The latest NIST FRVT 1:N report demonstrates the unique combination of accuracy and efficiency delivered by the ROC SDK as compared to industry peers.Read More ROC SDK v1.20 delivers top-tier accuracy and unparalleled efficiency in latest NIST 1:N report
When building mobile or embedded face recognition applications, there is a small amount of computer memory available. Thus, only face recognition algorithms that require a limited amount of RAM can be used in mobile and embedded applications. This article discusses these concepts and highlights how many vendors develop algorithms that are not usable in mobile and embedded applications.Read More Understanding the Importance of Peak Memory Usage
The ROC SDK version 1.20 delivers major accuracy improvements, alongside a wide range of other algorithmic and functionality enhancement.Read More Overview of ROC SDK Version 1.20
Rank One Computing believes in a just, non-violent world of equality and fairness. We prize democratic values, civil liberties and open and informed debate. When used to further these values, automated face recognition can continue to make the world a safer, better place for everyone. In the absence of regulatory guidance, we wish to advance limitations that we believe are appropriate in how face recognition should be utilized.
The following set of ethics serve as a guideline for how we will develop face recognition systems and how we will expect our integration partners and end-users to develop and utilize face recognition systems based on our algorithmsRead More Facial Recognition Code of Ethics
There is a misperception that face recognition algorithms do not work on persons of color, or are otherwise inaccurate in general. This is not true. The truth is that across a wide range of applications, modern face recognition algorithms achieve remarkably high accuracy on all races, and accuracy continues to improve at an exponential rate.Read More Race and Face Recognition Accuracy: Common Misconceptions
When automated face recognition technology is used for analyzing streaming video, an important question is: how much computer hardware is needed? The hardware required to process video depends on several factors which will be discussed in this article.Read More Hardware requirements for video processing applications – Part 1: Template generation
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.Read More Hardware requirements for video processing applications – Part 2: Template comparison