Volume 15, Issue 2 (9-2018)                   JSDP 2018, 15(2): 55-68 | Back to browse issues page


XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

ghanbari sorkhi A, Fateh M, Hassanpour H. Intelligent Identifications and Filtering of Unconventional Images Based on Deep Neural Networks. JSDP. 2018; 15 (2) :55-68
URL: http://jsdp.rcisp.ac.ir/article-1-590-en.html
shahrood university
Abstract:   (224 Views)

Currently vast improvement of internet access and significant growth of web based broadcasters have resulted in distribution and sharing of informative resources such as images worldwide. Although this kind of sharing may bring many advantages, there are certain risks such as access of kids to porn images which should not be neglected. In fact, access to these images can be a threat to the culture of any society where kids and adults are included. However, many of internet users are members of social websites including Facebook or Instagram and without an appropriate intelligent filtering system, presence of few unconventional images may result in total filtering of these websites causing unpleasant feeling of members. In this paper, an attempt was made to propose an approach for classification and intelligent filtering of unconventional images. One of the major issues on these occasions is the analysis of a large scale of data available in the websites which might be a very time consuming task. A deep neural network might be a good option to resolve this issue and provide a good accuracy in dealing with huge databases. In this research, a new architecture for identifying unconventional images is proposed. In the proposed approach, the new architecture is presented with a combination of AlexNet and LeNet architecture that uses convolutional, polling and fully-connected layers.
The activation function used in this architecture, is the Rectified Linear Unit (ReLU) function. The reason of using this activation function is the high speed of convergence in deep convolution networks and simplicity in implementation. The proposed architecture consists of several parts. The first two parts consist of convolutional layers, ReLUs and pooling. In this section, convolution is applied to the input image with different dimensions and filters. In the next section, the convolutional layer with ReLU is used without pooling. The next section, like the first two parts, includes convolutional layers, ReLU and pooling. Finally, the last three parts include the fully-connected layers with ReLU. The output of the last layer is the two classes, which specifies the degree of belonging of each input to the class of unconventional and conventional images. The results are tested on a large-scale dataset. These tests show that the proposed method is more accurate than the other methods recently developed for identifying unconventional images.
 

Full-Text [PDF 4496 kb]   (99 Downloads)    
Type of Study: Research | Subject: Paper
Received: 2016/10/8 | Accepted: 2017/03/5 | Published: 2018/09/16 | ePublished: 2018/09/16

References
1. [1] Richmond, R., Facebook's new way to combat child pornography. New York Times, 2011
2. [2] http://www.dailyinfographic.com/the-stats-on-internet-pornography-nfographic,accessed 2017/1/19.
3. [3] Malamuth, N.M., T. Addison, and M. Koss, Pornography and sexual aggression: Are there reliable effects and can we understand them? Annual review of sex research, 2000. 11(1): p. 26-91. [PMID]
4. [4] Malamuth, N.M., Criminal and noncriminal sexual aggressors. Annals of the New York Academy of Sciences, 2003. 989(1): p. 33-58. [DOI:10.1111/j.1749-6632.2003.tb07292.x] [PMID]
5. [5] Alexy, E.M., A.W. Burgess, and R.A. Prentky, Pornography use as a risk marker for an aggressive pattern ofbehavior among sexually reactive children and adolescents. Journal of the American Psychiatric Nurses Association, 2009. 14(6): p. 442-453 [DOI:10.1177/1078390308327137] [PMID]
6. [6] Carter, D.L., R.A. Prentky, R.A. Knight, P.L. Vanderveer, and R.J. Boucher, Use of pornography in the criminaland developmental histories of sexual offenders. Journal of Interpersonal Violence, 1987. 2(2): p. 196-211. [DOI:10.1177/088626087002002005]
7. [7] Lin, Y.-C., H.-W. Tseng, and C.-S. Fuh. Pornography detection using support vector machine. in 16th IPPR Conference on Computer Vision, Graphicsand Image Processing (CVGIP 2003). 2003.
8. [8] Zuo, H., W. Hu, and O. Wu. Patch-based skin color detection and its application to pornography image filtering. in Proceedings of the 19th international conference on World wide web. 2010. ACM.
9. [9] Largillier, T., G. Peyronnet, and S. Peyronnet, Efficient filtering of adult content using textual information. Murdock et al.[7], 2016: p. 14-17.
10. [10] Rowley, H.A., Y. Jing, and S. Baluja. Large scale image-based adult-content filtering. in VISAPP (1). 2006. Citeseer.
11. [11] Krizhevsky, A., I. Sutskever, and G.E. Hinton. Imagenet classification with deep convolutional neural networks. in Advances in neural information processing systems. 2012.
12. [12] Forsyth, D.A. and M.M. Fleck. Identifying nude pictures. in Applications of Computer Vision, 1996. WACV'96., Proceedings 3rd IEEE Workshop on. 1996. IEEE.
13. [13] Fleck, M.M., D.A. Forsyth, and C. Bregler. Finding naked people. in European Conference on Computer Vision. 1996. Springer. [PMCID]
14. [14] Hu, W., O. Wu, Z. Chen, Z. Fu, and S. Maybank, Recognition of pornographic web pages by classifying texts and images. IEEE transactions on pattern analysis and machine intelligence, 2007. 29(6): p. 1019-1034. [DOI:10.1109/TPAMI.2007.1133] [PMID]
15. [15] Zhuo, L., J. Zhang, Y. Zhao, and S. Zhao, Compressed domain based pornographic imagerecognition using multi-cost sensitive decision trees. Signal Processing, 2013. 93(8): p. 2126-2139. [DOI:10.1016/j.sigpro.2012.07.003]
16. [16] Wang, M. and X.-S. Hua, Active learning in multimedia annotation and retrieval: A survey. ACM Transactions on Intelligent Systems and Technology (TIST), 2011. 2(2): p. 10. [DOI:10.1145/1899412.1899414]
17. [17] Li, F.-f., S.-w. Luo, X.-y. Liu, and B.-j. Zou, Bag-of-visual-words model for artificial pornographic images recognition. Journal of Central South University, 2016. 23(6): p. 1383-1389. [DOI:10.1007/s11771-016-3190-1]
18. [18] Baeza-Yates, R. and B. Ribeiro-Neto, Modern information retrieval. Vol. 463. 1999: ACM press New York.
19. [19] Zhang, J., L. Sui, L. Zhuo, Z. Li, and Y. Yang, An approach of bag-of-words based on visual attention model for pornographic images recognition in compressed domain. Neurocomputing, 2013. 110: p. 145-152. [DOI:10.1016/j.neucom.2012.11.029]
20. [20] Wang, Y., L. Ning, and W. Gao, Detecting pornographic images with visual words. Transactions of Beijing Institute of Technology, 2008. 28(5): p. 410-13.
21. [21] Gao, Y., M. Wang, Z.-J. Zha, J. Shen, X. Li, and X. Wu, Visual-textual joint relevance learning for tag-based social image search. IEEE Transactions on Image Processing, 2013. 22(1): p. 363-376. [DOI:10.1109/TIP.2012.2202676] [PMID]
22. [22] Sae-Bae, N., X. Sun, H.T. Sencar, and N.D. Memon. Towards automatic detection of child pornography. in 2014 IEEE International Conference on Image Processing (ICIP). 2014. IEEE. [DOI:10.1109/ICIP.2014.7026079]
23. [23] Ulges, A. and A. Stahl. Automatic detection of child pornography using color visual words. in 2011 IEEE International Conference on Multimedia and Expo. 2011. IEEE. [DOI:10.1109/ICME.2011.6011977] [PMID]
24. [24] Sui, L., J. Zhang, L. Zhuo, and Y. Yang, Research on pornographic images recognition method based on visual words in a compressed domain. IET image processing, 2012. 6(1): p. 87-93. [DOI:10.1049/iet-ipr.2011.0005]
25. [25] Dong, K., L. Guo, and Q. Fu. An adult image detection algorithm based on Bag-of-Visual-Words and text information. in 2014 10th International Conference on Natural Computation (ICNC). 2014. IEEE.
26. [26] Lowe, D.G., Distinctiveimage features from scale-invariant keypoints. International journal of computer vision, 2004. 60(2): p. 91-110. [DOI:10.1023/B:VISI.0000029664.99615.94]
27. [27] Zheng, H., M. Daoudi, and B. Jedynak, Blocking adult images based on statistical skin detection. ELCVIA: electronic letters on computer vision and image analysis, 2004. 4(2): p. 001-14. [DOI:10.5565/rev/elcvia.78]
28. [28] Wang, M., X.-S. Hua, J. Tang, and R. Hong, Beyond distance measurement: constructing neighborhood similarity for video annotation. IEEE Transactions on Multimedia, 2009. 11(3): p. 465-476. [DOI:10.1109/TMM.2009.2012919]
29. [29] Wang, M., X.-S. Hua, R. Hong, J. Tang, G.-J. Qi, and Y. Song, Unified video annotation via multigraph learning. IEEE Transactions on Circuits and Systems for Video Technology, 2009. 19(5): p. 733-746. [DOI:10.1109/TCSVT.2009.2017400]
30. [30] Wang, M., X.-S. Hua, T. Mei, R. Hong, G. Qi, Y. Song, and L.-R. Dai, Semi-supervised kernel density estimation for video annotation. Computer Vision and Image Understanding, 2009. 113(3): p. 384-396. [DOI:10.1016/j.cviu.2008.08.003]
31. [31] Ries, C.X. and R. Lienhart, A survey on visual adult image recognition. Multimedia tools and applications, 2014. 69(3): p. 661-688. [DOI:10.1007/s11042-012-1132-y]
32. [32] Duan, L., G. Cui, W. Gao, and H. Zhang. Adult image detection method base-on skin color model and support vector machine. in Asian conference on computer vision. 2002.
33. [33] Yin, H., X. Huang, and Y. Wei, SVM-based pornographic images detection, in Software Engineering and Knowledge Engineering: Theory and Practice. 2012, Springer. p. 751-759. [DOI:10.1007/978-3-642-25349-2_100] [PMID] [PMCID]
34. [34] Zaidan, A., H.A. Karim, N. Ahmad, B. Zaidan, and M.M. Kiah, Robust Pornography Classification Solving the Image Size Variation Problem Based on Multi-Agent Learning. Journal of Circuits, Systems and Computers, 2015. 24(02): p. 1550023. [DOI:10.1142/S0218126615500231]
35. [35] Wu, O., H. Zuo, W. Hu, M. Zhu, and S. Li. Recognizing and filtering web images based on people's existence. in Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology-Volume 01. 2008. IEEE Computer Society.
36. [36] Li, D., N. Li, J. Wang, and T. Zhu, Pornographic images recognition based on spatial pyramid partition and multi-instance ensemble learning. Knowledge-Based Systems, 2015. 84: p. 214-223. [DOI:10.1016/j.knosys.2015.04.014]
37. [37] Zaidan, A.A., N.N. Ahmad, H.A. Karim, M. Larbani, B.B. Zaidan, and A. Sali, On the multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: An automated anti-pornography system. Neurocomputing, 2014. 131: p. 397-418. [DOI:10.1016/j.neucom.2013.10.003]
38. [38] Yin, H., X. Xu, and L. Ye. Big skin regions detection for adult image identification. in Digital Media and Digital Content Management (DMDCM), 2011 Workshop on. 2011. IEEE.
39. [39] Bosson, A., G.C. Cawley, Y. Chan, and R. Harvey. Non-retrieval: blocking pornographic images. in International Conference on Image and Video Retrieval. 2002. Springer. [DOI:10.1007/3-540-45479-9_6] [PMCID]
40. [40] Zhang, J., L. Sui, L. Zhuo, and Z. Li, Pornographic image region detection based on visual attention model in compressed domain. IET Image Processing, 2013. 7(4): p. 384-391. [DOI:10.1049/iet-ipr.2012.0381]
41. [41] Bozorgi, M., M.A. Maarof, and L.Z. Sam. Multi-classifier Scheme with Low-Level Visual Feature for Adult Image Classification. in International Conference on Software Engineering and Computer Systems. 2011. Springer. [PMCID]
42. [42] Kia, S.M., H. Rahmani, R. Mortezaei, M.E. Moghaddam, and A. Namazi, A Novel Scheme for Intelligent Recognition of Pornographic Images. arXiv preprint arXiv:1402.5792, 2014.
43. [43] Lienhart, R. and R. Hauke. Filtering adult image content with topic models. in 2009 IEEE International Conference on Multimedia and Expo. 2009. IEEE. [DOI:10.1109/ICME.2009.5202781]
44. [44] Islam, M., P. Watters, J. Yearwood, M. Hussain, and L.A. Swarna, Illicit Image Detection Using Erotic Pose Estimation Based on Kinematic Constraints, in Innovations and Advances in Computer, Information, Systems Sciences, and Engineering. 2013, Springer. p. 481-495.
45. [45] Bengio, Y., Learning deep architectures for AI. Foundations and trends® in Machine Learning, 2009. 2(1): p. 1-127. [DOI:10.1561/2200000006]
46. [46] Peter, Z.C., Building High-level Features Using Large Scale Unsupervised Learning.
47. [47] Fasel, B. Robust face analysis using convolutionalneural networks. in Pattern Recognition, 2002. Proceedings. 16th International Conference on. 2002. IEEE.
48. [48] Le Cun, B.B., J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, and L.D. Jackel. Handwritten digit recognition with a back-propagation network. in Advances in neural information processing systems. 1990. Citeseer.
49. [49] LeCun, Y. and Y. Bengio, Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 1995. 3361(10): p. 1995. [PMID]
50. [50] Fei-Fei, L. ImageNet: crowdsourcing, benchmarking & other cool things. in CMU VASC Seminar. 2010.
51. [51] Wang, J.Z., J. Li, G. Wiederhold, and O. Firschein, System for screening objectionable images. Computer Communications, 1998. 21(15): p. 1355-1360. [DOI:10.1016/S0140-3664(98)00203-5]
52. [52] Platzer, C., M. Stuetz, and M. Lindorfer. Skin sheriff: a machine learning solution for detecting explicit images. in Proceedings of the 2nd international workshop on Security and forensics in communication systems. 2014. ACM.
53. [53] Ahmadi, A., M. Fotouhi, and M. Khaleghi, Intelligent classification of web pages using contextual and visual features. Applied Soft Computing, 2011. 11(2): p. 1638-1647. [DOI:10.1016/j.asoc.2010.05.003]
54. [54] Zheng, Q.-F., W. Zeng, W.-Q. Wang, and W. Gao, Shape-based adult image detection. International Journal of Image and Graphics, 2006. 6(01): p. 115-124. [DOI:10.1142/S0219467806002082]
55. [55] Shih, J.-L., C.-H. Lee, and C.-S. Yang, An adult image identification system employing image retrieval technique. Pattern Recognition Letters, 2007. 28(16): p. 2367-2374. [DOI:10.1016/j.patrec.2007.08.002]

Add your comments about this article : Your username or Email:
CAPTCHA code

Send email to the article author


© 2015 All Rights Reserved | Signal and Data Processing