Source Camera Identification Using Sensor Pattern Noise in Digital Photographs


Authors

DOI:

https://doi.org/10.22517/23447214.24829

Keywords:

Sensor Pattern Noise (SPN), Source Camera Identification (SCI), Support Vector Machines (SVM), Undecimated Wavelet Transform (UWT).

Abstract

At present it is allowed to present digital evidence as evidence in judicial investigations, but at the same time the proliferation of editing programs can skew the information provided by the device that captured the evidence.

In computer forensics, normally for source camera identification (SCI), the sensor noise pattern (SPN) is proposed, on which this investigation was focused, where the objective was to implement and evaluate techniques to face the SCI problem with the SPN using the Non-Decimated Wavelet Transform (UWT). For the implementation of this technique, bright field photographs were used and noise extraction from dark frame photographs was also proposed in order to compare accuracy and training time in each background in which the extraction and filtering of characteristics was carried out. In the space of frequencies by means of the Wavelet Transform not Decimated (UWT) and a Wiener filter, which allows to obtain the fingerprint of the sensor and thus carry out a multiclass analysis by means of classification with vector support machines (SVM) with which obtained accuracy values ​​greater than 95% and an average training time of less than 1586 seconds.

Downloads

Download data is not yet available.

Author Biographies

Camilo Muñoz Bermúdez, Universidad Tecnológica de Pereira

Camilo Muñoz Bermúdez  nació en Pereira, Colombia en 1997. Es Ingeniero Físico de la Universidad Tecnológica de Pereira (UTP), desde el 2020. Las áreas de interés son: ciencias básicas, robótica, visión por computadora, machine learning y Deep learning. Obtuvo una calificación sobresaliente en su trabajo de pregrado, el cual estuvo enfocado en informática forense y aplicó técnicas de machine learning y Deep learning.

Jimmy Alexander Cortes Osorio, Universidad Tecnológica de Pereira

Jimmy Alexander Cortes-Osorio nació en Pereira, Colombia, en 1968. Recibió el título de pregrado en ingeniería eléctrica y de maestría en Instrumentación Física en  la Universidad Tecnológica de Pereira (UTP), Pereira, en 1999 y 2009, respectivamente. También es  PhD. en Ingeniería Automática  de  la Universidad Nacional de Colombia (UNAL), Colombia en 2020. Desde 2003 a 2012, fue profesor en el Departamento de Física de la UTP, donde ha sido trabajado  tiempo completo desde 2013. Sus intereses de investigación actuales incluyen procesamiento de imágenes, análisis de movimiento de imágenes, visión artificial, aprendizaje automático, aprendizaje profundo e instrumentación y medidas. El profesor Cortes-Osorio es autor de varios libros de texto y resultados de investigación y de decenas de artículos científicos. También ha participado en eventos científicos internacionales como ponente en varios países de Asia, Europa y América. Cortés-Osorio es a su vez Miembro Afiliado de la Sociedad de Matemáticas Industriales y Aplicadas (SIAM) y del Instituto de Ingenieros Eléctricos y Electrónicos (IEEE). Actualmente, es editor en jefe de la revista científica Scientia et Technica en Colombia, Sudamérica.

Downloads

Published

2021-11-30

How to Cite

Muñoz Bermúdez, C., & Cortes Osorio, J. A. (2021). Source Camera Identification Using Sensor Pattern Noise in Digital Photographs. Scientia Et Technica, 26(04), 474–485. https://doi.org/10.22517/23447214.24829

Issue

Vol. 26 No. 04 (2021): Octubre-Diciembre

Section

Sistemas y Computación

License

Copyright (c) 2021 Scientia et Technica

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

The undersigned authors declare that the article submitted to the journal Scientia et Technica is an original work and that all its content is free of third-party copyright restrictions or has the corresponding authorizations. Consequently, the authors assume responsibility for any litigation or claim related to intellectual property rights, releasing the Technological University of Pereira and the journal Scientia et Technica from any liability.

If the submitted work is accepted for publication, the authors retain copyright to the article and grant the journal Scientia et Technica the right of first publication, as well as a non-exclusive, perpetual license to reproduce, edit, distribute, display, and publicly communicate the article in any medium or format, including print, electronic, databases, repositories, the Internet, or other scientific dissemination systems. The authors agree that the article will be published in open access and distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0).

The journal Scientia will respect in all cases the moral rights of the authors, in accordance with the provisions of article 30 of Law 23 of 1982 of the Republic of Colombia, recognizing the authorship of the work, the right to integrity and the right of disclosure, which are inalienable and non-waivable.