Duplicate document detection by template matching

We discuss some operational issues pertaining to the detection of duplicate s in the databases of bitmapped binary document images, and reason that eff icient and effective duplicate document detection probably needs a combinat ion of an efficient primary detector and an effective subordinate detector to be achieved. An algorithm that executes binary pattern template matching by cross-correlation is proposed as a duplicate document detection methodo logy. The template matching operation is amenable to pixel-parallel computa tion on serial architecture computers by bitwise integer operations. A desc ription of the algorithm is accompanied by a discussion of issues that aris e in its practical implementation. Duplicate detection by template matching is especially well suited to facsimile (i.e. fax) databases, in particular for detecting the single feed-multiple transmissions that often dominate t he occurrence of duplicates in fax databases. Detailed experimental results presented for fax documents demonstrate that template matching is suitable as both a primary detector when conducted with small template and search a rea sizes, and a subordinate detector when conducted with moderate template and search area sizes. (C) 2000 Elsevier Science B.V. All rights reserved.