The ROC Difference
Faster and more accurate
- More than 99.4% accurate (NIST FRVT)
- Ranked #1 in algorithm speed and efficiency
- Detect persons, vehicles, text, and weapons in the same video feed
- Process videos in real-time on mobile devices
- Host millions of identities on a mobile device
- Identify faces and objects without ideal camera angles or lighting
- Proven FR accuracy with masks and sun glasses
- Hundreds of successful integrations
Ethical & Trustworthy
- American Nascency: 100% Made-in-America
- Highest ethical and privacy standards (Code of Ethics)
- Trusted by DoD, FBI, and Fortune 500 companies
- Free access to development SDK
- OS and platform agnostic
- Extensive documentation and sample code
- Deploy in the cloud, on-prem, or on a mobile device
- Works with existing camera and VMS systems
- Be up and running in minutes
Multi-National Financial Institutions
Learn more about AI/ML-powered computer vision from experts in the field.
In this article we explain how to factor in the computational demand for template comparison in video processing applications. While this task is not as computational burdensome as template generation, for larger-scale applications it can become meaningful.
The ROC SDK version 1.19 delivers top-tier accuracy and industry leading efficiency. This new version comes with accuracy improvements, clustering enhancements, homomorphic encrypted matching, GPU enrollment, and several other enhancements.
Law enforcement primarily uses face recognition as a post-incident forensic tool to enable detectives and analysts to generate investigative leads in violent and harmful crimes. In this article we explain how forensic face recognition works, and how it is used by law enforcement in this country.
The ROC SDK v1.22 delivers the largest set of technological improvements ever delivered in a ROC...
The ROC SDK now comes equipped with a cutting edge periocular recognition algorithm, capable of...
The latest NIST FRVT 1:N report demonstrates the unique combination of accuracy and efficiency...