CNN-Based Mobile Device Detection Using Still Images

Surbhi Gupta; Neela Pravalika; Padmalaya Nayak; Jaafar Al Ghazo

doi:10.1007/978-981-16-2919-8_3

CNN-Based Mobile Device Detection Using Still Images

Surbhi Gupta
, Neela Pravalika
, Padmalaya Nayak
, Jaafar Al Ghazo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Image forgery has been increased enormously due to the development of software and introduction of new cheaper digital devices like cameras and cellular phones. The introduction of new devices leads to inadvertent capturing of images. A lot of misuse of these devices led to the need for their identification. Source camera identification deals with the issue of identification of the mobile device using their camera through which image has been taken. This empowers the scientific agent to spot mobile device that has been used for capturing the specific image during the study. This is significant as this alphanumeric content is considered as a inaudible observer. In this proposed work, we are reviewing the various approaches for SCI which depend on classical machine learning algorithms feature extraction. Then, a CNN model is proposed for identification of mobile device using vision dataset. High accuracy of 92% is achieved for vision dataset.

Original language	English (US)
Title of host publication	IoT and Analytics for Sensor Networks - Proceedings of ICWSNUCA 2021
Editors	Padmalaya Nayak, Souvik Pal, Sheng-Lung Peng
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	23-33
Number of pages	11
ISBN (Print)	9789811629181
DOIs	https://doi.org/10.1007/978-981-16-2919-8_3
State	Published - 2022
Externally published	Yes
Event	1st International Conference on Wireless Sensor Networks, Ubiquitous Computing and Applications, ICWSNUCA 2021 - Virtual, Online Duration: Feb 26 2021 → Feb 27 2021

Publication series

Name	Lecture Notes in Networks and Systems
Volume	244
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	1st International Conference on Wireless Sensor Networks, Ubiquitous Computing and Applications, ICWSNUCA 2021
City	Virtual, Online
Period	2/26/21 → 2/27/21

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Classification
Convolutional neural network
Feature extraction
Mobile devices
Sensor fingerprint
Source camera identification

Publisher link

10.1007/978-981-16-2919-8_3

Find It

Find It at U of M Libraries

Cite this

Gupta, S., Pravalika, N., Nayak, P., & Al Ghazo, J. (2022). CNN-Based Mobile Device Detection Using Still Images. In P. Nayak, S. Pal, & S.-L. Peng (Eds.), IoT and Analytics for Sensor Networks - Proceedings of ICWSNUCA 2021 (pp. 23-33). (Lecture Notes in Networks and Systems; Vol. 244). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-2919-8_3

CNN-Based Mobile Device Detection Using Still Images. / Gupta, Surbhi; Pravalika, Neela; Nayak, Padmalaya et al.
IoT and Analytics for Sensor Networks - Proceedings of ICWSNUCA 2021. ed. / Padmalaya Nayak; Souvik Pal; Sheng-Lung Peng. Springer Science and Business Media Deutschland GmbH, 2022. p. 23-33 (Lecture Notes in Networks and Systems; Vol. 244).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Gupta, S, Pravalika, N, Nayak, P & Al Ghazo, J 2022, CNN-Based Mobile Device Detection Using Still Images. in P Nayak, S Pal & S-L Peng (eds), IoT and Analytics for Sensor Networks - Proceedings of ICWSNUCA 2021. Lecture Notes in Networks and Systems, vol. 244, Springer Science and Business Media Deutschland GmbH, pp. 23-33, 1st International Conference on Wireless Sensor Networks, Ubiquitous Computing and Applications, ICWSNUCA 2021, Virtual, Online, 2/26/21. https://doi.org/10.1007/978-981-16-2919-8_3

@inproceedings{8ffd8cf0a836499bac64507adb353f8c,

title = "CNN-Based Mobile Device Detection Using Still Images",

abstract = "Image forgery has been increased enormously due to the development of software and introduction of new cheaper digital devices like cameras and cellular phones. The introduction of new devices leads to inadvertent capturing of images. A lot of misuse of these devices led to the need for their identification. Source camera identification deals with the issue of identification of the mobile device using their camera through which image has been taken. This empowers the scientific agent to spot mobile device that has been used for capturing the specific image during the study. This is significant as this alphanumeric content is considered as a inaudible observer. In this proposed work, we are reviewing the various approaches for SCI which depend on classical machine learning algorithms feature extraction. Then, a CNN model is proposed for identification of mobile device using vision dataset. High accuracy of 92\% is achieved for vision dataset.",

keywords = "Classification, Convolutional neural network, Feature extraction, Mobile devices, Sensor fingerprint, Source camera identification",

author = "Surbhi Gupta and Neela Pravalika and Padmalaya Nayak and \{Al Ghazo\}, Jaafar",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 1st International Conference on Wireless Sensor Networks, Ubiquitous Computing and Applications, ICWSNUCA 2021 ; Conference date: 26-02-2021 Through 27-02-2021",

year = "2022",

doi = "10.1007/978-981-16-2919-8\_3",

language = "English (US)",

isbn = "9789811629181",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "23--33",

editor = "Padmalaya Nayak and Souvik Pal and Sheng-Lung Peng",

booktitle = "IoT and Analytics for Sensor Networks - Proceedings of ICWSNUCA 2021",

address = "Germany",

}

TY - GEN

T1 - CNN-Based Mobile Device Detection Using Still Images

AU - Gupta, Surbhi

AU - Pravalika, Neela

AU - Nayak, Padmalaya

AU - Al Ghazo, Jaafar

PY - 2022

Y1 - 2022

N2 - Image forgery has been increased enormously due to the development of software and introduction of new cheaper digital devices like cameras and cellular phones. The introduction of new devices leads to inadvertent capturing of images. A lot of misuse of these devices led to the need for their identification. Source camera identification deals with the issue of identification of the mobile device using their camera through which image has been taken. This empowers the scientific agent to spot mobile device that has been used for capturing the specific image during the study. This is significant as this alphanumeric content is considered as a inaudible observer. In this proposed work, we are reviewing the various approaches for SCI which depend on classical machine learning algorithms feature extraction. Then, a CNN model is proposed for identification of mobile device using vision dataset. High accuracy of 92% is achieved for vision dataset.

AB - Image forgery has been increased enormously due to the development of software and introduction of new cheaper digital devices like cameras and cellular phones. The introduction of new devices leads to inadvertent capturing of images. A lot of misuse of these devices led to the need for their identification. Source camera identification deals with the issue of identification of the mobile device using their camera through which image has been taken. This empowers the scientific agent to spot mobile device that has been used for capturing the specific image during the study. This is significant as this alphanumeric content is considered as a inaudible observer. In this proposed work, we are reviewing the various approaches for SCI which depend on classical machine learning algorithms feature extraction. Then, a CNN model is proposed for identification of mobile device using vision dataset. High accuracy of 92% is achieved for vision dataset.

KW - Classification

KW - Convolutional neural network

KW - Feature extraction

KW - Mobile devices

KW - Sensor fingerprint

KW - Source camera identification

UR - https://www.scopus.com/pages/publications/85115659018

UR - https://www.scopus.com/pages/publications/85115659018#tab=citedBy

U2 - 10.1007/978-981-16-2919-8_3

DO - 10.1007/978-981-16-2919-8_3

M3 - Conference contribution

AN - SCOPUS:85115659018

SN - 9789811629181

T3 - Lecture Notes in Networks and Systems

SP - 23

EP - 33

BT - IoT and Analytics for Sensor Networks - Proceedings of ICWSNUCA 2021

A2 - Nayak, Padmalaya

A2 - Pal, Souvik

A2 - Peng, Sheng-Lung

PB - Springer Science and Business Media Deutschland GmbH

T2 - 1st International Conference on Wireless Sensor Networks, Ubiquitous Computing and Applications, ICWSNUCA 2021

Y2 - 26 February 2021 through 27 February 2021

ER -

CNN-Based Mobile Device Detection Using Still Images

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this