Identifying Photorealistic Computer Graphics using Convolutional Neural Networks

Cited 18 time in webofscience Cited 0 time in scopus
  • Hit : 697
  • Download : 0
As computer graphics technology advances, it is becoming increasingly difficult to determine whether a given picture was taken by camera or via computer graphics. In this work, we propose a method to using simple CNN structures to identify photorealistic computer graphics (PRCG) using convolutional neural networks (CNN). This network trained to identify the source of image patches. We showed the network without pooling layer showed 98.2% accuracy, which is 2.1% higher than the result of using conventional object-recognition network. Testing random patches from image, the accuracy of identifying image reached 98.5%. Furthermore, it is possible to detect the photograph-PRCG synthesized regions from the image.
Publisher
IEEE Signal Processing Society
Issue Date
2017-09-17
Language
English
Citation

24th IEEE International Conference on Image Processing (ICIP), pp.4093 - 4097

ISSN
1522-4880
DOI
10.1109/ICIP.2017.8297052
URI
http://hdl.handle.net/10203/227015
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 18 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0