Incremental update of feature extractor for camera identification

Ruizhe Li; Chang Tsun Li; Yu Guan

doi:10.1109/ICIP.2015.7350813

Incremental update of feature extractor for camera identification

Ruizhe Li, Chang Tsun Li, Yu Guan

University of Warwick

Research output: Book chapter/Published conference paper › Conference paper › peer-review

2 Citations (Scopus)

4 Downloads (Pure)

Abstract

Sensor Pattern Noise (SPN) is an inherent fingerprint of imaging devices, which has been widely used in the tasks of digital camera identification, image classification and forgery detection. In our previous work, a feature extraction method based on PCA denoising concept was applied to extract a set of principal components from the original noise residual. However, this algorithm is inefficient when query cameras are continuously received. To solve this problem, we propose an extension based on Candid Covariance-free Incremental PCA (CCIPCA) and two modifications to incrementally update the feature extractor according to the received cameras. Experimental results show that the PCA and CCIPCA based features both outperform their original features on the ROC performance, and CCIPCA is more efficient on camera updating.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	324-328
Number of pages	5
ISBN (Electronic)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7350813
Publication status	Published - 09 Dec 2015
Event	2015 22nd IEEE International Conference on Image Processing: ICIP 2015 - Quebec City Convention Centre, Quebec City, Canada Duration: 27 Sept 2015 → 30 Sept 2015 http://icip2015.org/index.html

Conference

Conference	2015 22nd IEEE International Conference on Image Processing
Country/Territory	Canada
City	Quebec City
Period	27/09/15 → 30/09/15
Other	The International Conference on Image Processing (ICIP), sponsored by the IEEE Signal Processing Society, is the premier forum for the presentation of technological advances and research results in the fields of theoretical, experimental, and applied image and video processing. ICIP 2015, the twenty second in the series that has been held annually since 1994, brings together leading engineers and scientists in image and video processing from around the world. Research frontiers in fields ranging from traditional image processing applications to evolving multimedia and video technologies are regularly advanced by results first reported in ICIP technical sessions.
Internet address	http://icip2015.org/index.html

Access to Document

10.1109/ICIP.2015.7350813

Cite this

@inproceedings{9e8c33f6651f45d0a4a165876eb77672,

title = "Incremental update of feature extractor for camera identification",

abstract = "Sensor Pattern Noise (SPN) is an inherent fingerprint of imaging devices, which has been widely used in the tasks of digital camera identification, image classification and forgery detection. In our previous work, a feature extraction method based on PCA denoising concept was applied to extract a set of principal components from the original noise residual. However, this algorithm is inefficient when query cameras are continuously received. To solve this problem, we propose an extension based on Candid Covariance-free Incremental PCA (CCIPCA) and two modifications to incrementally update the feature extractor according to the received cameras. Experimental results show that the PCA and CCIPCA based features both outperform their original features on the ROC performance, and CCIPCA is more efficient on camera updating.",

keywords = "camera identification, Digital forensics, PCA denoising, sensor pattern noise",

author = "Ruizhe Li and Li, {Chang Tsun} and Yu Guan",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7350813",

language = "English",

pages = "324--328",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2015 22nd IEEE International Conference on Image Processing : ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

url = "http://icip2015.org/index.html",

}

Li, R, Li, CT & Guan, Y 2015, Incremental update of feature extractor for camera identification. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings., 7350813, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 324-328, 2015 22nd IEEE International Conference on Image Processing, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7350813

Incremental update of feature extractor for camera identification. / Li, Ruizhe; Li, Chang Tsun; Guan, Yu.

2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. United States : IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 324-328 7350813.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Incremental update of feature extractor for camera identification

AU - Li, Ruizhe

AU - Li, Chang Tsun

AU - Guan, Yu

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Sensor Pattern Noise (SPN) is an inherent fingerprint of imaging devices, which has been widely used in the tasks of digital camera identification, image classification and forgery detection. In our previous work, a feature extraction method based on PCA denoising concept was applied to extract a set of principal components from the original noise residual. However, this algorithm is inefficient when query cameras are continuously received. To solve this problem, we propose an extension based on Candid Covariance-free Incremental PCA (CCIPCA) and two modifications to incrementally update the feature extractor according to the received cameras. Experimental results show that the PCA and CCIPCA based features both outperform their original features on the ROC performance, and CCIPCA is more efficient on camera updating.

AB - Sensor Pattern Noise (SPN) is an inherent fingerprint of imaging devices, which has been widely used in the tasks of digital camera identification, image classification and forgery detection. In our previous work, a feature extraction method based on PCA denoising concept was applied to extract a set of principal components from the original noise residual. However, this algorithm is inefficient when query cameras are continuously received. To solve this problem, we propose an extension based on Candid Covariance-free Incremental PCA (CCIPCA) and two modifications to incrementally update the feature extractor according to the received cameras. Experimental results show that the PCA and CCIPCA based features both outperform their original features on the ROC performance, and CCIPCA is more efficient on camera updating.

KW - camera identification

KW - Digital forensics

KW - PCA denoising

KW - sensor pattern noise

UR - http://www.scopus.com/inward/record.url?scp=84956681216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956681216&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7350813

DO - 10.1109/ICIP.2015.7350813

M3 - Conference paper

AN - SCOPUS:84956681216

SP - 324

EP - 328

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 2015 22nd IEEE International Conference on Image Processing

Y2 - 27 September 2015 through 30 September 2015

ER -

Incremental update of feature extractor for camera identification

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this