A.I. Flower Classification

About us


Software Technology and Artificial Intelligence Research Laboratory
Chiba Institute of Technology

Flower Classification by Deep Learning

Since in LSVRC 2012 Hinton's group won the competition with his epoch-making deep learning system, SuperVision, applications of deep learning theory to various visual tasks have been active. We at STAIR Lab. developed an AI system that can recognize the species of a flower using the technology, and released the web service "hananona" in March 2017. hananona then could recognize 406 kinds of flowers.
Since then, we collected more flower photos, revised the model, retrained it, and finally the model can recognize 792 kinds of flowers.
We are pleased to release this new version of hananona.