Microsoft says its facial recognition tools are improving with error rates reduced by as much as 20 times for skin color and nine times for women. The Verge brought this interesting information to us in their article, “Microsoft’s facial recognition can better identify people with darker skin tones.”
A facial recognition system is a technology capable of identifying or verifying a person from a digital image or frame from a video source. There are multiples methods in which facial recognition systems work, but in general, they work by comparing selected facial features from a given image to faces within a database.
Microsoft has been training its artificial intelligence (AI) tools with larger and more diverse data sets, which has led to some significant progress. They are getting better at identifying people with darker skin tones. The error rates have been reduced by as much as 20 times for men and women with darker skin and by nine times for all women.
This indicates a reduction in racial bias within the facial recognition system. The application to safety and security will be comprehensive if progress continues to be made in this young but growing technological field.
Melody K. Smith
Sponsored by Access Innovations, the world leader in thesaurus, ontology, and taxonomy creation and metadata application.