Semester

Spring

Date of Graduation

2023

Document Type

Thesis

Degree Type

MS

College

Eberly College of Arts and Sciences

Department

Mathematics

Committee Chair

Marjorie Darrah

Committee Member

Harvey Diamond

Committee Member

Jacqueline Speir

Abstract

Forensic footwear impression analysis is a valuable tool in criminal investigations. Extracting useful features from images of footwear impressions is a critical step in this process. However, the quality of these images can vary widely, making feature extraction challenging. In order to give a quality assessment rating to a footwear impression image, the image should first be analyzed to extract features from the impression. In this paper, we present a method to extract features from a 2D grayscale footwear impression image. A Hierarchical Grid Model implementation has been adapted from use on a 3D dataset to assist in finding features, referred to as lugs for footwear, of a 2D grayscale image of a footwear impression. Depending on the number of lugs found by the grid search, the image is assigned a quality rating to determine the likelihood of promising results from further analysis. Quality ratings range from high, good, moderate, low, and poor. We evaluated the performance of our method using a data set of footwear impression images with varying quality. Our results show that the proposed method is effective in extracting useful features from footwear impressions and provides quantitative results indicating agreement with ground truth. Our proposed method offers a solution for extracting features from footwear impression images with varying quality, providing an efficient and reliable tool for forensic investigations.

Share

COinS