Abstract

The orchid flower dataset was selected from the northern part of Thailand. The dataset contains Thai native orchid flowers, and each class contains at least 20 samples. The orchid dataset including 52 species and the visual characteristics of the flower are varying in terms of shape, color, texture, size, and the other parts of the orchid plant like a leaf, inflorescence, roots, and surroundings. All images are taken from many devices such as a digital camera, a mobile phone, and other equipment. The orchids dataset contains 3,559 images from 52 categories.

Instructions:

Download links:

Test - https://drive.google.com/open?id=1AGYAHLJFS4qiLyNLznHDKtWZx0d4RCK1

Train - https://drive.google.com/open?id=1AHwLH3-P8eWAXgXMs-FU2Ni6b2YMO5yY

This dataset is only for research purposes.

Please remember cited correctly the paper: "Orchids Classification Using Spatial Transformer Network with Adaptive Scaling"

BibTeX:

@inproceedings{sarachai2019orchids,

title={Orchids Classification Using Spatial Transformer Network with Adaptive Scaling},

author={Sarachai, Watcharin and Bootkrajang, Jakramate and Chaijaruwanich, Jeerayut and Somhom, Samerkae},

booktitle={International Conference on Intelligent Data Engineering and Automated Learning – IDEAL 2019},

pages={1--10},