There are thousands of prescription pills, but only few colors and shapes to choose from.
To avoid dangerous mix-ups in hospitals and at home, Jesus Caban at the U.S. National Institutes of Health and colleagues have developed software that can identify a pill from a camera phone image, New Scientist reports.
Tools to identify pills on smartphones do exist – such as apps from Drugs.com and WebMD – and they help distinguish between pills using descriptions that you have to type in. In clinical settings, however, this might be too time consuming.
Caban’s new software extracts the shape, color, and imprint of a pill from a picture you can take on your phone.
The team tested the system on images of 568 prescribed pills, taken from different angles and in various light conditions.
The app identified the drugs with 91 percent accuracy, and within a second. (The team hopes accuracy will improve once the system learns to recognize a pill from a wider range of angles.)
And the technique is simple enough to become a smartphone app for use at home.
The work was presented at the International Conference on Image Processing last week.
[From New Scientist]
Image by .v1ctor. via Flickr
