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 various test sites.
Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data

Conference/Workshop:
106th International Association for Identification (IAI) Annual Educational Conference
106th International Association for Identification (IAI) Annual Educational Conference
Published: 2022
Primary Author: Andrew Lim
Secondary Authors: Danica Ommen
Type: Poster
Research Area: Handwriting
Related Resources
A statistical approach to aid examiners in the forensic analysis of handwriting
We develop a statistical approach to model handwriting that accommodates all styles of writing (cursive, print, connected print). The goal is to compute a posterior probability of writership of a…
CSAFE Project Update & ASCLD FRC Collaboration
This presentation highlighted CSAFE’s collaboration with the ASCLD FRC Collaboration Hub.
Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data
Identifying the source of handwriting is an important application in the field of forensic science that addresses questioned document evidence found in criminal cases and civil litigation. It is difficult,…
Quantifying Bayes Factors for Forensic Handwriting Evidence
Questioned Document Examiners (QDEs) are tasked with analyzing handwriting evidence to make source (or writership) determinations. The Center for Statistics and Applications of Forensic Evidence (CSAFE) has previously developed computational…