Visage Technologies, a Stockholm-based specialist in face-tracking and visual analysis, has initiated a €3.1 million EU-funded research initiative aimed at creating an intelligent platform capable of tailoring digital instruction and professional training simulations based on how learners feel and think. The European Union is contributing €1.9 million to the effort, which will run from April 2026 through April 2029.
The venture brings together Visage Technologies' Visage AI Labs division, the University of Zagreb's Faculty of Humanities and Social Sciences, and the University of Rijeka's Faculty of Maritime Studies. The consortium will concentrate initially on training systems for ship navigation, where cognitive strain and human mistakes during high-pressure scenarios remain a significant cause of accidents at sea.
Visage Technologies, established in 2002 with headquarters in Sweden and development teams based in Croatia, creates facial recognition and emotion-detection software deployed in sectors ranging from transportation and military applications to manufacturing and medicine.
Beyond Performance Scores
Conventional digital learning systems and professional training simulators typically adjust their content based on what users answer or how well they perform, ignoring whether learners are mentally exhausted or genuinely interested. This approach fails to meet individual learning requirements and leaves instructors uncertain whether training scenarios truly mirror the psychological strain of actual work environments.
Visage Technologies plans to overcome these shortcomings by constructing machine learning algorithms that process input from video cameras, audio recording, wearable sensors and other measurement tools to gauge the mental and emotional condition of people undergoing training.
The investigation will begin by tracking four dimensions: mental load, level of interest, emotional tone and intensity of feeling, though the final list of measurable states may shift depending on how reliably the models perform once real-world information is gathered.
The main idea behind the project is to help people learn by tracking two signals: stress level and cognitive load. If someone is overloaded with stress, they will have a hard time learning anything. It can also work the other way. If a person is bored, we can make them more engaged in the task. We can integrate any camera and any hardware, and everything we do runs on the edge
Hrvoje Šamija, Chief Business Development Officer at Visage Technologies
Three Components
The initiative will produce a foundational sensing system alongside three distinct tools built upon it. ACInsight SDK will merge information from multiple measurement sources to determine a trainee's mental and emotional profile. ACTutor will connect with current online learning systems to customise educational content for each person. ACTrainer will assist professional training environments by measuring whether simulated exercises accurately recreate the psychological and emotional intensity of genuine professional situations.
According to Bruno Rosan, Senior R&D Engineer at Visage Technologies, the company is constructing the whole infrastructure in-house, encompassing everything from information handling and predictive algorithms to rollout on multiple computing platforms.
Regulatory Alignment
The system is being engineered with safeguards for confidentiality, information security and digital safety built into its foundation from the start. The design takes into account the requirements of the GDPR, the EU AI Act and the NIS2 directive, and respects regulatory constraints on equipment designed to observe and measure mental and emotional responses.
Source: Tech.eu



