Abstract
Photo lineups play a significant role in the eyewitness identifica-tion process. This method is used to provide evidence in the prosecution and subsequent conviction of suspects.
Unfortu-nately, there are many cases where lineups have led to the con-viction of an innocent suspect. One of the key factors affecting the incorrect identification of a suspect is the lack of lineup fair-ness, i.e. that the suspect differs significantly from all other candidates.
Although the process of assembling fair lineup is both highly important and time-consuming, only a handful of tools are available to simplify the task. In this paper, we describe our work towards using recommend-er systems for the photo lineup assembling task.
We propose and evaluate two complementary methods for item-based rec-ommendation: one based on the visual descriptors of the deep neural network, the other based on the content-based attrib-utes of persons. The initial evaluation made by forensic technicians shows that although results favored visual descriptors over attribute-based similarity, both approaches are functional and highly diverse in terms of recommended objects.
Thus, future work should in-volve incorporating both approaches in a single prediction method, preference learning based on the feedback from forensic technicians and recommendation of assembled lineups instead of single candidates.