A survey of artificial intelligence strategies for automatic detection of sexually explicit videos

Abstract

Digital forensics and analysis have emerged as a discipline to fight against cyber and computer-assisted crime. In particular, taking into account the increasing of unconstrained pornographic content over Internet and the spreading cases of Child Sex Abuse material distribution, there is a growing need of efficient computational tools to automatically detect or/and block pornographic videos. The primary objective of this study is to review the different strategies available in the literature for pornography detection in videos and identify research gaps. This survey shows that deep learning based techniques detect videos with sexually explicit content more accurately compared with other conventional detection strategies. The accuracy of the strategies reported in this work, is found to be dependent on features extraction techniques, architecture, and learning algorithms. Finally, further research areas in pornographic video detection are outlined.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Ap-Apid R (2005) An algorithm for nudity detection. In: Proceedings of the 5th philippine computing science congress, pp 201–205

  2. 2.

    Avila S, Thome N, Cord M, Valle E, AraúJo AD (2013) Pooling in image representation: The visual codeword point of view. Comp Vision Image Underst 117(5):453–465

    Article  Google Scholar 

  3. 3.

    Avila S, Thome N, Cord M, Valle E, Araújo AA (2011) Bossa: Extended bow formalism for image classification. In: 2011 18th IEEE international conference on image processing. IEEE, pp 2909–2912

  4. 4.

    Behrad A et al (2012) Content-based obscene video recognition by combining 3D spatiotemporal and motion-based features. EURASIP J Image Video Process 2012(1):23

    Article  Google Scholar 

  5. 5.

    Caetano C, Avila S, Guimaraes S et al (2014) Pornography detection using bossanova video descriptor. In: Proceedings of 22nd european signal processing conference. IEEE, pp 1681–1685

  6. 6.

    Caetano C, Avila S, Schwartz WR (2016) A mid-level video representation based on binary descriptors: A case study for pornography detection. Neurocomputing 213:102–114

    Article  Google Scholar 

  7. 7.

    Carlsson A, Eriksson A, Isik M (2008) Automatic detection of images containing nudity. Master Thesis in intelligent systems design

  8. 8.

    Castro Polastro M, da Silva Eleuterio PM (2012) A statistical approach for identifying videos of child pornography at crime scenes. In: Proceedings of the Seventh International Conference on Availability, Reliability and Security. IEEE, pp 604–612

  9. 9.

    Deselaers T, Pimenidis L, Ney H (2008) Bag-of-visual-words models for adult image classification and filtering. In: Proceedings of 19th international conference on pattern recognition. IEEE, pp 1–4

  10. 10.

    Endeshaw T, Garcia J, Jakobsson A (2008) Classification of indecent videos by low complexity repetitive motion detection. In: Proceedings of 37th IEEE applied imagery pattern recognition workshop. IEEE, pp 1–7

  11. 11.

    Fleck MM, Forsyth DA, Bregler C (1996) Finding naked people. In: Proceedings of european conference on computer vision. Springer, pp 593–602

  12. 12.

    Gangwar A, Fidalgo E, Alegre E, González-Castro V (2017) Pornography and child sexual abuse detection in image and video: a comparative evaluation. In: IET Conference proceedings, pp 37–42. IET Digital Library. https://digital-library.theiet.org/content/conferences/10.1049/ic.2017.0046

  13. 13.

    Garcia MB et al (2018) A Pornographic Image and Video Filtering Application Using Optimized Nudity Recognition and Detection Algorithm. In: Proceedings of 10th international conference on humanoid, nanotechnology, information technology, communication and control, environment and management (HNICEM). IEEE, pp 1–5

  14. 14.

    He K et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  15. 15.

    Hyperdyne software (2019) Snitch plus. www.hyperdynesoftware.com

  16. 16.

    Jansohn C, Ulges A, Breuel TM (2009) Detecting pornographic video content by combining image features with motion information. In: Proceedings of the 17th ACM international conference on multimedia. ACM, pp 601–604

  17. 17.

    Jones MJ, Rehg JM (2002) Statistical color models with application to skin detection. Int J Comp Vision 46(1):81–96

    Article  Google Scholar 

  18. 18.

    Jung S, Youn J, Sull S (2014) A real-time system for detecting indecent videos based on spatiotemporal patterns. IEEE Trans Consum Electron 60(4):696–701

    Article  Google Scholar 

  19. 19.

    Kakumanu P, Makrogiannis S, Bourbakis N (2007) A survey of skin-color modeling and detection methods. Pattern Recog 40(3):1106–1122

    Article  Google Scholar 

  20. 20.

    Kim CY, Kwon OJ, Kim WG, Choi SR (2008) Automatic system for filtering obscene video. In: Proceedings of 10th international conference on advanced communication technology, vol 2. IEEE, pp 1435–1438

  21. 21.

    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105

    Google Scholar 

  22. 22.

    Laptev I (2005) On space-time interest points. Int J Comp Vision 64(2-3):107–123

    Article  Google Scholar 

  23. 23.

    Lee H, Lee S, Nam T (2006) Implementation of high performance objectionable video classification system. In: Proceedings of 8th international conference advanced communication technology, vol 2. IEEE, pp 959–961

  24. 24.

    Lillie O (2017) PHP video. https://github.com/buggedcom/phpvideotoolkit-v2

  25. 25.

    Liu Y et al (2020) Analyzing periodicity and saliency for adult video detection. Multimed Tools Appl 79(7):4729–4745

    Article  Google Scholar 

  26. 26.

    Lopes APB et al (2009) A bag-of-features approach based on hue-sift descriptor for nude detection. In: Proceedings of the 17th european signal processing conference. IEEE, pp 1552–1556

  27. 27.

    Lopes APB et al, Peixoto AN (2009) Nude detection in video using bag-of-visual-features. In: Proceedings of XXII brazilian symposium on computer graphics and image processing. IEEE, pp 224–231

  28. 28.

    Moreira D et al (2016) Pornography classification: The hidden clues in video space–time. Forensic Sci Int 268:46–61

    Article  Google Scholar 

  29. 29.

    Moustafa M (2015) Applying deep learning to classify pornographic images and videos. arXiv:1511.08899

  30. 30.

    Nian F et al (2016) Pornographic image detection utilizing deep convolutional neural networks. Neurocomputing 210:283–293

    Article  Google Scholar 

  31. 31.

    Ost S (2002) Children at risk: Legal and societal perceptions of the potential threat that the possession of child pornography poses to society. J Law Soc 29 (3):436–460

    Article  Google Scholar 

  32. 32.

    Papadamou K et al (2020) Disturbed YouTube for kids: Characterizing and detecting inappropriate videos targeting young children. In: Proceedings of the international AAAI conference on web and social media, vol 14, pp 522–533

  33. 33.

    Perez M et al (2017) Video pornography detection through deep learning techniques and motion information. Neurocomputing 230:279–293

    Article  Google Scholar 

  34. 34.

    Platzer C, Stuetz M, Lindorfer M (2014) Skin sheriff: a machine learning solution for detecting explicit images. In: Proceedings of the 2nd international workshop on security and forensics in communication systems. ACM, pp 45–56

  35. 35.

    Polastro MdC, da Silva Eleuterio PM (2010) Nudetective: A forensic tool to help combat child pornography through automatic nudity detection. In: Proceedings of workshop on database and expert systems applications. IEEE, pp 349–353

  36. 36.

    Rea N et al (2006) Multimodal periodicity analysis for illicit content detection in videos. In: Proceedings of the 3rd european conference on visual media production (CVMP 2006)-Part of the 2nd multimedia conference 2006. IET, pp 106–114

  37. 37.

    Silva Eleuterio PM da, Mateus de Castro P, Police BF (2012) An adaptive sampling strategy for automatic detection of child pornographic videos. In: Proceedings of the seventh international conference on forensic computer science, Brasilia, DF, Brazil, pp 12–19

  38. 38.

    Silva MV da, Marana AN (2018) Spatiotemporal CNNs for pornography detection in videos. In: Proceedings of Iberoamerican congress on pattern recognition. Springer, pp 547–555

  39. 39.

    Singh S et al (2019) KidsGUARD: fine grained approach for child unsafe video representation and detection. In: Proceedings of the 34th ACM/SIGAPP symposium on applied computing. ACM, pp 2104–2111

  40. 40.

    Song KH, Kim YS (2018) Pornographic video detection scheme using multimodal features. J Eng Appl Sci 13(5):1174–1182

    Google Scholar 

  41. 41.

    Souza F et al (2012) An evaluation on color invariant based local spatiotemporal features for action recognition. In: IEEE SIBGRAPI

  42. 42.

    Szegedy C et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  43. 43.

    TapTap software (2019) Media detective. www.mediadetective.com

  44. 44.

    Tran D, Bourdev L et al (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4489–4497

  45. 45.

    Tran D, Wang H et al (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6450–6459

  46. 46.

    Ulges A, Schulze C et al (2012) Pornography detection in video benefits (a lot) from a multi-modal approach. In: Proceedings of the 2012 ACM international workshop on audio and multimedia methods for large-scale video analysis. ACM, pp 21–26

  47. 47.

    Ulges A, Stahl A (2011) Automatic detection of child pornography using color visual words. In: Proceedings of IEEE international conference on multimedia and expo. IEEE, pp 1–6

  48. 48.

    Valle E et al (2011) Content-based filtering for video sharing social networks. arXiv:1101.2427

  49. 49.

    Vitorino P et al (2018) Leveraging deep neural networks to fight child pornography in the age of social media. J Vis Commun Image Represent 50:303–313

    Article  Google Scholar 

  50. 50.

    Wang Y, Jin X, Tan X (2016) Pornographic image recognition by strongly-supervised deep multiple instance learning. In: Proceedings of the IEEE international conference on image processing (ICIP). IEEE, pp 4418–4422

  51. 51.

    Wang H, Schmid C (2013) Action recognition with improved trajectories. In: Proceedings of the IEEE international conference on computer vision, pp 3551–3558

  52. 52.

    Wang JZ et al (1998) System for screening objectionable images. Comput Compact 21(15):1355–1360

    Article  Google Scholar 

  53. 53.

    Wang D et al (2005) Identification and annotation of erotic film based on content analysis. In: Proceedings of IV electronic imaging and multimedia technology. International Society for Optics and Photonics, vol 56, pp 88–95

  54. 54.

    Warner K (2010) Sentencing for child pornography. Aust Law J 84 (6):384–395

    Google Scholar 

  55. 55.

    Wehrmann J et al (2018) Adult content detection in videos with convolutional and recurrent neural networks. Neurocomputing 272:432–438

    Article  Google Scholar 

  56. 56.

    Zhang J et al (2013) An approach of bag-of-words based on visual attention model for pornographic images recognition in compressed domain. Neurocomputing 110:145–152

    Article  Google Scholar 

  57. 57.

    Zhiyi Q et al (2009) A method for reciprocating motion detection in porn video based on motion features. In: Proceedings of 2nd IEEE international conference on broadband network & multimedia technology. IEEE, pp 183–187

  58. 58.

    Zhu M-L (2000) Video stream segmentation method based on video page. J Comput Aided Desi Comput Graph 12(8):585–589

    Google Scholar 

  59. 59.

    Zuo H et al (2008) Recognition of blue movies by fusion of audio and video. In: Proceedings of IEEE international conference on multimedia and expo. IEEE, pp 37–40

Download references

Acknowledgements

This project has received funding from the European Unionâs Horizon 2020 research and innovation programme under grant agreement No 700326. Website: http://ramses2020.eu

Author information

Affiliations

Authors

Corresponding author

Correspondence to Jenny Cifuentes.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cifuentes, J., Sandoval Orozco, A.L. & García Villalba, L.J. A survey of artificial intelligence strategies for automatic detection of sexually explicit videos. Multimed Tools Appl (2021). https://doi.org/10.1007/s11042-021-10628-2

Download citation

Keywords

  • Sexually explicit content detection
  • Video classification
  • Digital forensics
  • Deep learning
  • Motion features
  • Visual information analysis