![]() ![]() This accuracy is significantly lower than the accuracy of rolled print to rolled print matching on a similar size database. ![]() ![]() Phase-I results showed that the best latent fingerprint matcher had an identification accuracy of 80 percent in identifying 100 latent images among a database of 10,000 rolled prints. NIST is conducting a multiphase project on Evaluation of Latent Fingerprint Technologies (ELFTs). On the other hand, the NIST latent fingerprint testing workshop reported that the rank-1 accuracy of an automatic latent matcher can be as low as 54 percent on a large database of more than 40 million subjects. The results of the Fingerprint Vendor Technology Evaluation (FpVTE) showed that the most accurate commercial fingerprint matchers achieved an impressive rank-1 identification rate of more than 99.4 percent on a database of 10,000 plain fingerprint images (see results of Medium Scale Test in ). Although tremendous progress has been made in improving the speed and accuracy of AFIS, these systems work extremely well only in scenarios where the matching is performed between rolled or plain fingerprint images. The system then outputs a short list of candidates that need to be examined by a latent examiner to determine if any of these fingerprint compar- isons is a match. In a Semi-Lights-Out System, some human intervention is allowed during feature extraction from a latent, e.g., orienting the fingerprint, marking the region of interest, etc. But, due to the limitations of the available algorithms, only “Semi-Lights-Out Systems” are feasible, especially for latent prints. Such a system should automatically extract features from query fingerprints (latents) and match them with a gallery database (rolled, plain, or even latent images) to obtain a set of possible “hits” with high confidence so that no human intervention is required. A Lights-Out System for fingerprint identification is characterized by a fully automatic (no human intervention) identification process. In order to deal with the throughput issue, the concept of “Lights-Out Systems” for latent matching has been introduced. One way to achieve this goal is to design an efficient and highly accurate automatic latent to rolled print matching system that is able to provide a quantitative estimate of the probability that two fingerprints being compared belong to the same finger. Therefore, it is very important that the cases sent to a latent examiner be carefully selected and prioritized so that he/she can spend an adequate amount of time in matching the fingerprint pairs. One of the causes for error is that latent examiners face a huge backlog of cases and are usually under time pressure to evaluate a fingerprint pair, particularly in high-profile cases. #SPENCER FINGERPRINT MAGNIFIER TRIAL#This is evident from a recent ruling of a Baltimore court which excluded fingerprints as evidence in a murder trial because the prosecutor was not able to justify the procedure followed in latent fingerprint matching as being sufficiently error free. These incidents and findings have undermined the importance of latent fingerprints as forensic evidence. Similar cases have been brought to light by the Innocence Project. One of the most high-profile cases in which an erroneous individualization was made involves Brandon Mayfield, who was wrongly apprehended in the 2004 Madrid train bombing incident after a latent fingerprint obtained from the bombing site was incorrectly matched with his fingerprint in the FBI’s IAFIS database. Erroneous individualizations are generally deemed as serious mis- takes, while erroneous exclusions are usually seen as less critical. On the other hand, the consequence of erroneous individualizations is that wrong- ful convictions of innocent people may occur. The consequence of erroneous exclusions is that criminals may not be apprehended. An erroneous individualization occurs when a latent print is incorrectly matched to the fingerprint of another subject by the latent examiner. An erroneous exclusion occurs when the mated fingerprint of the latent print is in the candidate list reviewed by the latent examiner, but the examiner fails to identify it. There are two types of errors a latent examiner can make: erroneous exclusion and erroneous individualization. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |