Face saving software

Face recognition processing requires a real-time database with a small and powerful memory.

Face storage database software: problem and solution

Face saving software problem:

Facial recognition technology inherently works with dense data; to identify a person, a system must take millions of precise measurements, compare them to a facial template stored several megabytes in size, and instantly allow or access to cancel

solution:

A real-time database system with a small memory footprint can perform sensitive diagnostics. Storage options in main memory or flash give product designers the flexibility to configure storage based on desired performance, cost, and form factor.

Understanding the needs of enterprise applications

Choosing a combination of commercially available real-time database hardware and software is a decision that almost every embedded systems designer must make. Especially when designing facial recognition systems, engineers use database products that meet the various needs of embedded systems used in real-time enterprise applications. L-1 Identity Solutionsí Bioscrypt Division has partnered with McObject and Texas Instruments (TI) to address the challenges of creating a facial recognition system. Bioscrypt developed a small, high-performance face reader product using the McObject eXtremeDB Fusion embedded database with a TI TMS320DM6446 digital media processor.

The VisionAccess 3D face reader can store up to 60,000 facial patterns and verify a person's identity in less than a second. The system performs key computing tasks including image processing and face detection and matching on the device, eliminating the industrial server behind it.

The use of embedded platform saves transportation costs, reduces installation complexity in minimum space. For example, this security technology has been successfully deployed in high-traffic workplaces such as the Venetian Macao-Resort Hotel in Asia, which uses facial readers to authenticate its 12,000 employees.

This project shows how advantages such as performance, ease of development, small size and low production costs are often secured early in the product's life. Although many devices are connected via the Internet, it is essential to have a local database that is fast and flexible enough to accommodate the many configuration options that exist in embedded computing systems.

Maintaining a secure connection with emerging enterprise solutions is critical to future success.