U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Just Science Podcast: Episode 38: 2018 IPTES: Just Handwriting Statistics

NCJ Number
251591
Author(s)
Cami Fuglsby
Date Published
March 2018
Length
2 pages
Annotation

This episode of the Forensic Technology Center of Excellence's Just Science podcast series consists of an audio interview with Cami Fuglsby, from South Dakota State University, who discusses "Sufficiency and Complexity Factors in Handwriting Examination."

Abstract

Ms. Fuglsby recently received a masters degree under South Dakota University's Department of Mathematics and Statistics. Her thesis addressed the sufficiency of an automated handwriting verification system using various comparison methodologies. She reported on her research at the Joint Statistical Meetings and the International Conference on Forensic Inference and Statistics. The current interview focuses on the nature and findings of her thesis research. She notes that her selection of the thesis topic stemmed from her interest in the link between statistics and handwriting patterns. In her research, she examined the sufficiency (performance quality) of the Flash ID automated handwriting matching capabilities. The Flash ID focuses on a comparison of the shapes of letters used in documents being compared. Applying statistical analysis to Flash ID's performance in comparing handwriting samples, she determined that chance matches decreased with the length of the questioned sample (beyond 50-60 words) and with the complexity of the handwriting. A comparison between the accuracy of automated systems of handwriting analysis and that of experienced document examiners is suggested in the interview.