Adult content classification through deep convolution neural network

Adult content filtering is one of the main challenge in Indonesia to prevent children from accessing the adult content. Conventional web blocking and filtering through domain name server filtering is not enough to prevent the adult content distribution. Mobile phones, tablet, and personal computer can distribute the adult content through the offline way. In this case, a more sophisticated and autonomous system is needed that can detect the adult content automatically. To leverage this problem, a deep neural network is used to build a model that is able to detect adult content automatically. In this experiments, our model is able to detect adult content with an accuracy of 75, 08% and 69, 02% during the validation and testing process, respectively.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Matthieu Cord,et al.  BOSSA: Extended bow formalism for image classification , 2011, 2011 18th IEEE International Conference on Image Processing.

[3]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[4]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[5]  Hermann Ney,et al.  Bag-of-visual-words models for adult image classification and filtering , 2008, 2008 19th International Conference on Pattern Recognition.

[6]  Adrian Ulges,et al.  Automatic detection of child pornography using color visual words , 2011, 2011 IEEE International Conference on Multimedia and Expo.

[7]  Li Zhuo,et al.  An approach of bag-of-words based on visual attention model for pornographic images recognition in compressed domain , 2013, Neurocomputing.

[8]  Chad M. S. Steel.  The Mask-SIFT cascading classifier for pornography detection , 2012, World Congress on Internet Security (WorldCIS-2012).

[9]  Matthieu Cord,et al.  Pooling in image representation: The visual codeword point of view , 2013, Comput. Vis. Image Underst..

[10]  Rodrigo C. Barros,et al.  Adult content detection in videos with convolutional and recurrent neural networks , 2018, Neurocomputing.

[11]  Vanessa Testoni,et al.  Pornography classification: The hidden clues in video space-time. , 2016, Forensic science international.

[12]  Arnaldo de Albuquerque Araújo,et al.  A bag-of-features approach based on Hue-SIFT descriptor for nude detection , 2009, 2009 17th European Signal Processing Conference.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.