SAN DIEGO, Sept. 15, 2015 /PRNewswire/ -- Emotient, which helps organizations better understand their audience response to media, products and experiences, today announced a major step towards protecting individual privacy and identity in the fast-evolving space of emotion and sentiment analytics: the U.S. Patent Office awarded a patent to Emotient's method of analyzing facial expressions while disabling and discarding personally identifiable information like images of individual faces.
"Emotient is the only company in the world with a patent that allows the anonymization of images before we have extracted emotions, not merely after. This means that images can be anonymized before sending them over a network for offline emotion processing. Think of it as sophisticated pixelating or blurring of an individual's features – while retaining the expressive information – before transmitting," said Emotient CEO Ken Denman. "So identity is never seen or captured, let alone transmitted."
"The ability to decode and analyze authentic expression data presents immense power," said Dr. Paul Ekman, Ph.D., Professor Emeritus in Psychology at UCSF and co-discoverer of micro-expressions. "It is essential to ensure that these methods are used wisely, cautiously and with the correct safeguards and protections for privacy and notification. Emotient stands apart in its dedication to merging expression analytics innovation with identity protection. With this new anonymization patent, Emotient is leading the industry in the right direction."
The new patent (US 9,105,119 B2), titled "Anonymization of Facial Expressions," inserts unequaled privacy protections into Emotient's expression analytics system via a proprietary method for anonymizing facial images before they have been processed for emotions and reactions. One of the patent's authors, Dr. Javier Movellan, a co-founder of Emotient, likened his company's technology to voting: "We do not want to recognize who is watching. All we care about is what they are watching and how they feel about it. Our goal is to provide avenues for people to express their feelings about content in an anonymous, effortless, and scalable manner, because there is enormous value to how people respond to what they're watching."
Emotient's platform already allows for images of people to be destroyed once the face is processed. Now, with the addition of this feature, the patented technology immediately makes facial identity unrecognizable before any other processing, thus deterring any outside or third-party use of the face or related meta-data. Effectively encrypting the image while still allowing expression measurement balances both market interest and individual privacy, a provision that both Emotient and other experts agree will be essential.
This patent is the seventh granted in Emotient's portfolio of scientific breakthroughs in the emerging emotion analytics space – covering technology ranging from face detection and primary emotions to detection of facial muscle movements.
"It is also important to note that Emotient is the only company that can process and analyze the emotions and expressions of hundreds of people at once – or "in the wild" – adapting to imperfect environmental conditions and natural movements. It improves on any market insight by a factor of at least 10; and along with that improvement is a responsibility to safeguard identity and privacy, a responsibility we take very seriously and which we are building into our platform and entire company," added Denman.
About Emotient – Automated Expression Analysis Emotient, Inc., is the leading authority in expression analysis. Emotient software translates expressions into actionable information that helps companies make better decisions based on audience response to media, products and experiences. Emotient's technology is currently available through the EmotientAnalytics web service or the Emotient API. Automated emotion measurement can generate insights that increase revenue across many industries including advertising, media and entertainment, consumer goods, retail, enterprise sales, healthcare and education.
Emotient was founded by a team of six PhDs from the University of California, San Diego, who are the foremost experts in the application of machine learning, computer vision and cognitive science to facial behavioral analysis. Its proprietary, patented technology sets the industry standard for accuracy and real-time delivery of facial expression data and analysis. Emotient was named a Gartner 2014 Cool Vendor and was recognized as a 2015 TiE Top 50 Startup.