ELFT-EFS Evaluation of Latent Fingerprint Technologies: Extended Feature Sets [Evaluation #2]
ELFT-EFS Evaluation of Latent Fingerprint Technologies: Extended Feature Sets [Evaluation #2]
复制标题
潜在指纹技术的 ELFT-EFS 评估：扩展功能集 [评估
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
G. Kiebuzinski
中科院分区：
文献类型：
--
作者：
M. Indovina;V. Dvornychenko;R. A. Hicklin;G. Kiebuzinski
美国国家标准与技术研究院（NIST）潜在指纹技术扩展特征集（ELFT-EFS）评估由多个正在进行的潜在算法评估组成。本报告描述了ELFT-EFS评估#2的结果和结论;除了自动特征提取和匹配（AFEM）外，还使用经验丰富的人类潜在指纹检查员标记的特征进行潜在指纹搜索的准确性测试。ELFT-EFS评估#1是对潜在指纹匹配器的第一次评估，其中来自不同供应商的系统使用通用的标准化功能集。ELFT-EFS评估#2使用更新的匹配器重复相同的测试。结果表明，在大多数情况下，匹配器使用图像加上手动标记的扩展特征（EFS）作为有效和可互操作的特征集的能力比评估#1结果有可测量的改进。考虑到结果来自早期开发的匹配器，使用EFS特征搜索时的准确性是有希望的。使用下一代匹配器的进一步研究是必要的，以确定EFS可能的性能增益。ELFT-EFS评价#2最终报告
The National Institute of Standards and Technology (NIST) Evaluation of Latent Fingerprint Technologies Extended Feature Sets (ELFT-EFS) consists of multiple ongoing latent algorithm evaluations. This report describes the results and conclusions of ELFT-EFS Evaluation #2; an accuracy test of latent fingerprint searches using features marked by experienced human latent fingerprint examiners, in addition to automatic feature extraction and matching (AFEM). ELFT-EFS Evaluation #1 was the first evaluation of latent fingerprint matchers in which systems from different vendors used a common, standardized feature set. ELFT-EFS Evaluation #2 repeats the same tests using updated matchers. The results show that in most cases there were measureable improvements in the ability of matchers to use images plus manually marked Extended Features (EFS) as an effective and interoperable feature set over the Evaluation #1 results. The accuracy when searching with EFS features is promising considering the results are derived from earlydevelopment matchers. Further studies using next-generation matchers are warranted to determine the performance gains possible with EFS. ELFT-EFS Evaluation #2 Final Report