|
MEGAMATCHER ACCELERATOR
SOLUTION FOR LARGE-SCALE AFIS OR MULTI-BIOMETRIC SYSTEMS
MegaMatcher Accelerator is a hardware/software solution that provides high speed, high volume biometric identification for national-scale projects.
The Extreme and Extended versions are designed to run on server hardware and perform fast biometric template matching on the server-side of a large-scale AFIS or multi-modal system. The Standard version and Development Edition are intended to be run on a common PC. MegaMatcher Accelerator software licenses are available for new and existing MegaMatcher Extended SDK customers.
MEGAMATCHER加速器
针对大型AFIS或多模态生物识别系统的解决方案
MegaMatcher加速器是一种硬件/软件解决方案，为国家规模的项目提供高速、高容量的生物特征识别。
这个极端和扩展版本被设计为运行在服务器硬件并在大型AFIS或多模式系统的服务器端执行快速生物识别模板匹配。这个标准版本和开发版可在普通PC机上运行。MegaMatcher加速器软件许可将提供给新的和现有的MegaMatcher扩展版SDK客户。
FEATURES AND CAPABILITIES
- Proven in national-scale projects, including voter registration and national ID.
- Available as a ready-to-use biometric solution with server hardware
or as biometric software that will run on server hardware or a common PC.
- Up to 1,200,000,000 fingerprints or 1,200,000,000 faces or 700,000,000 irises per second matching speed on a single unit.
- Fingerprint, iris, face and voice modalities supported.
- Scalable cluster architecture.
- Support for ISO & ANSI fingerprint template standards.
- Suitable for duplicates search.
产品特点和功能
- 在国家级项目中得到验证，包括选民登记和国民身份证系统。
- 可提供包括服务器硬件的即买即用生物识别解决方案，或者只是在服务器硬件或普通PC上运行的生物识别软件。
- 在一个硬件上，每秒匹配速度即可高达12亿枚指纹、12亿张人脸或7亿个虹膜。
- 支持指纹，虹膜，面部和声音四种识别模式。
- 可扩展的簇体系结构。
- 支持ISO和ANSI指纹模板标准。
- 适合查重搜索。
MegaMatcher Accelerator is availalble in these editions:
MegaMatcher Accelerator software provides these capabilities for biometric identification:
- Fast matching. A single MegaMatcher Accelerator 11.0 Extreme unit can match up to 1.2 billionfingerprints per second or up to 700 million irises per second or up to 1.2 billion faces per second in 1-to-many mode using the Neurotechnology proprietary biometric template format. A single MegaMatcher Accelerator 11.0 Extended unit can match up to 100 million fingerprints per second or up to 200 million irises per second or up to 100 million faces per second in 1-to-many mode. A PC with MegaMatcher Accelerator 11.0 Standard software can match up to 35 million fingerprints per second or up to 70 million irises per second or up to 35 millionfaces per second in 1-to-many mode.
- Multiple modalities support. MegaMatcher Accelerator 11.0 can be used within a biometric system that contains templates with any number of fingerprint, iris, face and/or voiceprint records.
- Full database search. The biometric engines included in MegaMatcher Accelerator do not perform internal database indexing or pre-classification (by fingerprint type, eye color etc) thus avoiding false rejections when incorrect classifiers appear. This way the whole database is scanned comprehensively during every matching request and very low false rejection ensured. On the other hand, integrators may use non-biometric classifiers like gender or a country's region to optimize system size.
- Optimal system size. A system based on the MegaMatcher Accelerator 11.0 solution can be configured to perform fast candidate selection using irises and/or faces and/or several fingerprints, and then use other biometric modalities to validate selection results. This approach allows the system to reach optimal matching speed and reliability while keeping the overall system cost within the defined limits.
- ISO & ANSI standards support. MegaMatcher Accelerator allows the use of ANSI and ISO biometric standards for fingerprint templates.
- Scalable architecture. Multiple MegaMatcher Accelerator units can be combined together in a cluster for higher matching speed. For example, a cluster of 4 MegaMatcher Accelerator 11.0 Extended units would enable matching at a rate of about 108 million templates per second (when a template contains 4 fingerprint records), a cluster of 10 units – about 270 million templates per second, and so on. No additional cluster software is required, as MegaMatcher Accelerator includes all the necessary software which is easily managed through a web interface.
- Suitable for duplicates search. Searching for duplicates in a biometric template database is a task that requires many computations, as each biometric template needs to be verified with every other template in the database. MegaMatcher Accelerator provides enough speed to complete duplicate searching in a reasonable time. Scalable architecture allows the combination of several MegaMatcher Accelerator units for tasks involving larger databases.
MegaMatcher加速器可提供下列版本：
MegaMatcher加速器软件提供以下生物识别性能：
- 快速匹配。一个超级匹配加速器11.0极限单位可以匹配多达12亿指纹每秒或至多每秒7亿虹膜每秒或至多每秒12亿脸每秒1对多模式使用神经技术专有生物特征模板格式.单个MegaMatcher加速器11.0扩展单元可匹配多达1亿指纹每秒或至多每秒2亿虹膜每秒或至多每秒1亿脸每秒1对多模式。配有MegaMatcher加速器11.0标准软件的PC机可与之匹配3500万指纹每秒或至多每秒7000万虹膜每秒或至多每秒3500万脸每秒1对多模式。
- 多模式支持。MegaMatcher加速器11.0可用于生物识别系统，其中包含有任意数量的指纹、虹膜、面部和/或声纹记录的模板。
- 全数据库搜索MegaMatcher加速器中包含的生物识别引擎不执行内部数据库索引或预分类(通过指纹类型、眼睛颜色等)，从而避免了错误分类器出现时的错误拒绝。这样，在每次匹配请求时，对整个数据库进行了全面的扫描，保证了极低的误拒绝率。另一方面，集成商可能使用非生物特征分类器，如性别或一个国家的地区，以优化系统的规模。
- ******系统规模基于MegaMatcher加速器11.0解决方案的系统可以配置为使用虹膜和/或人脸和/或几个指纹执行快速候选选择，然后使用其他生物识别模式验证选择结果。该方法使系统达到最优匹配速度和可靠性，同时使系统总成本保持在规定的范围内。
- ISO和ANSI标准支持。MegaMatcher加速器允许使用ANSI和ISO生物识别标准作为指纹模板。
- 可扩展架构多个MegaMatcher加速器单元可以合并在一个簇为了更高的匹配速度。例如，一个由4个MegaMatcher加速器11.0扩展单元组成的集群将能够以每秒1.08亿个模板(当模板包含4个指纹记录)、10个单元(每秒约2.7亿个模板)的速度进行匹配，等等。不需要额外的集群软件，因为MegaMatcher加速器包括所有必要的软件，这些软件很容易通过Web接口管理。
- 适合查重搜索。在生物识别模板数据库中搜索副本是一项需要多次计算的任务，因为每个生物识别模板都需要与数据库中的每个其他模板进行验证。MegaMatcher加速器提供足够的速度在合理的时间内完成重复搜索。可伸缩架构允许将多个MegaMatcher加速器单元组合用于涉及较大数据库的任务。
|
