Emotion Recognition

The algorithm is albe to automatically classify the emotional state of an individual at a certain moment based on the analysis of the face

The algorithm is capable of recognizing emotions and can be installed on any device equipped with an HTML 5 browser, without the need for an app or plug-in.

Reco 3.26 offers an innovative, fast and secure solution for recognizing the user's emotional state: sensitive data is never stored as it is processed in real-time.
The solution is 100% GDPR compliant. No biometric data is saved on the servers. The application is also modular and totally scalable: it runs on local architecture without any infrastructure cost.

What it notes:

  • Presence of up to 6 people in front of the camera
  • Position of the head along the three axes
  • Attention level from zero to 100%
  • Basic emotions (Anger, Disgust, Fear, Happiness, Sadness, Surprise, Neutral)
  • Circumflex model of emotional states based on arousal and valence values
  • Expressions of desire
  • Demographic data (age, gender)
  • Other features +30: Arched eyebrows, Attractiveness, Bags under the eyes, Baldness, Bangs, Beard, Big lips, Big nose, Black hair, Blonde hair, Brown hair, chubby, double chin, earrings, Thick eyebrows, Eyeglasses, Goatee, Gray hair, Hat, Heavy makeup, High cheekbones, Lipstick, Pale skin, Pointed nose, Rosy cheeks, Sideburns, Wavy hair, etc.


  1. Monitoring of the maximum level of customer satisfaction when purchasing a product
    • Facial expression detection: instant detection of the emotional state during the shopping experience
    • ADV: user involvement by enriching the in-store or remote experience with multimedia content using 3D & AR Viewer

  2. Customization of advertising campaigns
    • Detection of age and gender of the customer to provide relevant images and products to be displayed on the device
    • Detection of the emotional reaction of the customer viewing the product on the device

  3. Recognition of emotions during a live event (conferences, concerts, talks, other)