The Rank One Computing Software Development Kit provides scalable software libraries for developing state-of-the-art face recognition applications built atop our industry-leading, NIST-certified algorithms.
Reach Out to Learn More
Top-Tier Accuracy
ROC is a world leader in accurate facial recognition algorithms, as measured by NIST (the National Institute of Standards and Technology).
Graphic of arrow hitting the bullseye of its target
98.9% Visa
Passports, Photo IDs, Scanned Photos
TAR at FAR of 0.0001%
99.4% Mugshot
Controlled Capture, Access Control
TAR at FAR of 0.001%
96.8% Wild
Photo journalism, Social Media, Uncooperative
TAR at FAR of 0.01%
Rocket ship blasting off
Lightweight, Fast + Efficient
Rank One combines top-tier accuracy with fast and efficient template generation in a small footprint enabling FR technology for mobile applications in the field; most of our competitors require massive servers and an active internet connection for mobile use.
Template Size
7-15x smaller than our closest competitors.
Memory Footprint
10-20x smaller than our closest competitors.
Template Generation
2-5x smaller than our closest competitors.
Trustworthy + Reliable
Get the peace of mind knowing your software is developed in the USA by US citizens and is trusted by Fortune 500 companies and throughout the Department of Defense. We are advocates for the safe and morally sensible use of facial recognition to help solve challenging problems.
Graphic showing a hand shake
Graphic of message bubbles
Quick to Setup + Great Support
Our products are built by engineers for engineers. When you purchase the ROC SDK, you will get full access to a support team staffed by those very engineers.
Easy to Integrate
Armed with our SDK, you can start leveraging facial recognition right from the console.
# Verification ——————
# Create a template of each face
$ roc-represent faceA.jpg faceATemplate.t
$ roc-represent faceB.jpg faceBTemplate.t
# Run a comparison
$ roc-compare faceATemplate.t faceBTemplate.t
# Receive a similarity score
$ 0.992918

# Search ————————
# Generate your face gallery
$ roc-represent -r images/ gallery.t
# Create a template of your probe face
$ roc-represent probe.jpg probe.t
# Receive a set of match candidates in a JSON file
$ roc-search gallery.t probe.t candidates.json

[ {
    “Age”: 38,
    “AlgorithmID”: 746588177,
    “Artwork”: “Human”,
    “ChinX”: 340,
    “ChinY”: 518,
    “Confidence”: 0.9999476075172424,
    “Emotion”: “Neutral”,
    “FacialHair”: 2,
    “Female”: 0.9907202124595642,
    “Gender”: “Female”,
    “GeographicOrigin”: “European”,
    “Glasses”: “None”,
    “Height”: 270,
    “IOD”: 143,
    “Index”: 0,
    “LeftEyeX”: 413,
    “LeftEyeY”: 284,
    “MaskDetection”: “NoMask”,
    “MediaID”: “1234abcd”,
    “NoseRootX”: 337,
    “NoseRootY”: 282,
    “OCD”: 234,
    “Path”: “janedoe.jpg”,
    “Pose”: “Frontal”,
    “Quality”: 0.05382765829563141,
    “RightEyeX”: 270,
    “RightEyeY”: 284,
    “Rotation”: 0.33837127685546875,
    “TemplateID”: “{5678efgh}”,
    “Width”: 270,
    “X”: 337.09375,
    “Y”: 361.43768310546875
} ]

Face Detection
Locate faces in photos and video with industry-leading detection speed.
Person Counting
Count persons in a video stream seamlessly.
Periocular Recognition
Identify persons using only the eye and eyebrow regions of the face.
Detect print and digital screen replay attacks using a single image.
Artwork Analysis
Determine if a face is of a cartoon, a painting, or a human.
Perform 1:1 verification with industry leading accuracy.
Group unlabeled faces by identity.
Search millions of faces on a mobile device, or billions on a server, in seconds.
Landmark Detection
Track eye and chin locations.
Determine where a person is looking relative to the camera using roll, yaw and pitch measurements.
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.
Mask Detection
Analyze if a mask is occluding a portion of the face.
Glasses Detection
Detect eyeglasses, sunglasses, or no glasses.
Technical Specifications
Wide OS Support
Our SDK can be integrated across all prominent operating systems:

Mac OS





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.
Fully Native Solution
No internet connection required.
Homomorphic Encrypted Matching
Measure template similarity within the encrypted domain.
Video Support
Process videos in real-time using a single core on a mobile device or server.
Media Management
Manage and store your media and metadata in a simple to use database.
Leverage FR technology on your own Web service on hardware that you control.
GPU Support
Leverage GPUs for even greater templatization throughput.
Ready to test it out?
We license the ROC SDK in four tiers, designed to fulfill your specific needs. To learn more about our licensing options reach out and we will connect you with a sales representative.
Face Detection
Template Generation
Liveness Detection
Facial Comparison
Facial Tracking
Facial Search
Facial Clustering
Face Detection
Template Generation
Liveness Detection
Facial Comparison
Facial Tracking
Facial Search
Facial Clustering
Face Detection
Template Generation
Liveness Detection
Facial Comparison
Facial Tracking
Facial Search
Facial Clustering
Face Detection
Template Generation
Liveness Detection
Facial Comparison
Facial Tracking
Facial Search
Facial Clustering
Contact us for a free trial.
We would like to get the SDK in your hands for testing and evaluation.
Seamlessly integrate the SDK into your products.
Armed with our powerful SDK, you will be able to elevate your product’s biometric solutions.
Sign up for an evergreen licensing package that works for you!
We will help you build the right package for your needs, reach out to find out more about our mobile and volume discounts.