17 Category Flower Dataset

Maria-Elena Nilsback and Andrew Zisserman

Overview

We have created a 17 category flower dataset with 80 images for each class. The flowers chosen are some common flowers in the UK. The images have large scale, pose and light variations and there are also classes with large varations of images within the class and close similarity to other classes. The categories can be seen in the figure below. We randomly split the dataset into 3 different training, validation and test sets. A subset of the images have been groundtruth labelled for segmentation.

Downloads

The data needed for evaluation are:

1. Dataset images
2. The data splits
3. Segmentation groundtruth data
4. &Chi² distances CVPR 2006 - distance matrices for features and segmentation used in CVPR 2006 publication.
5. &Chi² distances ICVGIP 2008 - distance matrices for features and segmentation used in ICVGIP 2008 publication.

The README file explains everything.

Class Examples

Relevant Publications