Research at Cognitec, as well as our contributions to international research projects, involve the following subjects:
- deep learning techniques
- facial image forgeries and manipulations
- face recognition with low-resolution images and video material
- facial images with substantial pose variations and occlusions
- tracking people in crowds, even when the face is not visible
Facial image forgeries and manipulations
Recent years have seen significant advances in face forgery and manipulation methods that make it possible to create genuine-looking images and videos with modified facial identities. Deepfakes in particular—the exchange of a face in an image or a video with the face of a different person—have become known to a wider public due to media coverage on high-profile cases.
Read about measures to prevent facial image forgeries entering biometric systems in our white paper.
Cognitec is meeting the global demand for face recognition technologies that work well for masked faces by continuously improving our algorithms and increasing the matching accuracy for partially occluded faces.
Research and development in the past two years have resulted in robust algorithms for detecting and matching faces partly covered by protective masks. Evidently, matching accuracy differs in comparison to unmasked faces, since masks occlude a large area of the face and remove substantial information needed for comparison tasks.
Therefore, unmasked faces will remain the gold standard for automated face recognition technologies. High-security applications that need to establish a person's identity, like border control or passport issuance, will most likely require the removal of masks.
But as long as wearing masks is required or common in everyday life, recognizing masked faces is becoming an expected feature for systems that unlock phones, track and count people, measure demographics, or identify persons of interest.
Some face recognition companies are publishing doubtful claims about their technologies reaching the same matching accuracy for faces covered by masks. For accurate performance data, pleasesee the latest NIST test results on mask effects.