Biometrics research has been greatly influenced in recent years by the development of neural networks, which have brought many new possibilities to the field. Since we have a long history of developing hardware solutions, we are exploring ways to optimize neural networks for embedded or edge devices.
We are currently working on developing a finger vein sensor and the algorithms needed to create a 3D representation of blood flow in the finger. This is quite complex research, involving the development of a sensor that requires knowledge of both optics and electronics design. The next phase will be to develop the appropriate algorithms.
Research also focuses on face recognition algorithms. We have many years of experience in this area. It should be noted, however, that the field of face recognition is evolving rapidly and poses a great challenge to researchers.
We have been also working on localizing the disease in the retina of the eye for a long time.
In the context of forensic investigations, a situation may arise where the captured person has no recognizable face. As part of our research, we are developing a solution that reconstructs the basic anthropometric proportions of a person for identification purposes. The importance of this research lies primarily in situations where we have reference proportions of a suspect and try to compare them with the assumed proportions of a person obtained from a photograph or video sequence.