Dataset

This dataset was created by datajameson

Contents

Results reported for the Oxford Flower 17 and Oxford Flower 102 datasets using local features along with the methods detailed for each processing step.

The Oxford Flowers 102 dataset is a consistent of 102 flower categories commonly occurring in the United Kingdom. Each class consists of between 40 and 258 images. The images have large scale, pose and light variations. In addition, there are categories that have large variations within the category and several very similar categories.

The dataset is divided into a training set, a validation set and a test set. The training set and validation set each consist of 10 images per class (totalling 1020 images each). The test set consists of the remaining 6149 images (minimum 20 per class).

Note: The dataset by default comes with a test size larger than the train size. For more info see this issue.

To use this dataset:

import tensorflow_datasets as tfds

ds = tfds.load('oxford_flowers102', split='train')
for ex in ds.take(4):
 print(ex)

See the guide for more informations on tensorflow_datasets.

https://storage.googleapis.com/tfds-data/visualization/fig/oxford_flowers102-2.1.1.png" alt="Visualization" width="500px">

Class averaged classification accuracies on the OF17, the OF102, and the JF30 datasets using DoH-OpponentSIFT and an increasing amount of pyramidal levels (one to three).

Class averaged classification accuracy of the studied shape and color descriptors for the OF17, the OF102, and the JF30 datasets.

Computed using SIFT in combination with the Hessian and Harris-based detectors without and with (values in brackets) affine shape estimation.

Median amount of local features extracted per image for the OF17, the OF102, and the JF30 dataset.