Validation of Individuality of HandwritingDichotomy 手写体个性的验证.pptVIP

Automatic Detection of Handwriting forgery * ? S. Cha 8/8/2002 CSIS Dr. Sung-Hyuk Cha Dr. Charlies C. Tappert School of Computer Science Information Systems Analysis of Handwriting Recognition Examination Personality identification (Graphology) On-line Off-line Writer Verification Writer Identification Natural Writing Forgery Disguised Writing Handwriting Analysis Taxonomy Background Differences b/w authentic handwriting forgery Measure of Wrinkliness Automatic Forgery Detection Model Conclusion Overview To determine the Validity of Individuality in Handwriting Legal Motivation Frye vs. US (1923) scientific community Daubert vs. Merrell Dow (1993) testing, peer review, error rates U.S. vs. Starzecpyzel (1995) “skilled” testimony GE vs. Joiner (1997) weight of evidence Kumho vs.Carmichael (1999) reliability standard Each person writes differently. Individuality of Handwriting (b) Forgeries of (a) (a) Authentic handwriting samples from one writer Authentic vs. Forgeries 3 Differences b/w authentic forgery 1. Shape 2. Pressure 3. Speed Angular and Magnitude Type Element String Angular Magnitude Image Stroke Direction Stroke Width w1 w2 w3 w4 w5 w6 w7 5 3 6 5 4 5 5 min(wi) = 3 w1 w2 w3 w4 w5 w6 w7 w8 w9 w10 4.24 4.24 4.24 4.24 2.83 4.24 4.24 2.83 2.83 2.83 min(wi) = 2.83 Stroke Width Extraction (a) Vertical horizontal stroke width (b) Diagonal stroke width Fractal: How Long is a Coastline? Fractal: How wrinkly is the Coastline of Britain? (a) Number of in the boundary = 69 (b) Number of in the boundary = 32 (a) (b) Fractal: How wrinkly is Handwriting? Fractal: Measure of Wrinkliness (d-e) ascender descender Computational Features (f) stroke width (g-i) projected histogram and gradient histogram Computational Features sample1 by x sample2 by x sample1 by x Forgery of x by y Feature Extractor Distance computing d-dimensional within-authentic- handwriting distance set d-dimensional between-authentic- handwriting fo