Automatic Recognition of Partial Shoeprints Using a Correlation Filter Classifier

In this work we investigate the performance of Advanced Correlation Filters (ACFs) in the automatic classification of partial shoeprints for use in forensic science. In particular, the Optimum Trade-off Synthetic Discriminant Function (OTSDF) filter is used to match low quality partial shoeprints. Experiments were conducted on a database of images of 100 different shoes available on the market. For experimental evaluation, test images including different perturbations such as noise addition, blurring and in-plane rotation were generated. Results have shown that advanced correlation filters can provide attractive performance and outperform the existing methods when processing distorted partial prints.