Poster

Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data

July 12, 2023 / Poster / Forensic Statistics, Handwriting

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

July 12, 2023 / Poster / Forensic Statistics, Handwriting

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

Quantifying Writer Variance Through Rainbow Triangle Graph Decomposition of the Common Word “the”

July 12, 2023 / Poster / Forensic Statistics, Handwriting

Handwriting comparative analysis is based on the principle that no two individuals can produce the same writing and that an individual cannot exactly reproduce his/her handwriting. This project aims to

A Likelihood Ratio Approach for Detecting Behavioral Changes in Device Usage Over Time

July 12, 2023 / Poster / Digital

This work focuses on the situation in which investigators have obtained as evidence logs of user-generated activities on a device, such as sending text messages or emails, opening or interacting

A Data-Driven Approach to Model the Generation Process of Bloodstain Patterns

November 30, 2022 / Poster / Bloodstain

This poster was presented at the 106th International Association for Identification

A Pipeline for Cartridge Case Comparisons

November 30, 2022 / Poster / Firearms and Toolmarks

We introduce novel sub-procedures in the pre-processing, comparison and similarity feature steps. The sub-procedures result in an improved error rate compared to our implementation of the CMC method while also

Jury Perception of Bullet Matching Algorithms and Demonstrative Evidence

November 30, 2022 / Poster / Implementation and Practice

Presented at Joint Statistical Meetings

Ensemble of SLR systems for forensic evidence

November 29, 2022 / Poster / Forensic Statistics

Machine learning-based Score Likelihood Ratios have been proposed as an alternative to traditional Likelihood Ratio and Bayes Factor to quantify the value of forensic evidence. Scores allow formulating comparisons using

Likelihood Ratios for Categorical Evidence with Applications to Digital Forensics

November 29, 2022 / Poster / Digital, Forensic Statistics

In forensic investigations, the goal of evidence evaluation is often to address source-/identity-based questions in which the evidence consists of two sets of observations: one from an unknown source tied

Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data

November 29, 2022 / Poster / Handwriting

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

« Prev 1 2 Next »

Poster

Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data

Quantifying Bayes Factors for Forensic Handwriting Evidence

Quantifying Writer Variance Through Rainbow Triangle Graph Decomposition of the Common Word “the”

A Likelihood Ratio Approach for Detecting Behavioral Changes in Device Usage Over Time

A Data-Driven Approach to Model the Generation Process of Bloodstain Patterns

A Pipeline for Cartridge Case Comparisons

Jury Perception of Bullet Matching Algorithms and Demonstrative Evidence

Ensemble of SLR systems for forensic evidence

Likelihood Ratios for Categorical Evidence with Applications to Digital Forensics

Twin Convolutional Neural Networks to Classify Writers Using Handwriting Data

Our new learning platform

Partially Funded by