Detecting Computer Generated Images with Deep Convolutional Neural Networks

Computer graphics techniques for image generation are living an era where, day after day, the quality of produced content is impressing even the more skeptical viewer. Although it is a great advance for industries like games and movies, it can become a real problem when the application of such techniques is applied for the production of fake images. In this paper we propose a new approach for computer generated images detection using a deep convolutional neural network model based on ResNet-50 and transfer learning concepts. Unlike the state-of-the-art approaches, the proposed method is able to classify images between computer generated or photo generated directly from the raw image data with no need for any pre-processing or hand-crafted feature extraction whatsoever. Experiments on a public dataset comprising 9700 images show an accuracy higher than 94%, which is comparable to the literature reported results, without the drawback of laborious and manual step of specialized features extraction and selection.

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

[2]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

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

[4]  Wang-Q Lim,et al.  Compactly supported shearlets are optimally sparse , 2010, J. Approx. Theory.

[5]  Matti Pietikäinen,et al.  A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification , 2001, ICAPR.

[6]  Anderson Rocha,et al.  Computer generated images vs. digital photographs: A synergetic feature and classifier combination approach , 2013, J. Vis. Commun. Image Represent..

[7]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[8]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[9]  Hany Farid,et al.  Assessing and Improving the Identification of Computer-Generated Portraits , 2016, TAP.

[10]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[11]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Giulia Boato,et al.  Physiologically-based detection of computer generated faces in video , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[14]  Larry S. Davis,et al.  A novel feature descriptor based on the shearlet transform , 2011, 2011 18th IEEE International Conference on Image Processing.

[15]  Shih-Fu Chang,et al.  Identifying and prefiltering images , 2009, IEEE Signal Process. Mag..

[16]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[17]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[18]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[19]  Tao Zhang,et al.  Identifying photorealistic computer graphics using second-order difference statistics , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[20]  Mary J. Bravo,et al.  Perceptual discrimination of computer generated and photographic faces , 2012, Digit. Investig..

[21]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[22]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Siwei Lyu,et al.  How realistic is photorealistic , 2005 .

[24]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[25]  L. Liebovitch,et al.  A fast algorithm to determine fractal dimensions by box counting , 1989 .

[26]  H. Farid.  Creating and Detecting Doctored and Virtual Images: Implications to The Child Pornography Prevention Act , 2004 .

[27]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[28]  Francesco G. B. De Natale,et al.  Identify computer generated characters by analysing facial expressions variation , 2012, 2012 IEEE International Workshop on Information Forensics and Security (WIFS).

[29]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[31]  E. Candès,et al.  Curvelets: A Surprisingly Effective Nonadaptive Representation for Objects with Edges , 2000 .

[32]  Minh N. Do,et al.  Contourlets: a directional multiresolution image representation , 2002, Proceedings. International Conference on Image Processing.

[33]  H. P. Chen,et al.  Detecting computer generated images based on local ternary count , 2016, Pattern Recognition and Image Analysis.

[34]  Francesco G. B. De Natale,et al.  Discrimination between computer generated and natural human faces based on asymmetry information , 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

[35]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[36]  Alin C. Popescu,et al.  Exposing digital forgeries in color filter array interpolated images , 2005, IEEE Transactions on Signal Processing.