Authors

Thierry Pinheiro Moreira

E-mail: thierrypin [at] liv [dot] ic [dot] unicamp [dot] br

Rafael de Oliveira Werneck

Website: Rafael Werneck

E-mail: rafael [dot] werneck [at] ic [dot] unicamp [dot] br

Mauricio Lisboa Perez

Website: Mauricio Perez

E-mail: mauricio [dot] perez [at] students [dot] ic [dot] unicamp [dot] br

Eduardo Valle

Website: Eduardo Valle

E-mail: dovalle [at] dca [dot] fee [dot] unicamp [dot] br




Overview

We acquired the Flickr-dog dataset 6 by selecting dog photos from Flickr available under Creative Commons licenses. We cropped the dog faces, rotated them to align the eyes horizontally, and resized them to 250x250 pixels.

We selected dogs from two breeds: pugs and huskies. Those breeds were selected to represent the different degrees of challenge: we expected pugs to be difficult to identify, and huskies to be easy. For each breed, we found 21 individuals, each with at least 5 photos. We labeled the individuals by interpreting picture metadata (user, title, description, timestamps, etc.), and double checked with our own ability to identify the dogs.

Altogether, the Flickr-dog dataset has 42 classes and 374 photos.




Download

Flickr-dog dataset download




Examples

A sample of Flickr-dog dataset. We acquired 374 photos licensed under Creative Commons from Flickr, representing 2 breeds (pugs and huskies), 21 individuals per breed, and at least 5 photos per individual. The choice of breeds intended to reflect a difficult case (pugs) and an easy one (huskies).



Protocol

The protocol was a stratified k-fold cross-validation, that splits the dataset into k folds, preserving as much as possible the class proportions among the folds. We used 10 folds, with nine folds for training, and one for testing.

Our main metric is the balanced average accuracy, which is the arithmetic mean of the accuracy for each of the classes. We also employ confusion matrices for detailed analyses of the results.

For the retrieval experiment, we employ a top-k recall, which ranks the classification scores for all classes, and counts the test as successful if the right class is among the highest k scores.




Publication

Moreira, T.P., Perez, M.L., Werneck, R., Valle, E. Multimedia Tools and Applications (2017) 76: 15325. doi:10.1007/s11042-016-3824-1 DOI, Bibtex




Results

 
Method Flickr-dog
EigenFaces 33.9
FisherFaces 22.7
LBPH 43.2
Sparse 39.9
BARKflickr 67.6
WOOF 66.9
Balanced accuracies (in %) for all evaluated methods in both datasets.




Design by Nicolas Fafchamps