One of the biggest obstacles to developing quantitative and probabilistic methods for footwear impression evidence is that gathering data on the reference population or populations is incredibly difficult — the footwear changes as new shoes are released, but also due to weather, geography and other factors.
Researchers from the Center for Statistics and Applications in Forensic Evidence (CSAFE) are addressing these challenges by developing and deploying a shoe scanning device called the Modeling And iNventory of Tread Impression System, also known as MANTIS.
The MANTIS shoe scanning device addresses a critical gap in forensic tools available in the United States and the need for complete databases of footwear treads and upper soles. Currently, no other shoe scanning devices exist that can effectively function outdoors in real-time. MANTIS is designed to capture high-quality scans of shoes as individuals walk across the device. It can identify specific characteristics found on shoe soles, providing valuable insights into the origin of the shoes, where and how they are worn and the people who wear them.
The development of the shoe scanner was led by Richard Stone, associate professor of industrial and manufacturing systems engineering at Iowa State University; Braden Westby and Nell Jaskowiak, Iowa State graduate students in industrial engineering; and former Iowa State graduate student Colten Fales.
MANTIS was deployed in 2021 on the Iowa State campus in Ames, Iowa, to assess its capabilities and collect footwear scans. The research team found that MANTIS could effectively operate in all seasons, weather conditions, and temperatures. It was capable of capturing usable upper sole and tread patterns, regardless of external lighting conditions. This functionality enabled the scanner to log different shoe types and provide insights into the manufacturer, shoe model, and style of shoes worn in various seasons by the regional population.
So far, the researchers have collected over 7,000 images in just under three years of operation. The shoe images were transferred to an encrypted database, where they were utilized in an advanced algorithm designed to identify patterns based on the individual characteristics of the shoes. The development of the machine-learning model is led by Susan VanderPlas, an associate professor of statistics at the University of Nebraska-Lincoln.
The research team is already planning on making improvements to MANTIS by creating smaller, easier-to-use systems. They are also looking at installing the scanning device in-ground to reduce the effort required to walk over the scanner, which should help increase the number of scans collected.
In September, the researchers presented a retrospective on the development of the MANTS shoe scanning system at the 2024 Human Factors and Ergonomics Society (HFES) International Annual Meeting. A journal article was also published in the Proceedings of the HFES Annual Meeting.
The MANTIS project was partly funded by a grant from the National Institute of Justice, with additional support provided by CSAFE.
For more information about the MANTIS Shoe Scanning System, check out this CSAFE Learning on-demand webinar: “Modeling and Inventory of Tread Impression System (MANTIS): The development, deployment and application of an active footwear data collection system,” presented by Richard Stone.
