Development of a systematic computer vision-based method to analyse and compare images of false identity documents for forensic intelligence purposes-Part I: acquisition, calibration and validation issues

Following their detection and seizure by police and border guard authorities, false identity and travel documents are usually scanned, producing digital images. This research investigates the potential of these images to classify false identity documents, highlight links between documents produced by a same modus operandi or same source, and thus support forensic intelligence efforts. Inspired by previous research work about digital images of Ecstasy tablets, a systematic and complete method has been developed to acquire, collect, process and compare images of false identity documents. This first part of the article highlights the critical steps of the method and the development of a prototype that processes regions of interest extracted from images. Acquisition conditions have been fine-tuned in order to optimise reproducibility and comparability of images. Different filters and comparison metrics have been evaluated and the performance of the method has been assessed using two calibration and validation sets of documents, made up of 101 Italian driving licenses and 96 Portuguese passports seized in Switzerland, among which some were known to come from common sources. Results indicate that the use of Hue and Edge filters or their combination to extract profiles from images, and then the comparison of profiles with a Canberra distance-based metric provides the most accurate classification of documents. The method appears also to be quick, efficient and inexpensive. It can be easily operated from remote locations and shared amongst different organisations, which makes it very convenient for future operational applications. The method could serve as a first fast triage method that may help target more resource-intensive profiling methods (based on a visual, physical or chemical examination of documents for instance). Its contribution to forensic intelligence and its application to several sets of false identity documents seized by police and border guards will be developed in a forthcoming article (part II).

Marketing territorial et branding territorial : une revue de littérature systématique

Le présent article offre un aperçu systématique et complet de la littérature scientifique dédiée au domaine d'étude du marketing territorial et du branding territorial. 1172 contributions publiées entre 1976 et 2016 dans 98 revues différentes y sont analysées à l'aide d'un classement méticuleux dans des catégories et sous-catégories en fonction de l'approche disciplinaire, de la méthode utilisée et de la perspective adoptée. Cette revue de la littérature permet ainsi une vue d'ensemble détaillée de l'état de l'art et fait part des diverses tendances et évolutions concernant ce domaine d'étude en émergence. Elle atteste, entre autres, l'existence d'un flou conceptuel, de définitions divergentes et de faibles assises théoriques : ce qui contribue à un spectre très large d'objets d'étude. Un manque de preuves empiriques et de contributions à caractère explicatif est également observé : les nombreux postulats sur les effets des activités de marketing territorial par rapport à l'attractivité restent à démontrer. Elle souligne aussi un certain désintérêt de la littérature pour le contexte politico-institutionnel dans lequel les territoires s'inscrivent, pourtant crucial en termes de management public. Par ailleurs, ce travail souligne la place importante attribuée à la rhétorique des consultants, avec la publication d'une grande quantité de contributions normatives dans une optique de partage de bonnes pratiques. Pour finir, cette étude constate la présence d'un nombre significatif d'articles critiques.

Image processing of false identity documents for forensic intelligence

Forensic intelligence has recently gathered increasing attention as a potential expansion of forensic science that may contribute in a wider policing and security context. Whilst the new avenue is certainly promising, relatively few attempts to incorporate models, methods and techniques into practical projects are reported. This work reports a practical application of a generalised and transversal framework for developing forensic intelligence processes referred to here as the Transversal model adapted from previous work. Visual features present in the images of four datasets of false identity documents were systematically profiled and compared using image processing for the detection of a series of modus operandi (M.O.) actions. The nature of these series and their relation to the notion of common source was evaluated with respect to alternative known information and inferences drawn regarding respective crime systems. 439 documents seized by police and border guard authorities across 10 jurisdictions in Switzerland with known and unknown source level links formed the datasets for this study. Training sets were developed based on both known source level data, and visually supported relationships. Performance was evaluated through the use of intra-variability and inter-variability scores drawn from over 48,000 comparisons. The optimised method exhibited significant sensitivity combined with strong specificity and demonstrates its ability to support forensic intelligence efforts.