Friday, September 23, 2011

Speedier Fingerprint Matching through Classification

Accurate, automatic fingerprint classification would yield faster search results in large databases (The Star - South Africa)
“In fingerprint recognition, fingerprint templates normally sit in a database, so when going through an identification process, the system has to sift through thousands, if not millions, of templates, making the system slow in yielding results.

“A classification module essentially breaks down the overall database into smaller, manageable chunks to improve the performance of a fingerprint recognition system.

“Both the extensible fingerprint classifier and the pseudo-singular point detection module will allow the system to be extremely fast and accurate when a database search is conducted. This will add to the overall efficiency of a fingerprint recognition system,” he says.

The CSIR is working towards realising an identity authentication system through biometric research and development. South Africa desperately needs this capability because of crimes such as identity theft.
The technical part of this article is interesting. It illuminates a strategy to deal with the effects database size have on search speed.

The sketch of the scientist, Ishmael Msiza, and what motivates him is interesting, too.