PMID- 24051524
OWN - NLM
STAT- MEDLINE
DCOM- 20140227
LR  - 20211021
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 13
IP  - 9
DP  - 2013 Sep 18
TI  - Detection of upscale-crop and partial manipulation in surveillance video based on 
      sensor pattern noise.
PG  - 12605-31
LID - 10.3390/s130912605 [doi]
AB  - In many court cases, surveillance videos are used as significant court evidence. 
      As these surveillance videos can easily be forged, it may cause serious social 
      issues, such as convicting an innocent person. Nevertheless, there is little 
      research being done on forgery of surveillance videos. This paper proposes a 
      forensic technique to detect forgeries of surveillance video based on sensor 
      pattern noise (SPN). We exploit the scaling invariance of the minimum average 
      correlation energy Mellin radial harmonic (MACE-MRH) correlation filter to 
      reliably unveil traces of upscaling in videos. By excluding the high-frequency 
      components of the investigated video and adaptively choosing the size of the 
      local search window, the proposed method effectively localizes partially 
      manipulated regions. Empirical evidence from a large database of test videos, 
      including RGB (Red, Green, Blue)/infrared video, dynamic-/static-scene video and 
      compressed video, indicates the superior performance of the proposed method.
FAU - Hyun, Dai-Kyung
AU  - Hyun DK
AD  - Department of Computer Science, Korea Advanced Institute of Science and 
      Technology, 291 Daehak-Ro, Yuseong-Gu, Daejon, Korea. hklee@mmc.kaist.ac.kr.
FAU - Ryu, Seung-Jin
AU  - Ryu SJ
FAU - Lee, Hae-Yeoun
AU  - Lee HY
FAU - Lee, Heung-Kyu
AU  - Lee HK
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20130918
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - *Algorithms
MH  - *Data Interpretation, Statistical
MH  - *Fraud
MH  - Image Interpretation, Computer-Assisted/*methods
MH  - Pattern Recognition, Automated/*methods
MH  - Signal-To-Noise Ratio
MH  - Video Recording/*methods
PMC - PMC3821306
EDAT- 2013/09/21 06:00
MHDA- 2014/02/28 06:00
PMCR- 2013/09/01
CRDT- 2013/09/21 06:00
PHST- 2013/07/25 00:00 [received]
PHST- 2013/08/20 00:00 [revised]
PHST- 2013/09/06 00:00 [accepted]
PHST- 2013/09/21 06:00 [entrez]
PHST- 2013/09/21 06:00 [pubmed]
PHST- 2014/02/28 06:00 [medline]
PHST- 2013/09/01 00:00 [pmc-release]
AID - s130912605 [pii]
AID - sensors-13-12605 [pii]
AID - 10.3390/s130912605 [doi]
PST - epublish
SO  - Sensors (Basel). 2013 Sep 18;13(9):12605-31. doi: 10.3390/s130912605.