The practical side of face recognition

A National Institute of Standards and Technology report, based on a study of facial images collected at border entry points, recommends five steps for improving results

A study by the National Institute of Standards and Technology found that the facial images recorded at border entry points were not as clear or useful for automated recognition as they could be. So NIST researchers set out to learn what could be done to improve the situation.

They published a report in September titled “Assessing Face Acquisition: NIST Interagency Report 7540” (GCN.com, Quickfind 1262), which recommends five steps for improving results.

  • The camera should resemble a traditional camera.
  • The camera should click when the picture is taken so the traveler knows the picture is being taken.
  • The camera should be used in portrait mode.
  • The operator should be facing the traveler and the computer monitor while positioning the camera.
  • Border stations should have a mark, such as footprints, on the floor to indicate to the traveler where to stand for the photograph.
It seems to us that the cameras’ user manuals typically contain those sorts of recommendations. But better late than never.

About the Author

Patrick Marshall is a freelance technology writer for GCN.

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above