ROC SDK Version 1.9 Released
November 19, 2016
This new version provides a significant boost in accuracy to both the ROCFR and ROCID algorithms with roughly a 5x decrease in error rates for both algorithms. Two new classifiers are being introduced: an automated race/ethnicity classifier (White, Black, Hispanic, Asian and Other), and an automated glasses detector (eyeglasses, sunglasses, or no glasses). There is a multitude of other feature enhancements as described in the SDK change log. This release further validates the advantage of using ROC SDK for your face recognition needs. Despite being the most efficient face recognition solution, arguably the most accurate face recognition and detection algorithms, and the most affordable solution amongst top tier vendors, the ROC SDK is also a rapidly improving technology. We have already begun working on our next release which will provide users with more improvements and additional features, to include a state of the method for face liveness detection.
ROC SDK Version 1.8 Released
October 3, 2016
Rank One is excited to announce the release of ROC SDK version 1.8. The most notable improvements with this release are over a 25% improvement in enrollment speed (i.e., the speed to generate roc-templates), and the inclusion of a new face quality metric that is a strong predictor of the ability for an image to generate a successful match. The improvements to enrollment speed continue to establish ROC SDK as the fastest solution on the market and better support the ingestion of large face databases or template generation on small embedded devices. The quality metric will allow ROC SDK integrators to provide more meaningful feedback to system users, thus improving the predictability of such face recognition systems. Many other stability improvements and feature enhancements have been made across the SDK as well.
Rank One demonstrates technology at the Global Identity Summit (GIS)
September 11-14, 2016
Rank One, alongside their partners at Ideal Innovations, Inc., demonstrated at the GIS the game changing efficiency and accuracy of the ROC SDK in face recognition applications embedded on laptops and mobile devices. While other technology providers require multiple servers to host large face databases, and their customers still must wait long periods of time for the search results to become available, government and industry attendees at the GIS witnessed highly accurate, large-scale searches across millions of images on laptop and mobile hardware, with near-instantaneous search results. As Rank One's user base continues to grow, the face recognition community is realizing through events like GIS that accurate and scalable face recognition solution can be licensed for a fraction of the cost of legacy solutions. Contact us today for your organization to get started with your evaluation.
ROC SDK Version 1.7 Released
August 29, 2016
Rank One is pleased to annouce the release of a new version of the ROC SDK. Version 1.7 brings our customers and integrators several enhancements, including automated liveness/spoof detection, improved face detection accuracy, and wrappers for C#, Java and Python. Our engineers are busy developing many new features and algorithm improvements, continuing the rapid pace of improvements for the ROC SDK.
Ideal Innovations releases FABIS-Mobile
June 14, 2016
Rank One's partner, Ideal Innovations, Inc. (I3), has released the Facial Automated Biometric Identification System (FABIS)-Mobile product. Powered by the ROC SDK Mobile and ROC SDK Server, this solution enables searching over 1M face records on a mobile device without a backend connection, or tens of millions of face records on a laptop. Users of this system will have access to Rank One's breakthrough face recognition algorithms in a solution developed and delivered by an organization (I3) with extensive experience deploying operational systems to defense customers and private industry.
Rank One demostrates technology at Michigan State Police Biometrics Conference
Grand Rapids, MI
May 17-18, 2016
Law enforcement and industry partcipants were high with praise after observing ROC-integrated technology performing challenging face recognition searches across large databases. Whether it was searching 50M face records on a single laptop, or 1M face records on a mobile device without a backend connection, the postive hits returned in near real-time demonstrated the unprecedented capability offered in the rapidly evolving ROC SDK.
See this capability for yourself at the Police Security Expo (Atlantic City, NJ, 28-29 June 2016). We will be located with our partners from Ideal Innovations, Inc. (I3) at booth #175.
ROC SDK v1.4 released
February 16th, 2016
We are pleased to announce the release of ROC SDK v1.4, which advances a breakthrough set of commercial-off-the-shelf face recognition algorithms.
ROC SDK provides integrators a face recognition algorithm with state-of-the-art accuracy on imagery with variable illumination or facial poses (often referred to as unconstrained face recognition). Our 128-byte face template allows for facial searches to be conducted with an order of magnitude reduction in hardware costs over other industry solutions. Enrollment (or indexing) speeds are extremely fast, with state-of-the-art face detection accuracy and speed on near-frontal and full-pose face images.
This newest SDK version introduces efficiency improvements, improved face detection, new API features, and a gender estimation algorithm. A major milestone has been reached as this version supports enrollment and matching on Android mobile devices. With the efficiency of ROC SDK, a commodity phone can now perform on-device searching of up to one million face records in a matter of seconds.
Rank One’s customers have licensed our algorithms in applications ranging from social media to security. They continuously remark about the efficiency of the software. The accuracy is exceeding expectations despite deployments with imagery conditions that still plague other commercial solutions. Users without prior experience in automated face recognition are finding the SDK is simple and easy use. Others are quickly porting from their legacy face recognition solutions into systems powered by ROC SDK, a task that has been eased by ROC SDK’s ability to rapidly enroll their existing databases.
The academic license for ROC SDK is allowing researchers to explore applications such as searching and clustering billions of images. At the same time, multiple research groups are confirming that ROC SDK is the most accurate commercial face recognition benchmark for unconstrained imagery.
Rank One begins a news feed
February 16th, 2016
We will use this page to keep our partners informed on the latest updates from the Rank One team.
Copyright © Rank One Computing 2017