Communications of the ACM
Machine Learning Researchers Team p With Chinese Botanists on Flower-Recognition Project
Microsoft Research Asia scientists, working with botanists at the Institute of Botany, Chinese Academy of Sciences, trained a deep neural network to quickly identify any flower or plant.
Credit: Microsoft
Microsoft Research Asia scientists, working with botanists at the Institute of Botany, Chinese Academy of Sciences (IBCAS), have developed the Smart Flower Recognition System, which is designed to quickly identify any flower or plant.
The researchers trained a deep neural network to recognize images using a set of learnable filters. Each filter is initially convolved across the width and height of the input volume, computing the dot product between the entries of the filter and the input. The process produces a two-dimensional activation map of that filter, and the system then learns filters that activate specific types of features at a given spatial position in the input.
After entering millions of pictures into the deep-learning framework, the researchers say they enabled the engine to accurately identify images more than 90% of the time.
"The flower-recognition engine enables domain experts to acquire plant distribution in China in an efficient way," says IBCAS researcher Zheping Xu.
The researchers say the next step is to create applications based on the flower-recognition engine so botanists can conduct their research more efficiently.
From Phys.org
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found