Advertisement

Application of Image Classification for Fine-Grained Nudity Detection

  • Cristian IonEmail author
  • Cristian Minea
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11844)

Abstract

Many online social platforms need to use an image content filtering solution to detect nudity automatically. Existing solutions only focus on binary classification models to detect explicit nudity or pornography, which is not enough to distinguish between a great number of various racy outfits that people wear (swimsuit, summer outfit, etc.) that might be considered inappropriate according to user’s own preferences. This paper addresses the problem by proposing a robust technology which detects fine-grained human body parts (chest, back, abdomen, etc.) and assigns a level of nudity for each part using a multi-label image classification model.

Since existing datasets were not sufficient for the given problem, we created a new dataset with a total of 37.872 images and 4.879.517 annotated labels that describe human body parts and nudity level (6 labels for each body part).

We fine-tuned multiple state-of-the-art convolutional neural network models (VGG, ResNet, MobileNet) on our dataset for multi-label image classification. Our solution has a total accuracy of 98.1% on the test dataset and a low false positive rate of 0.8%.

Keywords

Dataset Deep learning Image classification Nudity Pornography 

References

  1. 1.
    Belém, R.J.S., Cavalcanti, J.M.B., de Moura, E.S., Nascimento, M.A.: Snif: a simple nude image finder. In: LA-WEB, pp. 252–258. IEEE Computer Society (2005). http://dblp.uni-trier.de/db/conf/la-web/la-web2005.html#BelemCMN05
  2. 2.
    Canny, J.F.: A computational approach to edge detection PAMI-8. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679–698 (1986) CrossRefGoogle Scholar
  3. 3.
    Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.: Detect what you can: detecting and representing objects using holistic models and body parts. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)Google Scholar
  4. 4.
    Fang, H., Lu, G., Fang, X., Xie, J., Tai, Y., Lu, C.: Weakly and semi supervised human body part parsing via pose-guided knowledge transfer. CoRR abs/1805.04310 (2018), http://arxiv.org/abs/1805.04310
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016.  https://doi.org/10.1109/CVPR.2016.90
  6. 6.
    Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation (2000). IEEE Trans. Pattern Anal. Mach. Intell. 24, 881–892 (2002)CrossRefGoogle Scholar
  7. 7.
    Karavarsamis, S., Pitas, I., Ntarmos, N.: Recognizing pornographic images. In: Li, C., Dittmann, J., Katzenbeisser, S., Craver, S. (eds.) Multimedia and Security Workshop, MM&Sec 2012, Coventry, UK, 6–7 September 2012, pp. 105–108. ACM (2012).  https://doi.org/10.1145/2361407.2361425
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017).  https://doi.org/10.1145/3065386CrossRefGoogle Scholar
  9. 9.
    LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989).  https://doi.org/10.1162/neco.1989.1.4.541CrossRefGoogle Scholar
  10. 10.
    Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. CoRR abs/1801.04381 (2018), http://arxiv.org/abs/1801.04381
  11. 11.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.BitdefenderBucharestRomania

Personalised recommendations