[1]黄杰,史啸.一种基于人体裸露皮肤形状的不良图像过滤系统[J].东南大学学报(自然科学版),2014,44(6):1111-1115.[doi:10.3969/j.issn.1001-0505.2014.06.003]
 Huang Jie,Shi Xiao.Pornographic image filtering system based on shape of naked skin[J].Journal of Southeast University (Natural Science Edition),2014,44(6):1111-1115.[doi:10.3969/j.issn.1001-0505.2014.06.003]
点击复制

一种基于人体裸露皮肤形状的不良图像过滤系统()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
44
期数:
2014年第6期
页码:
1111-1115
栏目:
计算机科学与工程
出版日期:
2014-11-20

文章信息/Info

Title:
Pornographic image filtering system based on shape of naked skin
作者:
黄杰史啸
东南大学信息科学与工程学院, 南京 210096
Author(s):
Huang Jie Shi Xiao
School of Information Science and Engineering, Southeast University, Nanjing 210096, China
关键词:
Zernike矩 灰度共生矩阵 支持向量机 遗传算法
Keywords:
Zernike moments grayscale co-occurrence matrix support vector machine genetic algorithm
分类号:
TP393
DOI:
10.3969/j.issn.1001-0505.2014.06.003
摘要:
为了提高不良图像的过滤精度,从人体裸露皮肤的形状出发,设计了一种新型不良图像过滤系统.该系统由自适应肤色分割模块、特征提取模块和分类器模块组成.首先,基于人脸检测和Graph Cuts分割方法,提出了一种自适应肤色分割方法,对包含人体的图像进行肤色的精确分割;然后,利用Zernike矩和灰度共生矩阵构造出全局特征与局部特征相组合的特征向量;最后,采用遗传算法优化基于RBF核函数的支持向量机.实验结果表明,所提的过滤系统能够准确过滤裸露皮肤较多的不良图像,正样本查准率超过94%.
Abstract:
Based on the shape of naked skin in a figure image, a novel pornographic image filtering system is proposed to improve the filter precision of pornographic images. This system contains adaptive skin segment module, features extraction module and classifier module. First, based on face detection and Graph Cuts segment method, an adaptive skin segmentation method is proposed to accurately detect skin color pixels of the images containing human body. Then, the feature vector, which is the combination of the global feature and the local feature, is constructed by Zernike moments and grayscale co-occurrence matrix. Finally, the genetic algorithm is used to optimize the support vector machine based on RBF(radial basis function)kernel. The experimental results show that the proposed filtering system can accurately screen out the pornographic images with more naked skin and the precision ratio of positive samples exceeds 94%.

参考文献/References:

[1] Ganar A N, Gode C S, Jambhulkar S M. Enhancement of image retrieval by using colour, texture and shape features [C]//2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies. Nagpur, India, 2014:251-255.
[2] Shen X, Wei W, Qian Q. A pornographic image filtering model based on erotic part[C]//Proceedings of the 3rd International Congress on Image and Signal Processing. Yantai, China, 2010: 2473-2477.
[3] Choi B, Chung B, Ryou J. Adult image detection using Bayesian decision rule weighted by SVM probability [C]//Fourth International Conference on Computer Sciences and Convergence Information Technology. Seoul, South Korea, 2009:659-662.
[4] Zhang J, Sui L, Zhuo L, et al. Pornographic image region detection based on visual attention model in compressed domain[J]. IET Image Processing, 2013, 7(4): 384-391.
[5] Viola P, Jones M J. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2): 137-154.
[6] Lv W, Huang J. Skin detection method based on cascaded AdaBoost classifier[J]. Journal of Shanghai Jiaotong University: Science, 2012, 17(2): 197-202.
[7] Lee J-S, Kuo Y-M, Chung P-C, et al. Naked image detection based on adaptive and extensible skin color model[J]. Pattern Recognition, 2007, 40(8): 2261-2270.
[8] Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9):1124-1137.
[9] Li Y, Sun J, Tang C K, et al. Lazy snapping[J].ACM Transactions on Graphics, 2004, 23(3): 303-308.
[10] UCI. Breast cancer wisconsin(diagnostic)data set[EB/OL].(2013-12-20)[2014-02]. http://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+(Diagnostic).
[11] Huang C L, Wang C J. A GA-based feature selection and parameters optimization for support vector machines[J]. Expert Systems with Applications, 2006, 31(2): 231-240.

相似文献/References:

[1]陈自新,黄仁,张志胜,等.表面粗糙度视觉检测中环境光补偿新方法[J].东南大学学报(自然科学版),2009,39(1):136.[doi:10.3969/j.issn.1001-0505.2009.01.026]
 Chen Zixin,Huang Ren,Zhang Zhisheng,et al.New compensation method for surface roughness inspection by machine vision in different ambient light[J].Journal of Southeast University (Natural Science Edition),2009,39(6):136.[doi:10.3969/j.issn.1001-0505.2009.01.026]
[2]刘薇,周振宇,刘小征,等.一种基于层选择的弥散张量优化算法[J].东南大学学报(自然科学版),2013,43(1):30.[doi:10.3969/j.issn.1001-0505.2013.01.006]
 Liu Wei,Zhou Zhenyu,Liu Xiaozheng,et al.Slice-wise optimization algorithm for diffusion tensor estimation[J].Journal of Southeast University (Natural Science Edition),2013,43(6):30.[doi:10.3969/j.issn.1001-0505.2013.01.006]
[3]李海啸,姜璐,舒华忠.基于Zernike矩和BP神经网络的纹理分割[J].东南大学学报(自然科学版),2005,35(2):199.[doi:10.3969/j.issn.1001-0505.2005.02.008]
 Li Haixiao,Jiang Lu,Shu Huazhong.Texture segmentation based on Zernike moment and BP neural network[J].Journal of Southeast University (Natural Science Edition),2005,35(6):199.[doi:10.3969/j.issn.1001-0505.2005.02.008]
[4]江克,陈北京,张辉,等.完备的Zernike矩不变量集的构造及应用[J].东南大学学报(自然科学版),2011,41(1):58.[doi:10.3969/j.issn.1001-0505.2011.01.012]
 Jiang Ke,Chen Beijing,Zhang Hui,et al.Construction of complete set of Zernike moment invariants and its application[J].Journal of Southeast University (Natural Science Edition),2011,41(6):58.[doi:10.3969/j.issn.1001-0505.2011.01.012]
[5]郭骁,杨冠羽,王征,等.基于Zernike矩和水平集的超声图像分割[J].东南大学学报(自然科学版),2015,45(2):247.[doi:10.3969/j.issn.1001-0505.2015.02.009]
 Guo Xiao,Yang Guanyu,Wang Zheng,et al.Ultrasound image segmentation based on Zernike moment and level set[J].Journal of Southeast University (Natural Science Edition),2015,45(6):247.[doi:10.3969/j.issn.1001-0505.2015.02.009]

备注/Memo

备注/Memo:
收稿日期: 2014-02-20.
作者简介: 黄杰(1970—),男,教授,博士生导师,jhuang@seu.edu.cn.
基金项目: 国家高技术研究发展计划(863计划)资助项目(2013AA014001).
引用本文: 黄杰,史啸.一种基于人体裸露皮肤形状的不良图像过滤系统[J].东南大学学报:自然科学版,2014,44(6):1111-1115. [doi:10.3969/j.issn.1001-0505.2014.06.003]
更新日期/Last Update: 2014-11-20