Detection of Forged Handwriting Using a Fractal Number Estimate of Wrinkliness

1. Detection of Forged HandwritingUsing a Fractal Number Estimate of Wrinkliness • Experts are required to differentiate between authentic and forged signatures • Important to develop an objective system to identify forged handwriting, or at least to identify those handwritings that are likely to be forged • Key idea – it seems reasonable that successful forgers often replicate handwriting shape and size by carefully copying or tracing the authentic handwriting

2. Hypotheses • Good forgeries – those that retain the shape and size of authentic writing – tend to be written more slowly and carefully than authentic writing • Good forgeries are likely to be wrinklier (less smooth) than authentic handwriting

3. Methodology • Collected online handwriting samples and then digitally scanned them • 10 subjects: 3 authentic + 3*9 forgery samples • The x-y coordinates of the online samples were used to calculate the speed of the handwriting. • The samples were digitally scanned at two different resolutions to calculate a fractal number estimate of the wrinkliness of the writing • Employed the IBM Transnote, pen-enabled notebook computer and associated SDK

4. Results • Writing speed of good forgeries was significantly slower than that of the authentic writings (p = 10-8) • Wrinkliness of the good forgeries was significantly greater than that of the authentic writings (p = 0.02) • Therefore, it is possible to identify candidate forgeries from scanned documents