Recaptured Images Dataset

Content and Format

6 different brands of camera were used to capture 2000 natural images and 2700 finely recaptured images. The resolutions range from 2272 by 1704 to 4256 by 2832. The total download size of this dataset is ~17GB which consist mainly of JPG images and some BMP images.

The 2000 natural images were captured using 5 different brands camera (Canon, Casio, Lumix, Nikon, and Sony) and are categorise as follows:
zCanon10D1zCanon10D2zCanon400D1
zCanon400D2zCanonIxusIndoorzCanonIxusOutdoor
zCasioIndoorzCasioOutdoorzLumixD1Indoor
zLumixD1OutdoorzNikonD70D1zNikonD70D2
zNikonS210zNikonS210D2zSonyAlpha
zSonyIndoorzSonyOutdoor

The 2700 recaptured images are recaptured from: and categorised as: The file structure of the recaptured images are:
CanonAcerMjuAcerOlymAcer
 Download Download Download
 OurPhoto OurPhoto OurPhoto
 Tampered Tampered Tampered
CanonNECMjuNECOlymNEC
 Download Download Download
 OurPhoto OurPhoto OurPhoto
 Tampered Tampered Tampered
CanonPhilipsMjuPhilipsOlymPhilips
 Download Download Download
 OurPhoto OurPhoto OurPhoto
 Tampered Tampered Tampered

 
Two pairs of Training Samples of
Nature and Recaptured Images
  Samples of 50 Images Used in
Human Recaptured Image Identification Survey

Usage for Academic Reseach

The image database is released only for academic researches. Any researcher from educational institute is allowed to use freely for academic purpose. Redistribution and modification in any way or form are considered illegal. Images in this database are only allowed for demonstration in academic publications and presentations.

If interested, researchers can download the Release Agreement and send it back to us (the deatails are in the form). We will then send you the ID and password to download the dataset.


Related Publications

All publications using the ROSE Recaptured Image Dataset should include the following acknowledgement: “(Portions of) the research in this paper used the ROSE Recaptured Image Dataset made available by the ROSE Lab at the Nanyang Technological University, Singapore.”

Furthermore, these publications should cite the following references:
H. Cao and A.C. Kot, "Identification of Recaptured Photographs on LCD Screens", in Proc. of ICASSP, pp. 1790-1793, 2010
H. Cao, "Statistical Image Source Model Identification and Forgery Detection", PhD thesis, Nanyang Technological University, 2010

Request Dataset

Authorised to Download