Analysis of Footwear Impression Evidence
Sargur N. Srihari
See also the instructional videos on "Footwear Impression Evidence"
Abstract
Impressions of footwear are commonly found in crime scenes. The quality and wide variability of these impressions and the large number of footwear outsole designs makes their manual analysis time-consuming and difficult. The goal of this research was to develop new computational methods that will eventually assist the forensic footwear examiner in the U.S. Two scenarios encountered by the forensic examiner were addressed: (i) in the investigative phase, to determine the source of an impression given a known set of outsole prints; which is useful in homicides and assaults where there are no known prints to match, and (ii) in the prosecutorial phase, to determine whether a particular impression evidence is from a known suspect’s shoe with a quantification of similarity and uncertainty. The research commenced with developing and acquiring representative footwear print images so that the algorithms developed would relate to the real problem encountered. Algorithms for several sub-problems were studied including image processing to improve the quality of the image for further automatic processing, extraction of features useful for discrimination, a measure of similarity between impressions and a content-based image retrieval system to reduce possible matches with knowns. The principal method pursued was one where the print is characterized as being composed of a pattern of geometric shapes, principally ellipses; with ellipses being able to represent straight line segments and circles as well. A distance measure based on comparing attribute relational graphs was developed. The retrieval system compares evidence features with pre-computed features of database entries and since comparison is time-consuming the database entries are clustered. Retrieval performance is better than that of other methods described in the literature, very few of which deal with real crime scene prints. Future research tasks are indicated including integration of the developed methods into a usable tool and a probabilistic measure of uncertainty in the verification task.