PCA-based denoising of Sensor Pattern Noise for source camera identification

Ruizhe Li, Yu Guan, Chang Tsun Li

Research output: Book chapter/Published conference paperConference paper

10 Citations (Scopus)

Abstract

Sensor Pattern Noise (SPN) has been proved to be an inherent fingerprint of the imaging device for source identification. However, SPN extracted from digital images can be severely contaminated by scene details. Moreover, SPN with high dimensionality may cause excessive time cost on calculating correlation between SPNs, which will limit its applicability to the source camera identification or image classification with a large dataset. In this work, an effective scheme based on principal component analysis (PCA) is proposed to address these two problems. By transforming SPN into eigenspace spanned by the principal components, the scene details and trivial information can be significantly suppressed. In addition, due to the dimensionality reduction property of PCA, the size of SPN is greatly reduced, consequently reducing the time cost of calculating similarity between SPNs. Our experiments are conducted on the Dresden database, and results demonstrate that the proposed method outperforms could achieve the state-of-art performance in terms of the Receiver Operating Characteristic (ROC) curves while reducing the dimensionality of SPN.
Original languageEnglish
Title of host publicationProceedings of 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages436-440
Number of pages5
ISBN (Electronic)9781479954032
DOIs
Publication statusPublished - 03 Sep 2014
Event2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP) - XiĄŻan International Conference Center (Qujiang Hotel), Xi'an, China
Duration: 09 Jul 201413 Jul 2014

Conference

Conference2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)
CountryChina
CityXi'an
Period09/07/1413/07/14
OtherAn elite group of plenary and invited world-class speakers to share technical and professional insights. Education & research panel by international and national leading SIP professors and scientists. 11 technical tracks on SIP, invited papers on latest significance contribution, and open-call papers on novel ideas. An industry forum for idea exchange and networking among SIP industries as well as between academia and industries. Summer school and tutorials on latest technical advances. Demo & exhibits. Showcase of recent journal articles from major domestic SIP labs and companies. Professional development activities to demystify issues of interests to many colleagues in China.

Fingerprint Dive into the research topics of 'PCA-based denoising of Sensor Pattern Noise for source camera identification'. Together they form a unique fingerprint.

Cite this