Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks

Nicolas Rahmouni; Vincent Nozick; Junichi Yamagishi; Isao Echizen

Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks

Nicolas Rahmouni ¹ Vincent Nozick ² Junichi Yamagishi ³ Isao Echizen ³

2 JFLI - Japanese French Laboratory for Informatics

3 NII - National Institute of Informatics

Abstract : 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.

Document type :

Conference papers

Domain :

Computer Science [cs] / Computer Vision and Pattern Recognition [cs.CV]

Computer Science [cs] / Image Processing [eess.IV]

Complete list of metadatas

Cited literature [29 references] Display Hide Download

https://hal-upec-upem.archives-ouvertes.fr/hal-01664590
Contributor : Vincent Nozick <>
Submitted on : Friday, December 15, 2017 - 8:06:33 AM
Last modification on : Friday, May 24, 2019 - 4:12:31 PM

without_IEEE_logo.pdf

Files produced by the author(s)

Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks

File

Identifiers

Collections

Citation

Export

Metrics

280

540

Contact

Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks

File

Identifiers

Collections

Citation

Export

Share

Metrics

280

540

Contact