Footwear impressions are one of the most frequently secured types of evidence at crime scenes. A part of the daily life of Forensic experts all over the world, is to assign the crime scene impression to a reference impression. Through this process, the noisy and incomplete evidence becomes a standardized information with outsole images, brand name, manufacturing time, etc. Since reference impression databases are contain thousands of data entries, that task is tedious and time consuming. Currently, no automated systems exist that can assess the similarity between a crime scene impression and reference impressions, due to the severe image degradations induced by the impression formation and lifting process.

The impression analysis task combines several challenging problems and therefore is at the heart of pattern recognition research. The main challenges here are the combination of unknown noise conditions with rigid transformations and missing data. Furthermore, training and testing data are scarce, because usually no or few crime scene impressions are available per reference impression. Additionally, in many cases no point-to-point correspondence exists between the impressions (see Figure above). Therefore, a higher level understanding of the pattern is necessary.


The database contains 170 samples of footwear impression evidence, that have been secured at crime scenes by forensic experts. The digital images were produced either by scanning gelatin lifters or by photographing the impression. Moreover, 1175 reference impressions are included in the database. The reference samples have been produced by applying gelatine lifters to the outsole of the reference shoe, followed by scanning the lifters. Thus, the data generating process is very similar for both types of impressions. The data is labeled, meaning that for each crime scene impression, the name of the corresponding reference impression is known.

The pattern recognition task can be stated as assessing the similarity between crime scene impressions and reference impressions.

The database can be downloaded at the following link: Crime Scene Footwear Impression Database
If you use the above data, please make sure to cite our paper (download forthcoming). The data is for research purposes only.


Unsupervised Footwear Impression Analysis and Retrieval from Crime Scene Data,
Adam Kortylewski, Thomas Albrecht, Thomas Vetter. ACCV 2014, Workshop on Robust Local Descriptors (download forthcoming)

In this work, we introduce an unsupervised image retrieval algorithm that overcomes the limitations of existing work by detecting and analyzing periodic patterns in the footwear impressions under unconstrained noise conditions. The basic idea behind our approach is that periodic structures are the most preserved information under unknown noise conditions because of their inherent redundancy.
We first extract the periodicity at each point in the impression evidence. Then, we compute Fourier features and use these to detect the periodic patterns. Finally, the periodic patterns are represented by the rotationally normalized Fourier features.


Please contact Adam Kortylewski if you have any questions or comments regarding this work or the database.


We thank the German State Criminal Police Offices and forensity AG for providing the data and supporting its publication.