Tygart Technology

Artificial Intelligence and Biometric Solutions

MXSERVER™ and Matchbox® leverage cloud-technology and deep learning-based face detection and recognition algorithms to:

  • Rapidly analyze and search massive collections (hundreds of millions) of videos/photos, and
  • Monitor large arrays of video surveillance cameras in real time

Combined, MXSERVER and Matchbox deliver “ubiquitous identification” – the ability to rapidly identify an unknown person anywhere, anytime and using any face capture device and/or video/digital camera which has Internet or LAN connectivity.

Read More about our MXSERVER & Matchbox Technology

Cloud-Based Architecture

Tygart has long recognized and understood that enterprise-grade video/photo analytic and face search systems can only be viable if the platform is designed for scalability and is underpinned by a High-Performance Computing (HPC) architecture. In 2008, before “the cloud” was an industry buzzword, Tygart began leveraging fabric computing technology to create MXSERVER. MXSERVER now utilizes COTS cloud-based technology to optimize the way data is processed across any collection of machines or compute nodes. The shared distribution of storage and processing increases scalability while reducing compute failure, a key advantage in handling complex, unstructured data types.

Tygart’s cloud-based architecture simplifies development, integration and operations and maintenance efforts by abstracting the complexity of a flexible and massively scalable computing architecture. It enables accelerated development timelines and significantly reduced costs when compared to custom or algorithm dependent solutions. Leveraging a COTS service-oriented cloud-based computing platform simplifies and dramatically shortens the time (within hours/days) needed to install, configure and begin operating a high-performance computing environment.

Applied Artificial Intelligence

Tygart is leveraging breakthroughs in machine learning to deliver highly accurate and efficient automated computer vision capabilities.  MXSERVER’s modular cloud-computing framework facilitates the integration of deep learning algorithms to meet next-generation image and video analysis requirements.  Tygart’s biometric solutions are algorithm agnostic, leveraging best-of-breed detection and matching algorithms for each modality.  Over time, no single vendor will be able to effectively serve as the best face, fingerprint and iris algorithm provider. Tygart’s vendor agnostic approach utilizes the matcher algorithm as a plug-and-play commodity, enabling a flexible biometric search service that can be quickly upgraded to deliver a better performing algorithm when one becomes available. An agency can simply replace the algorithm, not the entire biometric search core – avoiding a costly re-engineering of the biometric system.

Scalable

MXSERVER’s modular service-oriented architecture requires no specialized hardware or high-performance computing expertise, allowing the system to be rapidly extended simply by spinning up additional processing capacity to meet demand. MXSERVER delivers immediate scalability so that agencies can rapidly adapt to changing processing demands or increased information flow.

Docker

Tygart’s latest release of MXSERVER implements a microservice architecture leveraging Docker containers and Swarm to deliver a video/photo analytic and biometric search capability with massive processing capacity and speed. Containerizing services facilitates the rapid integration of new video analytic services and supports plug- and-play of improved algorithms – enabling MXSERVER to deliver processing pipelines that are scalable, flexible and run services/algorithms at unprecedented speeds.

Docker container technology is increasingly becoming an integral part of production environments of large corporations because it is Lightweight and Fast, Portable and Secure and Fault Tolerant.