A team from Brigham Young University has developed a new algorithm that allows computers to recognise a host of objects without any help from humans.
It's so accurate that not only does it recognise the difference between a tree and a fish, it has the potential to be able to tell an oak from a beech tree and a salmon from a goldfish and, crucially, it can do it all without any prompting.
"In most cases, people are in charge of deciding what features to focus on and they then write the algorithm based off that," said Dah-Jye Lee, a professor of electrical and computer engineering at Brigham Young University.
"With our algorithm, we give it a set of images and let the computer decide which features are important."
It works on the principle that a picture paints a thousand words. Why explain to a child or a computer why two animals are different when an image of the two side by side is a much simpler way of explaining?
In tests, the algorithm has scored 100% accuracy when tasked with identifying motorbikes, cars, airplanes and faces from video footage. And, when loaded with datasets from the university's biology department, was able to distinguish between four different species of fish with 99.4% accuracy.
Other object recognition systems are capable of similar levels of accuracy, but the big breakthrough with this system is that it doesn't need to be overseen or constantly reprogrammed in order to perform.
"It's very comparable to other object recognition algorithms for accuracy, but, we don't need humans to be involved," Lee said. "You don't have to reinvent the wheel each time. You just run it."
As such its potential uses are endless. It could be employed by car makers for use in smart collision avoidance systems or in agriculture to sort and discard damaged fruit and vegetables.
However, it is most likely to find a role as a critical component of future connected home and Internet of things systems because it can be taught to recognise the difference between an empty and full bottle of milk, a home owner and an intruder and even help you find where you dropped a sock. — ©AFP/Relaxnews 2014