基于人体关键部位的不良图像过滤

doi:10.3969/j.issn.0255-8297.2014.04.012

应用科学学报 ›› 2014, Vol. 32 ›› Issue (4): 416-422.doi: 10.3969/j.issn.0255-8297.2014.04.012

基于人体关键部位的不良图像过滤

黄杰，倪鹏宇

东南大学信息科学与工程学院，南京210096

收稿日期:2013-01-07 修回日期:2014-02-20 出版日期:2014-07-31 发布日期:2014-02-20
作者简介:黄杰，教授，博导，研究方向：网络信息安全、物联网安全，E-mail：jhuang@seu.edu.cn
基金资助:
国家“863”高技术研究发展计划基金(No.2013AA014001)资助

Pornographic-Image Filtering Based on Body Parts

HUANG Jie, NI Peng-yu

School of Information Science and Engineering, Southeast University, Nanjing 210096, China

Received:2013-01-07 Revised:2014-02-20 Online:2014-07-31 Published:2014-02-20

摘要/Abstract

摘要： 肤色过滤不良图像的方法对于皮肤裸露较多但不含关键部位或类肤色区域较多的图像容易产生误检，为此设计了一种基于人体关键部位的不良图像过滤系统. 首先提取人体关键部位灰度分布的Haar-like特征，采用Adaboost学习算法训练得到人体关键部位分类器；然后通过此分类器得到人体关键部位候选区域，提取其梯度
直方图特征、基于灰度共生矩阵的纹理特征和基于颜色矩的颜色特征，使用支持向量机(support vector machine,SVM)进行训练；最后将训练得到的SVM分类器二次过滤人体关键部位，以提高系统整体的精度. 实验结果表明，该系统能准确地检测出人体关键部位，有效地降低不良图像的误检率.

关键词: Haar-like特征, Adaboost学习算法, 梯度直方图, 灰度共生矩阵, 颜色矩

Abstract: Non-pornographic images containing large naked skin or skin-like areas may be detected as pornographic using ordinary pornographic image-filtering method that heavily depend on skin detection. We design a different pornographic image-filtering system based on body parts. The system extracts Haar-like features describing local grayscale distribution of the body parts, and uses these features to train and obtain a classifier for body parts using the Adaboost learning algorithm. The candidate body part areas can be obtained with the classifier. To further improve the system performance, we extract histogram of oriented gradient features,textual features based on gray level co-occurrence matrix, and color moment features of the candidates. These
features are then used to train an support vector machine (SVM) classifier. Experiments show that the system can precisely detect key body parts in images, and therefore can effectively reduce false detection rate against non-pornographic images.

Key words: Haar-like feature, Adaboost learning algorithm, histogram of oriented gradient, gray level cooccurrence matrix, color moment

中图分类号:

TN957.52

黄杰，倪鹏宇. 基于人体关键部位的不良图像过滤[J]. 应用科学学报, 2014, 32(4): 416-422.

HUANG Jie, NI Peng-yu. Pornographic-Image Filtering Based on Body Parts[J]. Journal of Applied Sciences, 2014, 32(4): 416-422.

参考文献

[1] HU W, WU O, CHEN A, Fu Z, MAYBANK S. Recognition of pornographic web pages by classifying texts and images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(6):1019- 1034.

[2] LEE J-S, KUO Y-M, CHUNG P-C, CHEN E-L. Naked image detection based on adaptive and extensible skin color model[J]. Pattern Recognition, 2007, 40(8): 2261-2270.

[3] YIN H, HUANG X, WEI Y. SVM-based pornographic images detection[J]. Software Engineering and Knowledge Engineering, 2012, Vol.2, AISC 115:751-759.

[4] SHARMA J, PATHAK V K. Automatic pornographic detection in web pages based on images and text data using support vector machine[C]// Proceedings of the International Conference on SocProcS, 2011, AISC 131:473-483.

[5] LV L-T, ZHAO C-X, LV H, SHANG J, YANG Y-X, WANG J-F. Pornographic images detection using high-level semantic features[C]// 2011 Seventh International Conference on Natural Computation, 2011:1015-1018.

[6] FUANGKHON P, TANPRASERT T. Nipple detection for obscene pictures[C]// Proceedings of the 5th International Conference On Signal, Speech and Image Processing, Greece, August 2005:315-320.

[7] SHEN X, WEI W, QIAN Q. The filtering of internet images based on detecting erotogenic-part[C]//Third International Conference on Natural Computation, ICNC 2007, v 2:732-736.

[8] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]// Computer Vision and Pattern Recognition, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001,Vol.1: I-511- I-518.

[9] LIENHART R, MAYDT J. An extended set of Haar-like features for rapid object detection[C]//Proceedings of IEEE Conference on Image Processing,2002:900-903.

[10] HARALICK R M, SHANMUGAM K, DINSTEIN I. Textual features for image classification[J]. IEEE Transaction on System, Man, and Cybernetics, 1973, 3(6):610-621.

[11] STRICKER M A, ORENGO M. Similarity of color images[C]//Proceedings of SPIE: Storage and Retrieval for Image and Video Databases,1995, volume 2420:381-392.

[12] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005, 1(2):886-893.

[13] VIOLA P, JONES M J. Robust real-time face detection [J]. International Journal of Computer Vision, 2004, 57(2):137-154.

[14] VAPNIK V. The nature of statistical learning theory. New York: Springer-Verlag,1995.

[15] NOR N, HARUN S, KASSIM A. Radial basis function modeling of hourly streamflow hydrograph[J]. Journal of Hydrologic Engineering, 2007,12(1):113-123.

[16] YANG Z-R. A model radial basis function neural network for discriminant analysis[J]. IEEE Transactions on Neural Networks, 2006, 17(3):604-612.

[17] KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection[J]. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, 1995:1137-1143.

基于人体关键部位的不良图像过滤

Pornographic-Image Filtering Based on Body Parts

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	卢才武, 齐凡, 阮顺领. 基于深度图像分析的细粒度矿石分级测定方法[J]. 应用科学学报, 2019, 37(4): 490-500.
[2]	董伟, 王建军. 改进的卷积神经网络用于对比度增强取证[J]. 应用科学学报, 2017, 35(6): 745-753.
[3]	方志坚, 傅仰耿, 陈建华. 纹理图像分类的置信规则库推理方法[J]. 应用科学学报, 2017, 35(5): 545-558.
[4]	付仲良，张文元，孟庆祥. 灰度和纹理特征组合的SAR影像SVM分类[J]. 应用科学学报, 2012, 30(5): 498-504.