DOCUMENT IDENTIFICATION FOR COPYRIGHT PROTECTION USING CENTROID DETECTION

A way to discourage illicit reproduction of copyrighted or sensitive d ocuments is to watermark each copy before distribution, A unique mark is embedded in the text whose recipient is registered, The mark can be extracted from a possibly noisy illicit copy, identifying the registe red recipient, Most image marking techniques are vulnerable to binariz ation attack and, hence, not suitable for text marking, We propose a d ifferent approach where a text document is marked by shifting certain text lines slightly up or down or words slightly left or right from th eir original positions, The shifting pattern constitutes the mark and is different on different copies, In this paper we develop and evaluat e a method to detect such minute shifts, We describe a marking and ide ntification prototype that implements the proposed method, We present preliminary experimental results which suggest that centroid detection performs remarkably well on Line shifts even in the presence of sever e distortions introduced by printing, photocopying, scanning, and facs imile transmission.