SAN DIEGO, Dec. 12, 2013 /PRNewswire/ -- Emotient, the leading authority in facial expression recognition, today announced the commercial availability of its new FACET® 2.1 SDK, which performs real-time, frame-by-frame analysis of the emotional responses of users. The latest version of the FACET SDK includes two advanced emotions: frustration and confusion, as well as a demographic detector for gender. Technology advances include improved robustness to extraneous factors, such as changes in illumination, image resolution, and ethnicity, as well as head pose and facial landmark details. This critical information is now available for developers that are interested in delivering emotion-aware applications and services.
"Emotient is setting the industry standard for real-time, high accuracy emotion detection," said Ken Denman, CEO, Emotient. "Our technology is the industry's leading provider of high accuracy, real-time facial expression recognition, which opens the door to a variety of innovative applications and services that are simply not possible with competing solutions. We look forward to the many ways emotion awareness will impact consumer, marketing, healthcare and business experiences."
FACET is a commercially proven, automated facial expression recognition technology that provides the ability to perform real-time, frame-by-frame analysis of the emotional responses of users. FACET detects and tracks expressions of primary emotions, including joy, surprise, anger, disgust, sadness, contempt and fear; overall sentiments, including positive, negative and neutral; and blended composites of two or more emotions.
FACET 2.1 SDK now features advanced emotions, including frustration and confusion. It also now includes 19 action unit (AU) channels, representing facial muscle movements from the Ekman Facial Action Coding System (FACS). The addition of Facial Action Units allows research customers to perform deeper levels of facial expression analysis and was a popular feature in the Computer Expression Recognition Toolkit (CERT), a predecessor technology developed by Emotient's founders during their tenure at University of California, San Diego.
Head pose estimates are also provided in the FACET 2.1 SDK, including yaw (side-to-side motion), pitch (up and down motion), and roll (clockwise and counterclockwise rotation of the image plane). The new SDK also outputs facial landmarks, which include the location of the eyes, nose and mouth. For a complete list of FACET 2.1 SDK features, please visit the Emotient product page.
FACET was developed using machine-learning methods to high-volume datasets that are carefully constructed by a team of FACS-certified behavioral scientists. The technology can detect single-frame microexpressions of emotions. The architecture is built with the future in mind; it is highly scalable and extensible to adapt quickly with changing market and customer needs.
The FACET 2.1 SDK uses device-resident cameras and webcams for image capture; no special camera equipment is required. The system is highly extensible and runs on both Windows® and Linux® applications, with a small memory footprint.
About Emotient – Facial Expression Recognition System
Emotient is the leading authority in facial expression analysis. Our flagship product is the FACET SDK, a proven software solution that translates facial expressions into actionable information, thereby enabling a broad array of companies to develop emotion aware technologies and to create new levels of customer engagement, research, and analysis.
Founded by the foremost experts in applying machine learning, computer vision and cognitive science to facial behavioral analysis, our proprietary technology sets the industry standard for accuracy and real-time delivery of facial expression data and analysis. For more information on Emotient, please visit www.emotient.com.