The goal of this presentation is to provide insights into which features of handwritten documents are important for statistical
modeling with the task of writer identification and to discuss how these features overlap with features that questioned document examiners typically
examine.
An Exploratory Analysis of Handwriting Features: Investigating Numeric Measurements of Writing That Are Important for Statistical Modeling
Conference/Workshop:
American Academy of Forensic Sciences Annual Scientific Meeting
American Academy of Forensic Sciences Annual Scientific Meeting
Published: 2019
Primary Author: Amy Crawford
Secondary Authors: Alica L. Carriquiry, Danica Ommen
Type: Presentation Slides
Research Area: Handwriting
Related Resources
Comparing handwriter and FLASH ID®, Two Handwriting Analysis Programs
FLASH ID and handwriter are computer programs that compare questioned handwritten documents against handwritten samples from known writers. FLASH ID was developed by Sciometrics and is used by the FBI,…
Error Rate Methods for Forensic Handwriting Identification
Presentation is from the 106th International Association for Identification (IAI) Annual Educational Conference
Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data
Primary goals are to examine: 1. Write diversification versus representation. 2. Preservation of handwriting structure versus image density. 3. Input size versus training size. 4. Writer identification complexity assessment using…
Center for Statistics and Application in Forensic Evidence Update
The information below highlights a sample of current research initiatives led by the CSAFE team. Additional accomplishments in other forensic science disciplines will be discussed in subsequent issues of Forensic…