Created at Moscow State University based on facial recognition, the “digital profiler” can be used to make deep fake calls, diagnose diseases and many other tasks. This was told socialbites.ca by one of the developers, a psychotherapist, Mikhail Baev, an expert in the analysis of facial expressions.
“We are not looking for emotions. We are looking for eyebrow shifting, squinting, mouth extension vertically, horizontally. We learned to measure 22 basic motor units that can make all kinds of facial expressions, including emotional expressions,” he explained.
The program can be used in medicine: to diagnose mental illness, to evaluate heart patients, to calculate the most successful face correction options in aesthetic medicine.
Also, the “digital profiler” will be useful in the work of researchers and HR professionals. On the basis of this system, scientists plan to create various methods of work in the field of personnel selection and forensic psychological examination.
In addition, the program allows you to effectively capture deep fakes, even in videos that are often impossible to see with your eyes. The program will do this by analyzing a person’s individual mimic motor profile. This profile is individual for everyone and it is extremely difficult or even impossible to imitate.
The system can also be applied in the field of animation and creation of robots. It will help to create completely natural facial expressions of the character without the use of acting and motion capture technology.
For more on how the “digital profiler” analyzes emotions and why neural networks fail to deal with it, see material “socialbites.ca”.