Local correspondence for detecting random forgeries

Progress on the problem of signature verification has advanced more rapidly in on-line applications than off-line applications, in part because information which can easily be recorded in on-line environments, such as pen position and velocity, is lost in static off-line data. In off-line applications, valuable information which can be used to discriminate between genuine and forged signatures is embedded at the stroke level. In this paper, we present an approach to segmenting strokes into stylistically meaningful segments and establish a local correspondence between a questioned signature and a reference signature to enable the analysis and comparison of stroke features. Questioned signatures which do not conform to the reference signature are identified as random forgeries. Most simple forgeries can also be identified, as they do not conform to the reference signature's invariant properties such as connections between letters. Since we have access to both local and global information, our approach also shows promise for extension to the identification of skilled forgeries.