ROC SDK

The World's Most Trusted

Face Recognition Solution

Learn More

Accurate

Efficient

Usable

Scalable

What we do

Our software development kit, the ROC SDK, gives system and device integrators access to the world's fastest, most compact and accurate face recognition engine.

Top tier accuracy

World leader in accurate facial recognition algorithms, as measured by the National Institute of Standards and Technology (NIST).

99.0%

Frontal
Constrained
(Photo ID)

98.1%

Frontal Unconstrained (Selfie)

92.5%

Non-Frontal Unconstrained (Wild)

* Accuracy is measured as the 1:1 identity verification True Acceptance Rate at a fixed False Acceptance Rate of 0.01%. Source: NIST FRVT Ongoing.

Robust to challenging environments

  • Excels in difficult identification situations
  • Accurate and usable on imagery regardless of being low-resolution, occluded, off-pose, poorly lit, or unique expressions.

Full spectrum functionality

  • Demographics:
    • Age, race/ethnicity, and gender
  • Facial pose estimation:
    • Yaw and pitch angles
  • Glasses estimation
  • Identity clustering
  • Rapid and accurate face detection


■ Male: 0%
■ Female 100%
■ Age: 22
■ Asian: 0%
■ Black: 0%
■ Hispanic: 4%
■ White: 95%
■ Other: 1%
■ Glasses: None
■ Lips: Apart

Best in class efficiency

The most efficient face recognition solution on the market:
  • Fastest enrollment speed
  • Fastest comparison speed
  • Smallest binary footprint
  • Smallest template size
  • Best option for mobile environments
  • Reduced server needs

Enrollment speed
71 milliseconds

Rank One has the fastest enrollment speed in the industry. Amongst top-tier vendors, the ROC SDK is typically 3x to 10x faster. Why does enrollment speed matter?

Enrollment is the process of detecting faces in an image (or video frame) and creating "templates" that encode the identifying characteristics of each face. The faster the enrollment speed, the less computing power required to support a face recognition application.

Template size
133 bytes

Rank One pioneered small template sizes. The ROC SDK can search larger databases on a smartphone than some of our competitors can on a server. Why does template size matter?

The template size is the amount of storage space required to save a template extracted in the enrollment process. Applications involving the search of a database of face records generally must cache templates in memory; thus the smaller the template size, the less RAM needed.

Template size
133 bytes

Comparison speed
340 nanoseconds

Yes, we measure our comparison time in nanoseconds. Rank One's comparison speed is 10x to 100x faster than most competing solutions. Why does comparison speed matter?

The comparison speed is how long it takes to measure the similarity between two templates. The faster the comparison speed, the faster the verification or search results.


* Efficiency is measured on Intel Xeon CPU E5-2630 v4 @ 2.20GHz using a single thread. Source: NIST FRVT Ongoing.

Usability

The ROC SDK is a light-weight, easy-to-integrate software library that enables rapid system development

Native face recognition

The ROC SDK is a fully native solution, with minimal system requirements. Decrease technical risks while increasing system flexibility and control. Keep your data on your machine, no internet connection required.

Multi-platform support

The ROC SDK supports all major operating systems and computer architectures. The ROC SDK exposes a C API with wrappers for Python, Java, C# and Go. A robust command line interface even allows constructing systems from shell scripts.

Android

macOS & iOS

Linux

Windows

Real-time Video

The ROC SDK's industry leading enrollment and comparison speeds make Rank One the best choice for analyzing real-time streaming video.

Video support

The ROC SDK makes processing and analysis of streaming video easy via its face tracking, consolidation, and clustering algorithms.

Anti-spoof

Face recognition is becoming the biometric of choice for access control and mobile payments. This heightens the need for methods to prevent false facial presentations such as a printed photo or screen replay.

Passive Liveness

The ROC SDK ships with a patent-pending method for liveness validation to help ensure that a face presented is genuine. While other anti-spoof methods require user-assisted actions or specialized hardware, Rank One's method works on commodity cameras, only requires a single frame, and does not require the user to perform any actions. Thus, you can perform both liveness and identity validation in a single face capture.

Artificial Intelligence

While we don't brand ourselves as an "AI" company, make no mistake, Rank One has deep roots under the widespread umbrella of AI. Learn More...

While AI has become a popular term in business circles and pop culture, it generally lacks any specificity as to what techniques are being applied to a given problem. In many ways all face recognition algorithms developed in the past two decades were AI. However, the recent rise of convolutional neural networks and deep learning frameworks have unlocked the means to learn representations that are vastly superior to the manual representations of the past.

In terms of Rank One's intellectual roots, they are more properly described by the academic disciplines of pattern recognition (see Duda and Hart, 1973) and computer vision (see OpenCV). Rank One's team of engineers have matriculated under and collaborated with some of the leading minds in these fields, and our software bears the marks of the parsimony and precision such disciplines extol.

Contact Us

Please fill in the information below and one of our representatives will contact you as soon as possible.