TY - JOUR
T1 - Modeling and Analysis of Correlated Binary Fingerprints for Content Identification
JF - Information Forensics and Security, IEEE Transactions on
Y1 - 2011
A1 - Varna,A.L.
A1 - M. Wu
KW - alarm
KW - approach;user
KW - binary
KW - computing;
KW - content
KW - criterion;Markov
KW - decision
KW - DETECTION
KW - detector;statistical
KW - distance
KW - fields;content
KW - filtering;content
KW - filtering;multimedia
KW - fingerprinting
KW - fingerprints;detection
KW - generated
KW - Hamming
KW - identification;correlated
KW - identification;optimal
KW - inspired
KW - likelihood
KW - Physics
KW - probability;false
KW - probability;log
KW - processes;Web
KW - random
KW - ratio
KW - rule;multimedia
KW - schemes;multimedia
KW - sites;information
KW - Websites;Markov
AB - Multimedia identification via content fingerprints is used in many applications, such as content filtering on user-generated content websites, and automatic multimedia identification and tagging. A compact #x201C;fingerprint #x201D; is computed for each multimedia signal that captures robust and unique properties of the perceptual content, which is later used for identifying the multimedia. Several different multimedia fingerprinting schemes have been proposed in the literature and have been evaluated through experiments. To complement these experimental evaluations and provide guidelines for choosing system parameters and designing better schemes, this paper develops models for content fingerprinting and provides an analysis of the identification performance under these models. As a first step, bounds on the identification accuracy and the required fingerprint length for the simplest case when the fingerprint bits are modeled as i.i.d. are summarized. Markov Random Fields are then used to address more realistic settings of fingerprints with correlated components. The optimal likelihood ratio detector is derived and a statistical physics inspired approach for computing the probability of detection and probability of false alarm is described. The analysis shows that the commonly used Hamming distance detection criterion is susceptible to correlations among fingerprint bits, whereas the optimal log-likelihood ratio decision rule yields 5-20% improvement in the accuracy over a range of correlations. Simulation results demonstrate the validity of the theoretical predictions.
VL - 6
SN - 1556-6013
CP - 3
M3 - 10.1109/TIFS.2011.2152394
ER -