Bees’ face recognition mechanism can improve artificial intelligence systems

Monday, January 26, 2009

SYDNEY - Bees can recognise faces even when viewed from different perspectives, a discovery that potentially opens the way to improved artificial intelligence software ystems.

Bee researcher Adrian Dyer of Monash University carried out a study and said the finding could be applied in the development of imaging systems.

‘What we have shown is that the bee brain, which contains less than one million neurons, is actually very good at learning to master complex tasks. Computer and imaging technology programmers who are working on solving complex visual recognition tasks using minimal hardware resources will find this research useful,’ Dyer said.

‘Most current artificial intelligence (AI) recognition systems perform poorly at reliably recognising faces from different viewpoints. However the bees have shown they can recognise novel views of rotated faces using a mechanism of interpolating or image averaging previously learnt views.’

The findings show that despite the highly constrained neural resources of the insects (their brains are 0.01 percent the size of the human brain) their ability has evolved so that they’re able to process complex visual recognition tasks.

The researchers trained different groups of free flying bees with a sugar reward for making correct choices, or alternatively the bees were punished with a bitter tasting solution for incorrect choices.

Dyer said the discovery helps to answer a fundamental question about how brains solve complex image rotational problems by either image averaging or mentally rotating previously learnt views, said a Monash release.

‘Bee brains clearly use image interpolation to solve the problem. In other words, bees that had learnt what a particular face looked like from two different viewpoints could then recognise a novel view of this target face. However, bees that had only learnt a single view could not recognise novel views,’ Dyer said.

The finding was published in PLoS ONE.

will not be displayed