A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification

Sharan Seshadri, K. R. Akshatha, A. K. Karunakar, Kelvin Harrison Paul

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

Abstract

In this paper, a preliminary method of source camera identification using transfer learning methods is proposed. Every image taken by a camera has a unique artefact, known as photo response non-uniformity (PRNU) noise that is manifested in the image, because of irregularities during the manufacturing process of the image sensor present in that camera. A convolutional neural network (CNN) is used here to extract the features pertaining to the noise residual of a specific camera, which can be later passed to a classifier. In this paper, we use a CNN architecture that has weights that have been pre-trained to extract the residual features. This method is called transfer learning and is used after denoising the images in the dataset. The noise residual features are extracted by the transfer learning model and are then passed to a Support Vector Machine (SVM) classifier. Despite the simplicity of this approach, the results obtained are favorable compared to the existing methods, especially considering the small dataset used.

Original languageEnglish
Title of host publicationAdvances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC
EditorsKohei Arai, Supriya Kapoor
PublisherSpringer Verlag
Pages246-255
Number of pages10
ISBN (Print)9783030177973
DOIs
Publication statusPublished - 01-01-2020
EventComputer Vision Conference, CVC 2019 - Las Vegas, United States
Duration: 25-04-201926-04-2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume944
ISSN (Print)2194-5357

Conference

ConferenceComputer Vision Conference, CVC 2019
CountryUnited States
CityLas Vegas
Period25-04-1926-04-19

Fingerprint

Cameras
Classifiers
Neural networks
Network architecture
Image sensors
Support vector machines

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Seshadri, S., Akshatha, K. R., Karunakar, A. K., & Paul, K. H. (2020). A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification. In K. Arai, & S. Kapoor (Eds.), Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC (pp. 246-255). (Advances in Intelligent Systems and Computing; Vol. 944). Springer Verlag. https://doi.org/10.1007/978-3-030-17798-0_21
Seshadri, Sharan ; Akshatha, K. R. ; Karunakar, A. K. ; Paul, Kelvin Harrison. / A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification. Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. editor / Kohei Arai ; Supriya Kapoor. Springer Verlag, 2020. pp. 246-255 (Advances in Intelligent Systems and Computing).
@inproceedings{7ae026b618b747dea77770d4fb9d0fb3,
title = "A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification",
abstract = "In this paper, a preliminary method of source camera identification using transfer learning methods is proposed. Every image taken by a camera has a unique artefact, known as photo response non-uniformity (PRNU) noise that is manifested in the image, because of irregularities during the manufacturing process of the image sensor present in that camera. A convolutional neural network (CNN) is used here to extract the features pertaining to the noise residual of a specific camera, which can be later passed to a classifier. In this paper, we use a CNN architecture that has weights that have been pre-trained to extract the residual features. This method is called transfer learning and is used after denoising the images in the dataset. The noise residual features are extracted by the transfer learning model and are then passed to a Support Vector Machine (SVM) classifier. Despite the simplicity of this approach, the results obtained are favorable compared to the existing methods, especially considering the small dataset used.",
author = "Sharan Seshadri and Akshatha, {K. R.} and Karunakar, {A. K.} and Paul, {Kelvin Harrison}",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-17798-0_21",
language = "English",
isbn = "9783030177973",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "246--255",
editor = "Kohei Arai and Supriya Kapoor",
booktitle = "Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC",
address = "Germany",

}

Seshadri, S, Akshatha, KR, Karunakar, AK & Paul, KH 2020, A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification. in K Arai & S Kapoor (eds), Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. Advances in Intelligent Systems and Computing, vol. 944, Springer Verlag, pp. 246-255, Computer Vision Conference, CVC 2019, Las Vegas, United States, 25-04-19. https://doi.org/10.1007/978-3-030-17798-0_21

A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification. / Seshadri, Sharan; Akshatha, K. R.; Karunakar, A. K.; Paul, Kelvin Harrison.

Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. ed. / Kohei Arai; Supriya Kapoor. Springer Verlag, 2020. p. 246-255 (Advances in Intelligent Systems and Computing; Vol. 944).

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

TY - GEN

T1 - A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification

AU - Seshadri, Sharan

AU - Akshatha, K. R.

AU - Karunakar, A. K.

AU - Paul, Kelvin Harrison

PY - 2020/1/1

Y1 - 2020/1/1

N2 - In this paper, a preliminary method of source camera identification using transfer learning methods is proposed. Every image taken by a camera has a unique artefact, known as photo response non-uniformity (PRNU) noise that is manifested in the image, because of irregularities during the manufacturing process of the image sensor present in that camera. A convolutional neural network (CNN) is used here to extract the features pertaining to the noise residual of a specific camera, which can be later passed to a classifier. In this paper, we use a CNN architecture that has weights that have been pre-trained to extract the residual features. This method is called transfer learning and is used after denoising the images in the dataset. The noise residual features are extracted by the transfer learning model and are then passed to a Support Vector Machine (SVM) classifier. Despite the simplicity of this approach, the results obtained are favorable compared to the existing methods, especially considering the small dataset used.

AB - In this paper, a preliminary method of source camera identification using transfer learning methods is proposed. Every image taken by a camera has a unique artefact, known as photo response non-uniformity (PRNU) noise that is manifested in the image, because of irregularities during the manufacturing process of the image sensor present in that camera. A convolutional neural network (CNN) is used here to extract the features pertaining to the noise residual of a specific camera, which can be later passed to a classifier. In this paper, we use a CNN architecture that has weights that have been pre-trained to extract the residual features. This method is called transfer learning and is used after denoising the images in the dataset. The noise residual features are extracted by the transfer learning model and are then passed to a Support Vector Machine (SVM) classifier. Despite the simplicity of this approach, the results obtained are favorable compared to the existing methods, especially considering the small dataset used.

UR - http://www.scopus.com/inward/record.url?scp=85065473773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065473773&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-17798-0_21

DO - 10.1007/978-3-030-17798-0_21

M3 - Conference contribution

AN - SCOPUS:85065473773

SN - 9783030177973

T3 - Advances in Intelligent Systems and Computing

SP - 246

EP - 255

BT - Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC

A2 - Arai, Kohei

A2 - Kapoor, Supriya

PB - Springer Verlag

ER -

Seshadri S, Akshatha KR, Karunakar AK, Paul KH. A Preliminary Approach to Using PRNU Based Transfer Learning for Camera Identification. In Arai K, Kapoor S, editors, Advances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC. Springer Verlag. 2020. p. 246-255. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-17798-0_21