Detecting the Presence of ENF Signal in Digital Videos: A Superpixel-Based Approach

Saffet Vatansever, Ahmet Emir Dirik, Nasir Memon

Research output: Contribution to journalArticle

Abstract

Electrical network frequency (ENF) instantaneously fluctuates around its nominal value (50/60 Hz) due to a continuous disparity between generated power and consumed power. Consequently, luminous intensity of a mains-powered light source varies depending on ENF fluctuations in the grid network. Variations in the luminance over time can be captured from video recordings and ENF can be estimated through content analysis of these recordings. In ENF-based video forensics, it is critical to check whether a given video file is appropriate for this type of analysis. That is, if ENF signal is not present in a given video, it would be useless to apply ENF-based forensic analysis. In this letter, an ENF signal presence detection method is introduced for videos. The proposed method is based on multiple ENF signal estimations from steady superpixels, i.e., pixels that are most likely uniform in color, brightness, and texture, and intra-class similarity of the estimated signals. Subsequently, consistency among these estimates is then used to determine the presence or absence of an ENF signal in a given video. The proposed technique can operate on video clips as short as 2 min and is independent of the camera sensor type, i.e., CCD or CMOS.

Original languageEnglish (US)
Article number8012515
Pages (from-to)1463-1467
Number of pages5
JournalIEEE Signal Processing Letters
Volume24
Issue number10
DOIs
StatePublished - Oct 1 2017

Fingerprint

Electrical Networks
Digital Video
Luminance
Video recording
Signal detection
Charge coupled devices
Light sources
Textures
Pixels
Cameras
Color
Sensors
Content Analysis
Brightness
Categorical or nominal
Texture
Pixel
Camera
Likely
Vary

Keywords

  • Electrical network frequency (ENF)
  • ENF detection
  • multimedia forensics
  • superpixel
  • video forensics

ASJC Scopus subject areas

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Detecting the Presence of ENF Signal in Digital Videos : A Superpixel-Based Approach. / Vatansever, Saffet; Dirik, Ahmet Emir; Memon, Nasir.

In: IEEE Signal Processing Letters, Vol. 24, No. 10, 8012515, 01.10.2017, p. 1463-1467.

Research output: Contribution to journalArticle

Vatansever, Saffet ; Dirik, Ahmet Emir ; Memon, Nasir. / Detecting the Presence of ENF Signal in Digital Videos : A Superpixel-Based Approach. In: IEEE Signal Processing Letters. 2017 ; Vol. 24, No. 10. pp. 1463-1467.
@article{4530cac100114087b4ef8669ba0d3189,
title = "Detecting the Presence of ENF Signal in Digital Videos: A Superpixel-Based Approach",
abstract = "Electrical network frequency (ENF) instantaneously fluctuates around its nominal value (50/60 Hz) due to a continuous disparity between generated power and consumed power. Consequently, luminous intensity of a mains-powered light source varies depending on ENF fluctuations in the grid network. Variations in the luminance over time can be captured from video recordings and ENF can be estimated through content analysis of these recordings. In ENF-based video forensics, it is critical to check whether a given video file is appropriate for this type of analysis. That is, if ENF signal is not present in a given video, it would be useless to apply ENF-based forensic analysis. In this letter, an ENF signal presence detection method is introduced for videos. The proposed method is based on multiple ENF signal estimations from steady superpixels, i.e., pixels that are most likely uniform in color, brightness, and texture, and intra-class similarity of the estimated signals. Subsequently, consistency among these estimates is then used to determine the presence or absence of an ENF signal in a given video. The proposed technique can operate on video clips as short as 2 min and is independent of the camera sensor type, i.e., CCD or CMOS.",
keywords = "Electrical network frequency (ENF), ENF detection, multimedia forensics, superpixel, video forensics",
author = "Saffet Vatansever and Dirik, {Ahmet Emir} and Nasir Memon",
year = "2017",
month = "10",
day = "1",
doi = "10.1109/LSP.2017.2741440",
language = "English (US)",
volume = "24",
pages = "1463--1467",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

TY - JOUR

T1 - Detecting the Presence of ENF Signal in Digital Videos

T2 - A Superpixel-Based Approach

AU - Vatansever, Saffet

AU - Dirik, Ahmet Emir

AU - Memon, Nasir

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Electrical network frequency (ENF) instantaneously fluctuates around its nominal value (50/60 Hz) due to a continuous disparity between generated power and consumed power. Consequently, luminous intensity of a mains-powered light source varies depending on ENF fluctuations in the grid network. Variations in the luminance over time can be captured from video recordings and ENF can be estimated through content analysis of these recordings. In ENF-based video forensics, it is critical to check whether a given video file is appropriate for this type of analysis. That is, if ENF signal is not present in a given video, it would be useless to apply ENF-based forensic analysis. In this letter, an ENF signal presence detection method is introduced for videos. The proposed method is based on multiple ENF signal estimations from steady superpixels, i.e., pixels that are most likely uniform in color, brightness, and texture, and intra-class similarity of the estimated signals. Subsequently, consistency among these estimates is then used to determine the presence or absence of an ENF signal in a given video. The proposed technique can operate on video clips as short as 2 min and is independent of the camera sensor type, i.e., CCD or CMOS.

AB - Electrical network frequency (ENF) instantaneously fluctuates around its nominal value (50/60 Hz) due to a continuous disparity between generated power and consumed power. Consequently, luminous intensity of a mains-powered light source varies depending on ENF fluctuations in the grid network. Variations in the luminance over time can be captured from video recordings and ENF can be estimated through content analysis of these recordings. In ENF-based video forensics, it is critical to check whether a given video file is appropriate for this type of analysis. That is, if ENF signal is not present in a given video, it would be useless to apply ENF-based forensic analysis. In this letter, an ENF signal presence detection method is introduced for videos. The proposed method is based on multiple ENF signal estimations from steady superpixels, i.e., pixels that are most likely uniform in color, brightness, and texture, and intra-class similarity of the estimated signals. Subsequently, consistency among these estimates is then used to determine the presence or absence of an ENF signal in a given video. The proposed technique can operate on video clips as short as 2 min and is independent of the camera sensor type, i.e., CCD or CMOS.

KW - Electrical network frequency (ENF)

KW - ENF detection

KW - multimedia forensics

KW - superpixel

KW - video forensics

UR - http://www.scopus.com/inward/record.url?scp=85028499689&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028499689&partnerID=8YFLogxK

U2 - 10.1109/LSP.2017.2741440

DO - 10.1109/LSP.2017.2741440

M3 - Article

AN - SCOPUS:85028499689

VL - 24

SP - 1463

EP - 1467

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 10

M1 - 8012515

ER -