Palo Alto, California - April 29, 2016 - Sighthound, Inc. today announced that it has joined the Embedded Vision Alliance and will be demonstrating its latest facial recognition software at the Embedded Vision Summit 2016, to be held on May 2-4 in Santa Clara, CA. Sighthound will be exhibiting at Stand T6.
On display will be demonstrations of the latest Sighthound face recognition software, which has attained scores of 99.2% against the PubFig200 benchmarking database, beating both academic research institutions and other commercial and open source alternatives. The software makes it easy for companies to add face verification or identification to products or services without needing expertise in computer vision, and is the result of over 3 years of research into deeply learned neural networks by the Sighthound computer vision research lab.
Sighthound designs and builds intelligent convolutional neural networks that stand out for their accuracy and speed. Our model achieves better results than Google’s FaceNet but uses only about 1.5% of the number of training images Google uses, and uses a single crop of the face for speed. The result is that Sighthound’s software is highly accurate, robust to a variety of real world use cases, and runs in real time.
Sighthound’s face detection and recognition software is the latest addition to the Sighthound Sentry suite of computer vision capabilities, used by OEMs to add intelligence to products and services. Sighthound also markets an intelligent home and business surveillance system, Sighthound Video, which uses its person detection software, and Sighthound Cloud, a set of computer vision APIs for developers.
Sighthound is the easiest way to add state-of-the-art computer vision software to your products and services.
About the Embedded Vision Summit
The Embedded Vision Summit is the only event in the world focused entirely on helping product developers build better products using computer vision. You’ll get to learn about the latest proven technologies and practical techniques in computer vision and deep learning, as well as see keynotes from Jeff Dean of Google and Larry Matthies of NASA.