Imagine a Shazam for Plants

By
Tuesday, August 25th, 2015
liked this article
Embed
Autodesk – 300 X 250 (expire December 31)
advertisement
Shazam
FavoriteLoadingsave article

There’s more than 250,000 flowering plants on Earth, but until now the only fool-proof way to identify them was to ask your friendly, neighbourhood botanist.

A project by an ECU computer science researcher aims to automatically identify plants using high-tech image recognition software similar to popular music identification app Shazam.

ECU School of Computer and Security Science PhD candidate Oluleye Hezekiah Babatunde has developed a computer program which can identify the species of a plant based on a digital photo of a single leaf.

“The program uses a combination of highly complex mathematical algorithms and artificial intelligence to identify leaves based on their colour, shape and texture,” he said.

“In testing so far, the program correctly identifies leaves more than 93 per cent of the time.”
The software could have extensive applications in the agricultural sector.

The same processes used by the software to distinguish between different species could be used to monitor damage to crops by pests, weather and herbicide according to Mr Babatunde.

“There’s potential for farmers to use this tool in an app form to get real time updates on their crops with a simple smartphone image,” he said.

Mr Babtunde is now seeking partnerships to take the project out of the lab and into the field.

Embed
FavoriteLoadingsave article

Comments

 characters available
*Please refer to our comment policy before submitting
Discussions