Abstract | ||
---|---|---|
A fingerprinting is related to cryptographic hash functions. In contrast to cryptographic hash functions this robust digest is sensitive only to perceptual change. 'Minor changes. which are not affecting the perception, do not result in a different fingerprint. This technique is used in content-based retrieval, content monitoring, and content filtering. In this paper we present a cumulant-based image fingerprinting method. Cumulants are typically used in signal processing and image processing, e.g. for blind source separation or Independent Component Analysis (ICA). From an image with reduced dimensions we calculate cumulants its an initial feature vector. This feature vector is transformed into an image fingerprint. The theoretical advantages of cumulants are verified in experiments evaluating robustness (e.g. against operations like loss ' v compression. scaling and cropping) and discriminability. The results show an improved performance our met hod in comparison to existing methods. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1117/12.587708 | Proceedings of SPIE |
Keywords | Field | DocType |
cumulants,higher-order statistics,image fingerprinting,image retrieval | Feature vector,Pattern recognition,Fingerprint recognition,Computer science,Cryptographic hash function,Higher-order statistics,Image retrieval,Image processing,Hash function,Independent component analysis,Artificial intelligence | Conference |
Volume | ISSN | Citations |
5681 | 0277-786X | 6 |
PageRank | References | Authors |
0.72 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Longjiang Yu | 1 | 32 | 4.38 |
Martin Schmucker | 2 | 138 | 16.11 |
Christoph Busch | 3 | 140 | 12.82 |
Sheng-he Sun | 4 | 385 | 35.28 |