Efficient techniques for sensor fingerprint matching in large image and video databases

Sevinc Bayram, H. Taha Sencar, Nasir Memon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Several promising techniques have been recently proposed to bind an image or video to its source acquisition device. These techniques have been intensively studied to address performance issues, but the computational efficiency aspect has not been given due consideration. Considering very large databases, in this paper, we focus on the efficiency of the sensor fingerprint based source device identification technique.1 We propose a novel scheme based on tree structured vector quantization that offers logarithmic improvements in the search complexity as compared to conventional approach. To demonstrate the effectiveness of the proposed approach several experiments are conducted. Our results show that with the proposed scheme major improvement in search time can be achieved.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II
Volume7541
DOIs
StatePublished - 2010
EventMedia Forensics and Security II - San Jose, CA, United States
Duration: Jan 18 2010Jan 20 2010

Other

OtherMedia Forensics and Security II
CountryUnited States
CitySan Jose, CA
Period1/18/101/20/10

Fingerprint

Video Databases
Image Database
Vector quantization
Fingerprint
Computational efficiency
Sensor
vector quantization
Vector Quantization
sensors
Sensors
Computational Efficiency
acquisition
Logarithmic
Experiments
Demonstrate
Experiment
Acquisition

Keywords

  • Camera identification
  • Efficient search
  • PRNU noise

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Bayram, S., Sencar, H. T., & Memon, N. (2010). Efficient techniques for sensor fingerprint matching in large image and video databases. In Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II (Vol. 7541). [754109] https://doi.org/10.1117/12.845737

Efficient techniques for sensor fingerprint matching in large image and video databases. / Bayram, Sevinc; Sencar, H. Taha; Memon, Nasir.

Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II. Vol. 7541 2010. 754109.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bayram, S, Sencar, HT & Memon, N 2010, Efficient techniques for sensor fingerprint matching in large image and video databases. in Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II. vol. 7541, 754109, Media Forensics and Security II, San Jose, CA, United States, 1/18/10. https://doi.org/10.1117/12.845737
Bayram S, Sencar HT, Memon N. Efficient techniques for sensor fingerprint matching in large image and video databases. In Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II. Vol. 7541. 2010. 754109 https://doi.org/10.1117/12.845737
Bayram, Sevinc ; Sencar, H. Taha ; Memon, Nasir. / Efficient techniques for sensor fingerprint matching in large image and video databases. Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II. Vol. 7541 2010.
@inproceedings{618a4e104d9740db9fb516f9bcbbdd3e,
title = "Efficient techniques for sensor fingerprint matching in large image and video databases",
abstract = "Several promising techniques have been recently proposed to bind an image or video to its source acquisition device. These techniques have been intensively studied to address performance issues, but the computational efficiency aspect has not been given due consideration. Considering very large databases, in this paper, we focus on the efficiency of the sensor fingerprint based source device identification technique.1 We propose a novel scheme based on tree structured vector quantization that offers logarithmic improvements in the search complexity as compared to conventional approach. To demonstrate the effectiveness of the proposed approach several experiments are conducted. Our results show that with the proposed scheme major improvement in search time can be achieved.",
keywords = "Camera identification, Efficient search, PRNU noise",
author = "Sevinc Bayram and Sencar, {H. Taha} and Nasir Memon",
year = "2010",
doi = "10.1117/12.845737",
language = "English (US)",
isbn = "9780819479341",
volume = "7541",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II",

}

TY - GEN

T1 - Efficient techniques for sensor fingerprint matching in large image and video databases

AU - Bayram, Sevinc

AU - Sencar, H. Taha

AU - Memon, Nasir

PY - 2010

Y1 - 2010

N2 - Several promising techniques have been recently proposed to bind an image or video to its source acquisition device. These techniques have been intensively studied to address performance issues, but the computational efficiency aspect has not been given due consideration. Considering very large databases, in this paper, we focus on the efficiency of the sensor fingerprint based source device identification technique.1 We propose a novel scheme based on tree structured vector quantization that offers logarithmic improvements in the search complexity as compared to conventional approach. To demonstrate the effectiveness of the proposed approach several experiments are conducted. Our results show that with the proposed scheme major improvement in search time can be achieved.

AB - Several promising techniques have been recently proposed to bind an image or video to its source acquisition device. These techniques have been intensively studied to address performance issues, but the computational efficiency aspect has not been given due consideration. Considering very large databases, in this paper, we focus on the efficiency of the sensor fingerprint based source device identification technique.1 We propose a novel scheme based on tree structured vector quantization that offers logarithmic improvements in the search complexity as compared to conventional approach. To demonstrate the effectiveness of the proposed approach several experiments are conducted. Our results show that with the proposed scheme major improvement in search time can be achieved.

KW - Camera identification

KW - Efficient search

KW - PRNU noise

UR - http://www.scopus.com/inward/record.url?scp=77951856971&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951856971&partnerID=8YFLogxK

U2 - 10.1117/12.845737

DO - 10.1117/12.845737

M3 - Conference contribution

AN - SCOPUS:77951856971

SN - 9780819479341

VL - 7541

BT - Proceedings of SPIE-IS and T Electronic Imaging - Media Forensics and Security II

ER -