Get our free email newsletter

Software Algorithm Analyzes Facial Microexpressions

Algorithm for emotionsAdvances in facial recognition software enable companies to discern their customers’ emotions. Several software providers have systems that use cameras and algorithms to analyze what subtle differences in facial movements can reveal about people’s underlying feelings. The algorithms utilize databases of millions of faces to quickly interpret emotions that can appear in split seconds—a small lift of an eyebrow, for example, could suggest disgust.

The software has many potential uses, such as detecting whether drivers are too tired, enhancing law enforcement interrogations, or analyzing pain levels in pediatric patients. However, any application—particularly commercial use without consent—has obvious privacy concerns. After all, is there anything more invasive than spying on our deepest feelings? Some retailers are already developing programs for using security camera footage to analyze customers’ true reactions to products on display.

Today the technology is mostly used to gauge consumers’ emotions as they react to advertisements or try new products. Companies such as Emotient Inc., Affectiva Inc. and Eyeris sell software to marketers who use the systems to measure consumer engagement. The companies gathered massive amounts of data to train their software’s algorithms. They recorded millions of faces of people from various cultures and ethnicities and extracted billions of data points from each frame. Facial expressions are then sorted by emotional categories and used by the algorithm to interpret the emotions of people in videos. Several competing startups share a goal of embedding their software into tiny cameras so they can be used in video chats.

- Partner Content -

Pulse Amplifier Definitions and Terminology

This application note serves as a comprehensive resource, defining key terms like duty cycle, pulse rate, rise/fall time, and pulse width, as well as discussing pulse on/off ratio, RF delay, jitter, and stability.

Doctor Paul Ekman, an 80-year-old psychologist whose research and Facial Action Coding System are the foundation for facial recognition software, told the Wallstreet Journal, “I can’t control usage. I can only be certain that what I’m providing is at least an accurate depiction of when someone is concealing emotion.”

Source: Wallstreet Journal | Affectiva | Emotient

Related Articles

Digital Sponsors

Become a Sponsor

Discover new products, review technical whitepapers, read the latest compliance news, and check out trending engineering news.

Get our email updates

What's New

- From Our Sponsors -

Sign up for the In Compliance Email Newsletter

Discover new products, review technical whitepapers, read the latest compliance news, and trending engineering news.