Smart object recognition algorithm doesn't need humans

Jan 16, 2014
Credit: BYU Photo.

(Phys.org) —If we've learned anything from post-apocalyptic movies it's that computers eventually become self-aware and try to eliminate humans.

BYU engineer Dah-Jye Lee isn't interested in that development, but he has managed to eliminate the need for humans in the field of . Lee has created an that can accurately identify objects in images or video sequences without human calibration.

"In most cases, people are in charge of deciding what features to focus on and they then write the algorithm based off that," said Lee, a professor of electrical and computer engineering. "With our algorithm, we give it a set of images and let the computer decide which features are important."

Not only is Lee's genetic algorithm able to set its own parameters, but it also doesn't need to be reset each time a new object is to be recognized—it learns them on its own.

Lee likens the idea to teaching a child the difference between dogs and cats. Instead of trying to explain the difference, we show children images of the animals and they learn on their own to distinguish the two. Lee's object recognition does the same thing: Instead of telling the computer what to look at to distinguish between two objects, they simply feed it a set of images and it learns on its own.

In a study published in the December issue of academic journal Pattern Recognition, Lee and his students demonstrate both the independent ability and accuracy of their "ECO features" genetic algorithm.

Credit: BYU Photo

The BYU algorithm tested as well or better than other top object recognition algorithms to be published, including those developed by NYU's Rob Fergus and Thomas Serre of Brown University.

Lee and his students fed their object recognition program four image datasets from CalTech (motorbikes, faces, airplanes and cars) and found 100 percent accurate recognition on every dataset. The other published well-performing object recognition systems scored in the 95-98% range.

The team has also tested their algorithm on a dataset of fish from BYU's biology department that included photos of four species: Yellowstone cutthroat, cottid, speckled dace and whitefish. The algorithm was able to distinguish between the species with 99.4% accuracy.

Lee said the results show the algorithm could be used for a number of applications, from detecting invasive fish species (think of the carp in Utah Lake) to identifying flaws in produce such as apples on a production line.

"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."

Explore further: New algorithm finds you, even in untagged photos

Related Stories

New algorithm finds you, even in untagged photos

Dec 02, 2013

A new algorithm designed at the University of Toronto has the power to profoundly change the way we find photos among the billions on social media sites such as Facebook and Flickr. This month, the United ...

Mapping objects in the brain

Dec 20, 2013

A brain region that responds to a particular category of objects is found to consist of small clusters of neurons encoding visual features of these objects.

Recommended for you

Researchers developing algorithms to detect fake reviews

Oct 21, 2014

Anyone who has conducted business online—from booking a hotel to buying a book to finding a new dentist or selling their wares—has come across reviews of said products and services. Chances are they've also encountered ...

User comments : 12

Adjust slider to filter visible comments by rank

Display comments: newest first

Kedas
3.8 / 5 (5) Jan 16, 2014
OBJECT ID: HUMAN
ACTION ID: SELF-DESTRUCT
ACCURACY: 99.9%
Pattern_chaser
5 / 5 (3) Jan 16, 2014
It could only turn into Skynet if we already allowed ourselves to be observed and controlled by out-of-control agencies of our own governments. ... Oh. Is Edward Snowden really John Connor?
Birger
5 / 5 (1) Jan 16, 2014
Pattern chaser, Naah, Skynet will be programmed to eliminate competitors of Halliburton...
malapropism
5 / 5 (1) Jan 16, 2014
OBJECT ID: HUMAN
ACTION ID: DESTRUCT
ACCURACY: 99.9%


There. Fixed that for you.
Whydening Gyre
5 / 5 (1) Jan 16, 2014
Malo -
You must be a programmer...
NoTennisNow
not rated yet Jan 16, 2014
This might be a boon for 'fore and forget' weapons.
adave
5 / 5 (1) Jan 16, 2014
Why would AI evolve to repeat the mistakes of man? Billions of years of evolution converges on a balance of resources. AI would need to nudge human behavior to support an ecological balance. Breed people for the best behavior and fit or design GMO human organisms, would best serve themselves and the new world of AI. Keep the best, use the rest.
AngryMoose
not rated yet Jan 17, 2014
Stick this in Google Glass, I want to know what I'm looking at damn it!
Shakescene21
3 / 5 (2) Jan 19, 2014
Think of all the boring jobs this will eliminate! All those people who sit at conveyor belts looking for blemished oranges and broken eggs can be replaced with "smart" machines. The unemployed workers can be retrained for higher-value jobs of the future, such as brain surgeons and rocket scientists.
Whydening Gyre
5 / 5 (1) Jan 19, 2014
Think of all the boring jobs this will eliminate! All those people who sit at conveyor belts looking for blemished oranges and broken eggs can be replaced with "smart" machines. The unemployed workers can be retrained for higher-value jobs of the future, such as brain surgeons and rocket scientists.

And, of course, the resulting glut will provide us with a lot of really well educated McDonalds associates and Starbucks baristas...
russell_russell
not rated yet Jan 19, 2014
"Lee likens the idea to teaching a child the difference between dogs and cats. Instead of trying to explain the difference, we show children images of the animals and they learn on their own to distinguish the two. Lee's object recognition does the same thing: Instead of telling the computer what to look at to distinguish between two objects, they simply feed it a set of images and it learns on its own."

Read more at: http://phys.org/n...html#jCp

Algorithms. Learning.
Reductionism.

Real world example:
http://www.newsci...elf.html

This twelve-year-old development has been perfected.

There is no human criterion to distinguish between a temperament set
by an algorithm and a temperament set by human hearing.

The only obstacle standing in Lee's reductionist approach is Kurt Gödel's Incompletness Theory as far as human pattern recognition is concerned.

Cont...
russell_russell
not rated yet Jan 19, 2014
There is no human criterion to distinguish between a temperament set
by an algorithm and a temperament set by human hearing:

Translated this means the pattern recognition of human hearing in tuning is limited to the resolution of human hearing and the algorithm to perform the same task matches and surpasses this "learned" ability.