Slantlet Transform-based Image Fingerprints

L. Yu and S. Sun (PRC)

Keywords

Slantlet transform, image fingerprints, image authentication, contentbased retrieval

Abstract

Image fingerprints are 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. In addition applied in authentication and tamper detection as traditional digital signatures, image fingerprinting technique is used in content-based retrieval, content-based monitoring, and content-based filtering. In this paper we present a slantlet transform based method for image fingerprints. The slantlet transform is a kind of orthogonal wavelet and performs better in data compression than discrete cosine transform and the other wavelets. Phase information is extracted from slantlet domain for image fingerprints. Better performance is verified in experiments evaluating robustness (e.g. against operations like lossy compression, scaling and cropping) and discriminability in comparison to an existing method.

Important Links:



Go Back