CSAFE’s Latest Resources
Change cannot happen without community. CSAFE is passionate about achieving its mission to apply a statistically sound and scientifically solid foundation to the interpretation of forensic evidence. To that end, we invite fellow scientists and researchers, along with those in the forensic and legal communities, to use and share these resources as we work together to elevate forensic science and technology.
Knowledge Transfer
Found 345 Results
Page 2 of 35
Page 2 of 35
Page 2 of 35
Combining reproducibility and repeatability studies with applications in forensic science
Type: Publication Research Area(s): Forensic Statistics
Published: 2023 | By: Hina Arora
Studying the repeatability and reproducibility of decisions made during forensic examinations is important in order to better understand variation in decisions and establish confidence in procedures. For disciplines that rely on comparisons made by trained examiners such as for latent…
Reliability of ordinal outcomes in forensic black-box studies
Type: Publication Research Area(s): Forensic Statistics
Published: 2024 | By: Hina M. Arora
Forensic science disciplines such as latent print examination, bullet and cartridge case comparisons, and shoeprint analysis, involve subjective decisions by forensic experts throughout the examination process. Most of the decisions involve ordinal categories. Examples include a three-category outcome for latent…
Density-based matching rule: Optimality, estimation, and application in forensic problems
Type: Research Area(s): Forensic Statistics
Published: 2024 | By: Hana Lee
We consider matching problems where the goal is to determine whether two observations randomly drawn from a population with multiple (sub)groups are from the same (sub)group. This is a key question in forensic science, where items with unidentified origins from…
A finely tuned deep transfer learning algorithm to compare outsole images
Type: Publication Research Area(s): Footwear
Published: 2023 | By: Moonsoo Jang
In forensic practice, evaluating shoeprint evidence is challenging because the differences between images of two different outsoles can be subtle. In this paper, we propose a deep transfer learning-based matching algorithm called the Shoe-MS algorithm that quantifies the similarity between…
An automated alignment algorithm for identification of the source of footwear impressions with common class characteristics
Type: Publication Research Area(s): Footwear
Published: 2024 | By: Hana Lee
We introduce an algorithmic approach designed to compare similar shoeprint images, with automated alignment. Our method employs the Iterative Closest Points (ICP) algorithm to attain optimal alignment, further enhancing precision through phase-only correlation. Utilizing diverse metrics to quantify similarity, we…
A deep learning approach for the comparison of handwritten documents using latent feature vectors
Type: Publication Research Area(s): Forensic Statistics,Handwriting
Published: 2024 | By: Juhyeon Kim
Forensic questioned document examiners still largely rely on visual assessments and expert judgment to determine the provenance of a handwritten document. Here, we propose a novel approach to objectively compare two handwritten documents using a deep learning algorithm. First, we…
Likelihood ratios for changepoints in categorical event data with applications in digital forensics
Type: Publication Research Area(s): Digital,Forensic Statistics
Published: 2024 | By: Rachel Longjohn
We investigate likelihood ratio models motivated by digital forensics problems involving time-stamped user-generated event data from a device or account. Of specific interest are scenarios where the data may have been generated by a single individual (the device/account owner) or…
Interpretable algorithmic forensics
Type: Publication Research Area(s): Forensic Statistics,Implementation and Practice
Published: 2023 | By: Brandon Garrett
One of the most troubling trends in criminal investigations is the growing use of “black box” technology, in which law enforcement rely on artificial intelligence (AI) models or algorithms that are either too complex for people to understand or they…
Producing Datasets: Capturing Images on Multi-Camera Smartphones for Source Camera Identification
Type: Poster Research Area(s): Digital
Published: 2024 | By: Megan McGuire
This poster introduces the new CSAFE Multi-camera Smartphone Image Database and describes how the image were collected and reviewed.
The Impact of Zoom on Smartphone Camera Identification
Type: Poster Research Area(s): Digital
Published: 2024 | By: Gavin Norton
This poster explores the impact of digital zoom on source camera identification. Images were collected at 5 zoom magnifications using the telephoto cameras of ten iPhone 14 Pro smartphones.
Page 2 of 35
