Skip to main content
SpringerLink
Log in

Deep Learning Neural Network for Unconventional Images Classification

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

The pornographic materials including videos and images are easily in reach for everyone, including under-age youths, allover Internet. It is also an aim for popular social network applications to contain no public pornographic materials. However, their frequent existence throughout all the Internet and huge amount of available images and videos there, make it impossible for manual monitoring to discriminate positive items (porn image or video) from benign images (non-porn image or video). Therefore, automatic detection techniques can be very useful here. But, the traditional machine learning models face many challenges. For example, they need to tune their many parameters, to select the suitable feature set, to select a suitable model. Therefore, this paper proposes an intelligent filtering system model based on a recent convolutional neural networks where it bypasses the aforementioned challenges. We show that the proposed model outperforms the recent machine learning based models. It also outperforms the state of the art deep learning based models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Allen A, Kannis-Dymand L, Katsikitis M (2017) Problematic internet pornography use: the role of craving, desire thinking, and metacognition. Addict Behav 70:65–71

    Google Scholar 

  2. https://www.dailyinfographic.com/the-stats-oninternet-pornography-nfographic, Accessed 21 Feb 2019

  3. Eyes (2018) Porn Stats: 250+ facts, quotes, and statistics about pornography use. Covenant Eyes pp 4–5

  4. Short M, Black L, Smith A, Wetterneck C, Wells D (2012) A review of internet pornography use research: methodology and content from the past 10 years. Cyberpsychol Behav Soc Netw 15(1):13–23

    Google Scholar 

  5. Amini S, Homayouni S, Safari A (2018) Object-based classification of hyperspectral data using Random Forest algorithm. Geo-spatial Inf Sci 21(2):127–138

    Google Scholar 

  6. Yu Y, Li M, Fu Y (2018) Forest type identification by random forest classification combined with SPOT and multitemporal SAR data. J For Res 29(5):1407–1414

    Google Scholar 

  7. Anthony S (2012), Just how big are porn sites? https://www.extremetech.com/computing/123929-just-how-big-are-porn-sites

  8. Zuo H, Hu W, Wu O (2010) Patch-based skin color detection and its application to pornography image filtering. In Proceedings of the 19th international conference on World Wide Web. ACM

  9. Largillier T, Peyronnet G, Peyronnet S (2016), Efficient filtering of adult content using textual information. Murdock et al. [7]. pp 14–17

  10. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In Proceedings of the advances in neural information processing systems, pp 1097–1105

  11. Yin H, Xu X, Ye L (2011) Big skin regions detection for adult image identification. In 2011 workshop on digit media and digital content management (DMDCM), pp 242–247

  12. Ries C, Lienhart R (2014) A survey on visual adult image recognition. Multimed Tools Appl 69(3):661–688

    Google Scholar 

  13. Avila S, Thome N, Cord M, Valle E, Araujo A (2013) Pooling in image representation: the visual codeword point of view. Comput Vision Image Underst 117(5):453–465

    Google Scholar 

  14. Dong KK, Li G, Fu Q (2014) An adult image detection algorithm based on Bag-of-Visual Words and text information. In Proceedings of the 10th international conference on natural computation (ICNC), pp 556–560

  15. Zhao ZC, Cai A (2010) Combining multiple SVM classifiers for adult image recognition. In Proceedings of the 2010 2nd IEEE international conference on network infrastructure and digital content, pp 149–153

  16. Deselaers T, Ferrari V (2010) Global and efficient self-similarity for object classification and detection. Proc IEEE Conf Comput Vis Pattern Recogn (CVPR) 2010:1633–1640

    Google Scholar 

  17. Guo ZH, Zhang L, Zhang D (2010) A completed modeling of local binary pattern operator for texture classification. IEEE Trans Image Process 19(6):1657–1663

    MathSciNet  MATH  Google Scholar 

  18. Zhuo L, Zhang J, Zhao Y, Zhao S (2013) Compressed domain based pornographic image recognition using multi-cost sensitive decision trees. Signal Process 93(8):2126–2139

    Google Scholar 

  19. Lowe DG (2004) Distinctive image features from scale-invariant key points. Int J Comput Vis 60(2):91–110

    Google Scholar 

  20. Li FF, Luo SW, Liu XY, Zou BJ (2016) Bag-of-visual-words model for artificial pornographic images recognition. J Cent South Univ 23(6):1383–1389

    Google Scholar 

  21. Zhang J, Sui L, Zhuo L, Li Z, Yang Y (2013) An approach of bag-of-words based on visual attention model for pornographic images recognition in compressed domain. Neurocomputing 110:145–152

    Google Scholar 

  22. Gao Y, Wang M, Zha Z-J, Shen J, Li X, Wu X (2013) Visual-textual joint relevance learning for tag-based social image search. IEEE Trans Image Process 220:363–376

    MathSciNet  MATH  Google Scholar 

  23. Sae-Bae N, Sun X, Sencar HT, Memon ND (2014) Towards automatic detection of child pornography. In 2014 IEEE international conference on image processing (ICIP). IEEE

  24. Zaidan A, Karim HA, Ahmad N, Zaidan B, Kiah MM (2015) Robust pornography classification solving the image size variation problem based on multi-agent learning. J Circuits Syst Comput 24(02):1550023

    Google Scholar 

  25. Zaidan AA, Ahmad NN, Larbani HAM, Zaidan BB, Sali A (2014) On the multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: an automated anti-pornography system. Neurocomputing 131:397–418

    Google Scholar 

  26. Li D, Li N, Wang J, Zhu T (2015) Pornographic images recognition based on spatial pyramid partition and multi-instance ensemble learning. Knowl-Based Syst 84:214–223

    Google Scholar 

  27. Zhang J, Sui L, Zhuo L, Li Z (2013) Pornographic image region detection based on visual attention model in compressed domain. IET Image Proc 7(4):384–391

    Google Scholar 

  28. Kia SM, Rahmani H, Mortezaei R, Moghaddam ME, Namazi A (2014) A novel scheme for intelligent recognition of pornographic images. http://arxiv.org/abs/1402.5792

  29. Yuan Y, Xiong Z, Wang Q (2019) VSSA-NET: vertical spatial sequence attention network for traffic sign detection. IEEE Trans Image Process 28(7):3423–3434

    MathSciNet  MATH  Google Scholar 

  30. Wang Q, Gao J, Yuan Y (2018) Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Trans Intell Transp Syst 19(1):230–241

    Google Scholar 

  31. Wang Q, Yuan Z, Du Q, Li X (2019) GETNET: a general end-to-end two-dimensional CNN framework for hyperspectral image change detection. CoRR abs/1905.01662

  32. Wang YH, Xin J, Tan X (2016) Pornographic image recognition by strongly-supervised deep multiple instance learning. Proc IEEE Int Conf Image Process 2016:4418–4422

    Google Scholar 

  33. Cheng F, Wang SL, Wang XZ, Liew AWC, Liu GS (2019) A global and local context integration DCNN for adult image classification. Pattern Recogn. https://doi.org/10.1016/j.patcog.2019.106983

    Article  Google Scholar 

  34. Moustafa M (2015) Applying deep learning to classify pornographic images and videos. In Proceedings of the Pacific-RIM symposium on image and video technology (PSIVT)

  35. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 1–9

  36. Ou XY, Ling H, Yu H, Li P, Zou F, Liu S (2017) Adult image and video recognition by a deep multicontext network and fine-to-coarse strategy. ACM Trans Intell Syst Technol (TIST) 8(5):68

    Google Scholar 

  37. Ren SQ, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In Proceedimgs of the advances in neural information processing systems, pp 91–99

  38. Wang XZ, Cheng F, Wang S, Sun H, Liu G, Zhou C (2018) Adult image classification by a local-context aware network. Proc IEEE Int Conf Image Process (ICIP) 2018:2989–2993

    Google Scholar 

  39. Sarafianos N, Giannakopoulos T, Nikou C, Kakadiaris IA (2018) Curriculum learning of visual attribute clusters for multi-task classification. Pattern Recogn 80:94–108

    Google Scholar 

  40. Zhang Z, Luo P, Loy CC, Tang X (2014) Facial landmark detection by deep multi-task learning. In Proceedings of the European conference on computer vision (ECCV), pp 94–108

  41. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: Single shot multibox detector. In Proceedings of the European conference on computer vision (ECCV), pp 21–37

  42. Xiang TZ, Xia GS, Bai X, Zhang L (2018) Image stitching by line-guided local warping with global similarity constraint. Pattern Recogn 77:113–125

    Google Scholar 

  43. Bengio Y (2009) Learning deep architectures for Al. Foundations and trends @. Mach Learn 20:1–127

    MATH  Google Scholar 

  44. Peter ZC Building high-level features using large scale unsupervised learning

  45. Fasel B (2002) Robust face analysis using convolutional neural networks. In Proceedings of the 16th international conference on pattern recognition. IEEE

  46. Jenghara MM, Ebrahimpour-Komleh H, Rezaie V, Nejatian S, Parvin H, Yusof SKS (2018) Imputing missing value through ensemble concept based on statistical measures. Knowl Inf Syst 56(1):123–139

    Google Scholar 

  47. Jamalinia H, Khalouei S, Rezaie V, Nejatian S, Bagheri-Fard K, Parvin H (2018) Diverse classifier ensemble creation based on heuristic dataset modification. J Appl Stat 45(7):1209–1226

    MathSciNet  Google Scholar 

  48. Hosseinpoor MJ, Parvin H, Nejatian S, Rezaie V (2019) Gene regulatory elements extraction in breast cancer by Hi-C data using a meta-heuristic method. Russ J Genet 55(9):1152–1164

    Google Scholar 

  49. Nejatian S, Parvin H, Faraji E (2018) Using sub-sampling and ensemble clustering techniques to improve performance of imbalanced classification. Neurocomputing 276:55–66

    Google Scholar 

  50. Mojarad M, Nejatian S, Parvin H, Mohammadpoor M (2019) A fuzzy clustering ensemble based on cluster clustering and iterative Fusion of base clusters. Appl Intell 49(7):2567–2581

    Google Scholar 

  51. Mojarad M, Parvin H, Nejatian S, Rezaie V (2019) Consensus function based on clusters clustering and iterative fusion of base clusters. Int J Uncertainty Fuzz Knowl-Based Syst 27(1):97–120

    Google Scholar 

  52. Zhou Z (2012) Ensemble methods: foundations and algorithms. CRC Press, Boca Raton

    Google Scholar 

  53. Nazari A, Dehghan A, Nejatian S, Rezaie V, Parvin H (2019) A comprehensive study of clustering ensemble weighting based on cluster quality and diversity. Pattern Anal Appl 22:133–145

    MathSciNet  Google Scholar 

  54. Bagherinia B, Minaei-Bidgoli M, Hossinzadeh H (2019) Parvin, Elite fuzzy clustering ensemble based on clustering diversity and quality measures. Appl Intell 49:1724–1747

    Google Scholar 

  55. Alizadeh H, Minaei-Bidgoli B, Parvin H (2011) A new criterion for clusters validation. In: Artificial intelligence applications and innovations (AIAI 2011), IFIP, Part I. Springer, Heidelberg pp 240–246

  56. Abbasi S, Nejatian S, Parvin H, Rezaie V, Bagherifard K (2019) Clustering ensemble selection considering quality and diversity. Artif Intell Rev 52:1311–1340

    Google Scholar 

  57. Rashidi S, Nejatian H, Parvin V (2019) Rezaie, diversity based cluster weighting in cluster ensemble: an information theory approach. Artif Intell Rev 52:1341–1368

    Google Scholar 

  58. Malamuth NM (2003) Criminal and noncriminal sexual aggressors. Ann N Y Acad Sci 989(1):33–58

    Google Scholar 

  59. 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

  60. T. Deselaers, L. Pimenidis, H. Ney, Bag-of-visual-words models for adult image classification and filtering, in: International Conference on Pattern Recognition (ICPR), 2008, pp. 1–4.

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

  62. Steel CM (2012) The Mask-SIFT cascading classifier for pornography detection. In world congress on internet security (WorldCIS), pp 139–142

  63. Zhuo L, Geng Z, Zhang J, Guangli X (2016) ORB feature based web pornographic image recognition. Neurocomputing 173:511–517

    Google Scholar 

  64. Nian T, Li Y, Wang M, Xu J (2016) Pornographic image detection utilizing deep convolutional neural networks. Neurocomputing 120:283–293

    Google Scholar 

  65. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. http://arxiv.org/abs/1409.1556

  66. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. CVPR 2016:770–778

    Google Scholar 

  67. Ahmadi A, Fotouhi M, Khaleghi M (2011) Intelligent classification of web pages using contextual and visual features. Appl Soft Comput 11(2):1638–1647

    Google Scholar 

  68. Zheng QF, Zeng W, Wang WQ, Gao W (2006) Shape-based adult image detection. Int J Image Graph 6(01):115–124

    Google Scholar 

  69. Shih JL, Lee CH, Yang CS (2007) An adult image identification system employing image retrieval technique. Pattern Recogn Lett 2806:2367–2374

    Google Scholar 

  70. Wilcoxon F (1945) Individual comparisons by ranking methods. Biometr Bull 1(6):80–83

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Technology, Hubei University of Police, Hubei, China

    Wei Xu

  2. Hubei Collaborative Innovation Center of Digital Forensics and Trusted Application, Wuhan, China

    Wei Xu

  3. Depparteman of Computer Science, Nourabad Mamasani Branch, Islamic Azad University, Fars, Mamasani, Iran

    Hamid Parvin & Hadi Izadparast

  4. Young Researchers and Elite Club, Nourabad Mamasani Branch, Islamic Azad University, Fars, Mamasani, Iran

    Hamid Parvin

Authors
  1. Wei Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hamid Parvin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hadi Izadparast
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wei Xu.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, W., Parvin, H. & Izadparast, H. Deep Learning Neural Network for Unconventional Images Classification. Neural Process Lett 52, 169–185 (2020). https://doi.org/10.1007/s11063-020-10238-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-020-10238-3

Keywords

Search

Navigation