词分布的成人图像检测[J].北京理工大学学报,2008,28(5):410-413.

[9]王宇石,高文.基于视觉单词和语义映射的色情图像检测算法[J].高技术通讯,2009,19(10):1041-1047.

[10]LI TENG, MEI TAO, KWEON I, et al. Contextual bag-of-words for visual categorization [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010, 21(4):381-392.

[11]WANG MEI, WU YANLING, LI GUANGDA, et al. Object recognition via adaptive multi-level feature integration [C]// APWEB 2010: 12th International Asia-Pacific Web Conference. Washington, DC: IEEE, 2010: 253-259.

[12]CHEN MIANSHU, FU PING, LI YONG, et al. Condensed semantic tree model for image category representation [C]// 2010 ICCAE: Proceedings of the 2nd International Conference on Computer and Automation Engineering. Chongqing: [s.n.], 2010,4:358-362.

基于高层语义视觉词袋的色情图像过滤模型

Pornographic images filtering model based on high-level semantic bag-of-visual-words

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

[1]	杜柳青, 许贺作, 余永维, 张建恒. 基于改进SURF算法的柔性装夹机器人快速工件匹配方法[J]. 计算机应用, 2018, 38(7): 2050-2055.
[2]	王茜, 陈一民, 丁友东. 复杂环境中基于视觉词袋模型的车辆再识别算法[J]. 计算机应用, 2018, 38(5): 1299-1303.
[3]	张永, 杨浩. 基于优化视觉词袋模型的图像分类方法[J]. 计算机应用, 2017, 37(8): 2244-2247.
[4]	张素兰, 张继福, 胡立华, 褚萌. 基于形式概念分析的图像场景语义标注模型[J]. 计算机应用, 2015, 35(4): 1093-1096.
[5]	朱为盛王鹏. 基于Hadoop云计算平台的大规模图像检索方案[J]. 计算机应用, 2014, 34(3): 695-699.
[6]	宋真颜永丰. 基于兴趣点综合特征的图像检索[J]. 计算机应用, 2012, 32(10): 2840-2842.
[7]	杨磊郭秀娟. 基于特征场景的快速图像匹配方法[J]. 计算机应用, 2011, 31(07): 1850-1852.
[8]	杨喜权代书. 基于知网的概念匹配细粒度化研究[J]. 计算机应用, 2008, 28(11): 2837-2839.
[9]	杨军邢琪诸昌钤彭强 . 散乱点数据的Bayesian曲面重建[J]. 计算机应用, 2007, 27(10): 2522-2524.