Practical Implementation of Visual Hash Functions for CCTV Footage Authentication

1Citations
Citations of this article
2Readers
Mendeley users who have this article in their library.
Get full text

Abstract

This paper deals with practical implementation of semi-fragile watermarking for CCTV footage authentication. Despite the variety of available literature, certain important aspects remain unaddressed. The existing schemes are mostly evaluated against purely academic attacks, and the most practical attacks on information trust remain unaddressed. In this paper, we focus on the collage and the visually insignificant changes attacks, which are of critical importance in the video surveillance scenario. Based on a well-known robust hash function, we design three variants of a digital image authentication scheme. We show that the choice of the watermark embedding technique, although unaddressed in the literature, has critical influence on the tampering detection accuracy. Based on the performed evaluation, we also propose small modifications of the original algorithm, which lead to further improvement of the classification performance. © Springer-Verlag Berlin Heidelberg 2013.

Cite

CITATION STYLE

APA

Zarnowiec, K., Korus, P., Dziech, A., & Głowacz, A. (2013). Practical Implementation of Visual Hash Functions for CCTV Footage Authentication. In Communications in Computer and Information Science (Vol. 368 CCIS, pp. 309–323). Springer Verlag. https://doi.org/10.1007/978-3-642-38559-9_27

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free