Performance impact of ordinal ranking on content fingerprinting

Content fingerprinting provides a compact representation ofmultimedia objects for copy identification. This paper ana-
lyzes the impact of the ordinal-ranking based feature encod-
ing on the performance of content fingerprinting. Expressions
are derived for the identification performance of a fingerprint-
ing system with and without ordinal ranking. The analysis in-
dicates that when the number of features is moderately large,
ordinal ranking can improve the robustness of the fingerprint-
ing system to large distortions of the features and significantly
increase the probability of detection. These results enhance
understandings of ordinal ranking and provide design guide-
lines for choosing different system parameters to achieve a
desired identification accuracy.