This website uses cookies to improve your experience. OK
ROC FACIAL RECOGNITION
Is your system powered by the industry's fastest
and most accurate solution?
Learn More

The ROC SDK

A lightweight software development kit that gives system and device integrators access to the world's most versatile face recognition technology. Click on an icon below for more details.

ACCURATE


2x MORE ACCURATE ON WILD
2x MORE ACCURATE ON MUGSHOTS

FAST


2x FASTER ENROLLMENT SPEED
13x FASTER COMPARISON SPEED

COMPACT


SMALLEST TEMPLATE AND BINARY SIZE IN THE INDUSTRY

USABLE


BEST IN CLASS API WITH EASY SOFTWARE INTEGRATION

Industry leading accuracy

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

99.6%

Photo ID
(Visa)

99.2%

Controlled Capture
(Mugshot)

95.8%

Social Media
(Wild)

Accuracy is measured as the 1:1 identity verification True Acceptance Rate at a fixed False Acceptance Rate of 0.01% for VISA and Wild and at a False Acceptance Rate of 0.001% for Mugshot. Source: NIST FRVT Ongoing.

Unrivaled Speed

  • Fastest enrollment speed
  • Fastest comparison speed
  • Best option for video processing
  • Reduced server needs

210 milliseconds
Enrollment speed
443 nanoseconds
Comparison speed

Speed is measured on Intel Xeon CPU E5-2630 v4 @ 2.20GHz. Source: NIST FRVT Ongoing.


UNPARALLELED EFFICIENCY

  • Smallest template size
  • Smallest binary footprint
  • Best option for mobile environments


165 bytes
Template size
155 MB
Memory footprint

Easy to integrate

The ROC SDK is a lightweight, simply integrated software library that enables rapid system development.

Android

macOS & iOS

Linux

Windows

ROC SDK Features

Verification

Perform 1:1 verification with industry leading accuracy.

Identification

Search millions of faces on a mobile device, or billions on a server, in seconds.

Face Detection

Locate faces in photos and video with industry leading detection speed.

Landmark Detection

Track eye and chin locations.

Clustering

Group unlabeled faces by identity.

Face Quality Metric

Predict a face likelihood to generate a successful match.

Face Analytics

Analyze a face to predict its age, ethnicity and gender.

Emotion Analysis

Analyze a face for anger, disgust, fear, joy, neutral, sadness or surprise expressions.

Video Support

Process videos in real-time using a single core on a mobile device or server.

Pose

Determine where a person is looking relative to the camera using roll, yaw and pitch measurements.

Liveness

Detect print and digital screen replay attacks using a single image.

Person Counting

Count persons in a video stream seamlessly.

Homomorphic Encrypted Matching

Measure template similarity within the encrypted domain.

Glasses

Detect eyeglasses, sunglasses, or no glasses.

GPU Support

Optionally enroll images on a GPU.

Artwork Analysis

Determine if a face is of a cartoon, a painting or a human.

Fully Native Solution

No internet connection is required.

C API Wrappers

Support for all major programming languages including Python, Java, C# and Go.

Command Line Interface

A robust command line interface allows constructing systems from shell scripts.

Trusted by

6
U.S. DEPT. OF DEFENSE AGENCIES
20+
LAW ENFORCEMENT AGENCIES
5+
FORTUNE 500 FINANCIAL INSTITUTIONS
1 of 2
MAJOR GLOBAL CREDIT CARD COMPANIES
10M+
FACIAL VERIFICATIONS PER YEAR

Our latest blog posts

Learn more about facial recognition technology from experts in the field.

Contact Us

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