Large-Scale Image Retrieval Based on Compressed Camera Identification

Retrieving pictures from large collections according to a specific criterion is an increasingly relevant task. An important , but so far overlooked, such criterion is the retrieval of pictures acquired by a specific camera. Instead of relying on metadata , which can be absent or easily manipulated, a forensic tool is exploited, namely the photo response non-uniformity (PRNU) of the camera sensor. Recent works showed that random projections can be used to significantly compress the PRNU, enabling operation on very large scales, previously impossible due to the size of the PRNU and to the complexity of the matching operations. In this paper, we propose efficient techniques for management and retrieval of images employing the PRNU, and test them on a database of 1174 cameras and half a million pictures downloaded from the Internet.

[1]  Hongbin Zha,et al.  Coarse-to-fine vision-based localization by indexing scale-Invariant features , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Roberto Caldelli,et al.  Fast image clustering of unknown source images , 2010, 2010 IEEE International Workshop on Information Forensics and Security.

[3]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[4]  Ricardo da Silva Torres,et al.  Comparative study of global color and texture descriptors for web image retrieval , 2012, J. Vis. Commun. Image Represent..

[5]  Miroslav Goljan,et al.  Digital camera identification from sensor pattern noise , 2006, IEEE Transactions on Information Forensics and Security.

[6]  Yongjian Hu,et al.  Source Camera Identification Using Large Components of Sensor Pattern Noise , 2009, 2009 2nd International Conference on Computer Science and its Applications.

[7]  Nasir D. Memon,et al.  Efficient Sensor Fingerprint Matching Through Fingerprint Binarization , 2012, IEEE Transactions on Information Forensics and Security.

[8]  Enrico Magli,et al.  Scale-robust compressive camera fingerprint matching with random projections , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Heung-Kyu Lee,et al.  On classification of source cameras: A graph based approach , 2010, 2010 IEEE International Workshop on Information Forensics and Security.

[10]  Aicke Hinrichs,et al.  Johnson‐Lindenstrauss lemma for circulant matrices* * , 2010, Random Struct. Algorithms.

[11]  Chang-Tsun Li,et al.  Fast camera fingerprint search algorithm for source camera identification , 2012, 2012 5th International Symposium on Communications, Control and Signal Processing.

[12]  Jessica J. Fridrich,et al.  Large scale test of sensor fingerprint camera identification , 2009, Electronic Imaging.

[13]  Enrico Magli,et al.  Compressed Fingerprint Matching and Camera Identification via Random Projections , 2015, IEEE Transactions on Information Forensics and Security.

[14]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[15]  Jukka Teuhola,et al.  A Compression Method for Clustered Bit-Vectors , 1978, Inf. Process. Lett..

[16]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[17]  J. Fridrich,et al.  Digital image forensics , 2009, IEEE Signal Processing Magazine.

[18]  Chang-Tsun Li.  Unsupervised classification of digital images using enhanced sensor pattern noise , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[19]  Holger Rauhut,et al.  Circulant and Toeplitz matrices in compressed sensing , 2009, ArXiv.

[20]  Chang-Tsun Li,et al.  Fast source camera identification using matching signs between query and reference fingerprints , 2014, Multimedia Tools and Applications.

[21]  Jan Lukás,et al.  Determining digital image origin using sensor imperfections , 2005, IS&T/SPIE Electronic Imaging.

[22]  Jessica J. Fridrich,et al.  Sensor fingerprint digests for fast camera identification from geometrically distorted images , 2013, Electronic Imaging.

[23]  Matthias Kirchner,et al.  Unexpected artefacts in PRNU-based camera identification: a 'Dresden Image Database' case-study , 2012, MM&Sec '12.

[24]  Andrea Marino,et al.  Blind image clustering based on the Normalized Cuts criterion for camera identification , 2014, Signal Process. Image Commun..

[25]  Mo Chen,et al.  Determining Image Origin and Integrity Using Sensor Noise , 2008, IEEE Transactions on Information Forensics and Security.

[26]  Nicole Immorlica,et al.  Locality-sensitive hashing scheme based on p-stable distributions , 2004, SCG '04.

[27]  Jessica J. Fridrich,et al.  Managing a large database of camera fingerprints , 2010, Electronic Imaging.

[28]  James Ze Wang,et al.  Image retrieval: Ideas, influences, and trends of the new age , 2008, CSUR.

[29]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .