RESUMO
The purpose of this work is to critically analyse the aspects connected both with the measurement of error rates and with the design of proficiency tests and collaborative exercises in the fingerprint domain. All from the dual perspective of practitioners and organizers of PT's/CE's. A thorough analysis of the types of errors, of the methods to infer them through black-box studies and PT's/CE's is carried out, and the limits to the generalization of error rates are described, providing insightful indication on how to design PT's/CE's in the fingerprint domain, which are aimed to represent the complexity of casework.
RESUMO
In 2017 the Fingerprint Working Group (EFP-WG) of the European Network of Forensic Science Institutes (ENFSI) undertook a collaborative exercise (CE) with the aim of assessing the use of ninhydrin as a fingermark development technique in the laboratory. The test was prepared and managed by the officially established advisory group. The characteristics of the CE are summarised. The results indicate that ninhydrin is a robust methodology. Unexpected negative outcomes have been outlined and discussed, followed by an overview of the knowledge that has been gained.
RESUMO
Face recognition systems aim to recognize the identity of a person depicted in a photograph by comparing it against a gallery of prerecorded images. Current systems perform quite well in controlled scenarios, but they allow for none or little interaction in case of mistakes due to the low quality of images or to algorithmic limitations. Following the needs and suggestions of investigators, we present a guided user interface that allows to adjust from a fully automatic to a fully assisted modality of execution, according to the difficulty of the task and to amount of available information (gender, age, etc.): the user can generally rely on automatic execution and intervene only on a limited number of examples when a failure is automatically detected or when the quality of intermediate results is deemed unsatisfactory. The interface runs on top of a preexistent automatic face recognition algorithm in such a way to guarantee full control over the execution flow and to exploit the peculiarities of the underlying image processing techniques. The viability of the proposed solution is tested on a classic face identification task run on a standard publicly available database (the XM2VTS), assessing the improvement to user interaction over the automatic system performance.