102 Flower Category Database

This set contains images of flowers belonging to 102 different categories. The images were acquired by searching the web and taking pictures. There are a minimum of 40 images for each category.

The images are contained in the file 102flowers.tgz and the image labels in imagelabels.mat.

We provide 4 distance matrices. D_hsv, D_hog, D_siftint, D_siftbdy. These are the chi^2 distance matrices used in the publication below.

The database was used in:

Nilsback, M-E. and Zisserman, A. Automated flower classification over a large number of classes. Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (2008) http://www.robots.ox.ac.uk/~vgg/publications/papers/nilsback08.{pdf,ps.gz}.

Datasplit

The datasplits used in this paper are specified in setid.mat.

The results in the paper are produced on a 103 category database. The two categories labeled Petunia have since been merged since they are the same. There is a training file (trnid), a validation file (valid) and a testfile (tstid).

Segmentation Images

We provide the segmentations for the images in the file 102segmentations.tgz

More details can be found in:

Nilsback, M-E. and Zisserman, A. Delving into the whorl of flower segmenation. Proceedings of the British Machine Vision Conference (2007) http:www.robots.ox.ac.uk/~vgg/publications/papers/nilsback07.(pdf,ps.gz). .

History

version 1.1 - Two petunia categories merged into one.