A Software Development Kit for personalized mood recognition through video analysis of facial expressions
A Spanish research group in computer science has developed a new method capable of recognizing the mood of a person through a video analysis of facial expressions. This method has been embedded in an Software Development Kit (SDK) for developers (web and mobile) in fields such as market research, education, gaming. Commercial agreements with technical assistance, and license agreements are being sought.
This technology can be useful for marketing companies willing to offer product strategies based on customer experience, in the education sector (for on-line courses) and for game development to adjust the games’ playability and engagement.
Facial expression recognition has been widely applied in the field of psychology, video games, health, learning and man-machine interactions in general, being a very active research area. The concepts of "mood" and "emotion" are often confused in colloquial language and in their formal definitions. However, there is a consensus that marks at least two major differences between these concepts: • Moods have a longer duration than emotions. • Moods are related to emotions because a person who is in a certain mood is prone to experience emotions in his/her facial expression. Current technologies analyze emotions, but they are not able to analyze moods. This method is based on the machine learning of personalized facial expression models for each subject. Once trained, the method performs a dynamic evaluation of the contribution of subject’s facial micro expressions to a certain mood. This method could be implemented in different computer-based systems or in mobile devices by means of a proprietary SDK and it performs in real time.
Advantages and innovations
Currently there are tools that can analyze people's emotions, but they are not able to analyze and evaluate one's mood. The existing tools use procedures that focus on the recognition and processing of snapshots, while this SDK is based on video sequences, which allows to dynamically evaluate the mood in real time. An important innovation is that the SDK offers a subject’s personalization to minimize errors of different subjects’ micro expressions to express their feelings, for this reason, the method of recognition is precise and customizable. Existing methods are restricted to the identification of emotions (happiness, sadness, etc.) but do not allow the detection of complex constructs such as mood, the activation of which can at the same time comprise different configurations of emotions, sometimes even opposing ones (for example, anxiety can occur in a sad or in happy person). This method solves the problem, giving way to a much more precise analysis and recognition.
Available for demonstration
Intellectual Property Rights (IPR)
Register your interest
How it works
- Tell us about yourself
- We’ll discuss with you
- We put the right partners in touch
EEN help you find the right partner, rather than you going it alone.
Our role is to review and collate the most suitable submissions, and then send them to the client who posted the opportunity. We consult with you, and the client, to make the process professional and easy.
These are live opportunities. Your registration of interest on the site is just like a professional approach to a business at a networking event. To stand the best chance of success, make your submission really sing. Sell why the client who posted the opportunity should work with you. Excite them. Ask questions. Try and avoid copy and pasting words from elsewhere.
Once the client has chosen their partner, we'll introduce them over email and keep in touch with both parties to see how it's going. Sometimes things progress quickly. Sometimes because of changing priorities for either party, things progress slowly, but you never know - your next big business break could start right here.
First we need to check you’re human.
Thank you for verifying your email. We have sent you a confirmation email containing a 6 digit verification code to unlock the form below