(b) Red-eye detection in the entire image (c) Skin detection result with red-eye isolated (d) Final result of red-eye correction Credit: Konstantinos Plataniotis. |
It's an all-too-common experience - the perfect photograph ruined by the demonic glow of the "red-eye" effect. Now, a researcher at the University of Toronto has developed a method that can automatically remove those unsightly scarlet spots from digital images.
"The technique will offer consumers a convenient, automatic tool for eliminating red eye in digital photographs," says Professor Konstantinos Plataniotis of the Edward S. Rogers Sr. Department of Electrical and Computer Engineering.
Red eye occurs when a camera flash reflects back from the retina of the eye, making the coloured portion of eyes appear red in photographs. The software Plataniotis has developed isolates the reddened areas of the eyes and automatically replaces the abnormally coloured region with natural eye colour.
The current high-end digital camera filters that reduce red eye or the software that manually removes red are either time-consuming or have limited success, Plataniotis says. His technique, which could be used in cameras or labs that process digital images, could be available in about a year. Beyond photography, he adds, the technology could be applied to medical imaging, virtual human-computer interfaces and to monitor fatigue by tracking the eyes of drivers, pilots or others in jobs that require quick reaction times.
The study that he co-authored appears in an upcoming issue of the journal Pattern Recognition Letters.
CONTACT: Professor Konstantinos Plataniotis, Edward S. Rogers Sr. Department of Electrical and Computer Engineering, 416-946-5605, kostas@dsp.toronto.edu or Nicolle Wahl, U of T public affairs, 416-978-6974, nicolle.wahl@utoronto.ca
Journal
Pattern Recognition Letters