Distinguish computer generated and digital images: A CNN solution

The development of computer graphics has promoted the creation of computer generated images (CG) to a degree of unrivaled realism. It is of benefit to some industries like games and movies, which is aiming at making photo‐realistic images. At the same time, it brought attacks on many vision systems. An artist can modify one fake image using knowledge based on computer graphics to deceive most people, turning this into a very dangerous weapon. It is of great importance to differentiate a photo‐realistic computer generated image from a real photograph (PG). This problem can be modeled as a binary classification problem. Given one image, we just predict a label like “CG” or “PG” on it. To address this classification problem, we propose a method based on convolutional network through transfer learning. We choose VGG and ResNet as our base network structure and develop different models. Current state‐of‐the‐art approaches rely on hand‐crafted feature while we adopt a power convolutional network as an alternative and achieve the state‐of‐the‐art performance. In comparison, our method is end to end and more stable.

[1]  Ying Wang,et al.  On Discrimination between Photorealistic and Photographic Images , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[2]  Shih-Fu Chang,et al.  Physics-motivated features for distinguishing photographic images and computer graphics , 2005, ACM Multimedia.

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[7]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[8]  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).

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

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

[11]  Junichi Yamagishi,et al.  Distinguishing computer graphics from natural images using convolution neural networks , 2017, 2017 IEEE Workshop on Information Forensics and Security (WIFS).

[12]  Hany Farid,et al.  Detecting Photographic Composites of People , 2008, IWDW.

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

[14]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

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

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

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

[19]  Xiaogang Wang,et al.  Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[21]  Siwei Lyu,et al.  How realistic is photorealistic? , 2005, IEEE Transactions on Signal Processing.

[22]  Manuel Menezes de Oliveira Neto,et al.  Humans are easily fooled by digital images , 2017, Comput. Graph..

[23]  Hany Farid.  A 3-D Photo Forensic Analysis of the Lee Harvey Oswald Backyard Photo , 2010 .

[24]  David Zhang,et al.  Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[26]  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).

[27]  Gang Wang,et al.  Gated Siamese Convolutional Neural Network Architecture for Human Re-identification , 2016, ECCV.

[28]  Wei Zhang,et al.  Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning , 2018, Sensors.

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

[30]  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).

[31]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

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

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

[34]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

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

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

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

[38]  Mary J. Bravo,et al.  Image forensic analyses that elude the human visual system , 2010, Electronic Imaging.

[39]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[41]  Michael Jones,et al.  An improved deep learning architecture for person re-identification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[43]  Husrev T. Sencar,et al.  Source Camera Identification Based on Sensor Dust Characteristics , 2007 .

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