Detection of Upscale-Crop and Partial Manipulation in Surveillance VideoBased on Sensor Pattern Noise
| Autor: | Hae-Yeoun Lee, Dai-Kyung Hyun, Seung Jin Ryu, Heung-Kyu Lee |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2013 |
| Předmět: |
Computer science
Video Recording ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Signal-To-Noise Ratio lcsh:Chemical technology Biochemistry Article Pattern Recognition Automated Analytical Chemistry Digital image Signal-to-noise ratio Image Interpretation Computer-Assisted Computer vision lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation forgery detection digital image forensic sensor pattern noise business.industry Fraud surveillance video forgery Atomic and Molecular Physics and Optics MACE-MRH correlation filter Data Interpretation Statistical Video tracking RGB color model Noise (video) Artificial intelligence business Algorithms Energy (signal processing) |
| Zdroj: | SENSORS(13): 9 Sensors, Vol 13, Iss 9, Pp 12605-12631 (2013) Sensors (Basel, Switzerland) Sensors Volume 13 Issue 9 Pages: 12605-12631 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|