Description
The Wild-Anim dataset available from this page consists of 5 classes that contains uniformly distributed images examples of wild animals. In total, the dataset contains 5000 images. The images are slightly anamorphic in their representation. These images were passed as input to both deep learning and classical computer vision methods for carrying out animal recognition task. In our experiments, we considered two subsets each containing 1000 examples (non-repetitive images) from the total image examples.
| Datum van beschikbaarheid | 25-mrt.-2019 |
|---|---|
| Uitgever | DataverseNL |
| Datum van data-aanmaak | okt.-2015 |
Onderzoekersoutput
- 2 Conference contribution
-
Comparative study between deep learning and bag of visual words for wild-animal recognition
Okafor, E., Pawara, P., Karaaba, M., Surinta, O., Codreanu, V., Schomaker, L. & Wiering, M., 9-feb.-2017, 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc., (2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016).Onderzoeksoutput › Academic › peer review
Open AccessBestand43 Citaten (Scopus)394 Downloads (Pure) -
Comparative Study Between Deep Learning and Bag of Visual Words for Wild-Animal Recognition
Okafor, E., Pawara, P., Karaaba, M., Surinta, O., Codreanu, V., Schomaker, L. & Wiering, M., 2016, IEEE Symposium Series on Computational Intelligence. Athens, Greece: IEEE, 9 blz.Onderzoeksoutput › Academic › peer review
Open AccessBestand
Citeer dit
- DataSetCite