Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks

Nicolas Rahmouni, Vincent Nozick, Junichi Yamagishi, Isao Echizen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This paper presents a deep-learning method for distinguishing computer generated graphics from real photographic images. The proposed method uses a Convolutional Neural Network (CNN) with a custom pooling layer to optimize current best-performing algorithms feature extraction scheme. Local estimates of class probabilities are computed and aggregated to predict the label of the whole picture. We evaluate our work on recent photo-realistic computer graphics and show that it outperforms state of the art methods for both local and full image classification.
Original languageEnglish
Title of host publication9th IEEE International Workshop on Information Forensics and Security (WIFS) 2017
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
VolumeRennes, France
ISBN (Electronic)978-1-5090-6769-5
ISBN (Print)978-1-5090-6770-1
DOIs
Publication statusPublished - 25 Jan 2018
Event9th IEEE International Workshop on Information Forensics and Security - , Hong Kong
Duration: 4 Dec 20177 Dec 2017
https://project.inria.fr/wifs2017/

Publication series

Name
PublisherIEEE
ISSN (Electronic)2157-4774

Conference

Conference9th IEEE International Workshop on Information Forensics and Security
Abbreviated titleWIFS 2017
Country/TerritoryHong Kong
Period4/12/177/12/17
Internet address

Fingerprint

Dive into the research topics of 'Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks'. Together they form a unique fingerprint.

Cite this