University of Queensland scientists release AI tool for plant microscopy
University of Queensland researchers unveiled a new software benchmark to improve artificial intelligence analysis of microscopic plant images at the European Conference on Computer Vision in Malmö, Sweden, from September 8 to 12.
New dataset addresses AI blind spots
Ph.D. student Tianqi Wei noted that advanced vision-language models struggle with cellular details in plant science. The team created PlantMicro to guide these models toward a more robust understanding of microscopic structures. This software integrates thousands of images to test how well AI can identify and sort minute plant features.
Collaboration supports food security research
The project involved the School of Electrical Engineering and Computer Science alongside the School of Agriculture and Food Sustainability. Partial funding came from the Grains Research and Development Corporation to advance discoveries in environmental sustainability. The benchmark is now available on GitHub for other researchers to use.
Reported by one outlet
Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.
Reported by
1 independent outlet. Headline as published. Links open the original report.