Licensing opportunity
Researchers at the Department of Artificial Intelligence of the Universidad Politécnica de Madrid’s School of Computing (FIUPM) have developed an algorithm that is capable of processing 30 images per second to appraise a person’s facial expressions in real time and categorise them as one of six prototype expressions: anger, disgust, fear, happiness, sadness and surprise.
The software, which can be run on PCs and laptops, has a range of potential applications, for example, for the development of advanced human-computer interfaces, improving relationships with the e-commerce customers, and for generating avatars with an unprecedented capability to relate to the person they represent.
The developer say it would be possible to create avatars that simulate a person’s facial expression, possibility they believe will appeal to the video games industry.
During e-commerce transactions, the system could monitor the gestures of potential buyers, to determine whether or not they intend to make a purchase.
The developers say that although there are some facial analysis products on the market, none specifically target the analysis of facial expressions. While similar systems focus on just part of expression recognition, the Spanish prototype does the whole job, locating and monitoring the face in the image using an algorithm that works despite changes of illumination or user movement, and classifying the facial expression. It also incorporates an algorithm that calculates the likely “evolution” of the facial expressions.
Receive our Policy Bulletin each Tuesday & Thursday and news about bridging Europe’s east-west innovation gap twice a month in The Widening. 
