Towards Similarity Models in Police Photo Lineup Assembling Tasks
Photo lineups play a significant role in the eyewitness identification process. Lineups are used to provide evidence in the prosecution and subsequent conviction of suspects. Unfortunately, there are many cases where lineups have led to the incorrect identification and conviction of innocent suspects. One of the key factors affecting the incorrect identification is the lack of lineup fairness, i.e. that the suspect differs significantly from other candidates. Although the process of assembling a fair lineup is both highly important and time-consuming, only a handful of tools are available to simplify the task.
In this paper, we follow our previous work in this area and focus on defining and tuning the inter-person similarity metric that will serve as a base for a lineup candidate recommender system. This paper proposes an inter-person similarity metric based on DCNN descriptors of candidates’ photos and their content-based features, which is further tuned by the feedback of domain experts. The recommending algorithm further considers the need for uniformity in lineups. The proposed method was evaluated in a realistic user study focused on lineup fairness over solutions proposed by domain experts.
Results shown indicate that the precision of the proposed method is similar to the solutions proposed by domain experts and therefore the approach may significantly reduce the amount of manual work needed for assembling photo lineups.
KeywordsPhoto lineups Recommender systems Inter-person similarity
This work was supported by the Czech grants GAUK-232217 and GACR-17-22224S. Source codes and raw results are available from github.com/lpeska/LineRec.
- 2.Carbonell, J., Goldstein, J.: The use of MMR, diversity-based reranking for reordering documents and producing summaries. In: 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1998 (1998)Google Scholar
- 4.Gatys, L.A., et al.: Image style transfer using convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
- 5.Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 2015 International Conference on Learning Representations, pp. 1–15 (2015)Google Scholar
- 10.Parkhi, O.M., et al.: Deep face recognition. In: 2015 Proceedings of the British Machine Vision Conference (2015)Google Scholar
- 11.Peska, L., Trojanova, H.: Towards recommender systems for police photo lineup. In: ACM International Conference Proceeding Series (2017)Google Scholar
- 15.Valentine, T.R., et al.: How can psychological science enhance the effectiveness of identification procedures? An international comparison. Public Interest Law Report (2007)Google Scholar