Researchers explore face recognition for the visually impaired
01 April 2016 14:35 GMT

A team of university researchers has produced the first detailed analysis of how face recognition tools can be adapted for use by the visually impaired.

Conducted by a team from the University of Surrey, University Group for Identification Technologies (GUTI), and Carlos III University of Madrid, the exploratory research found that people with poor vision can struggle to use facial biometrics for identity verification.

This is often because, when asked to take selfies, a poor positioning of the camera leads to the face being blurry or off-centre.

The primary purpose of the study is to assess if state-of-the-art face recognition is ready to be used by blind or partially blind subjects or not; and if they are not adequate, how alternative forms of feedback (other than visual), such as audio and tactile can be used to assist them so that the technology is more usable.

The researcher have built the first specific database for testing on the subject, noting that 15% of the world’s population have a form of disability.

For their research, a blind-subject face database (BSFDB) was created which contains some 40 individuals with visual disabilities who took selfies with a mock-up mobile device.

Related articles

Researchers invent facial recognition cane for the blind

Industry Events

connect:ID 17-18 Mar 21