EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks

Hakan Temiz

The European Journal of Research and Development · 2022

DOI: 10.56038/ejrnd.v2i2.23 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The European Journal of Research and Development, 2022. Verfasst von Hakan Temiz. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Images cannot always be expected to come in a certain standard format and orientation. Deep networks need to be trained to take into account unexpected variations in orientation or format. For this purpose, training data should be enriched to include different conditions. In this study, the effects of data enrichment on the performance of deep networks in the super resolution problem were investigated experimentally. A total of six basic image transformations were used for the enrichment procedures. In the experiments, two deep network models were trained with variants of the ILSVRC2012 dataset enriched by these six image transformation processes. Considering a single image transformation, it has been observed that the data enriched with 180 degree rotation provides the best results. The most unsuccessful result was obtained when the models were trained on the enriched data generated by the flip upside down process. Models scored highest when trained with a mix of all transformations.

Zitieren

APA

Temiz, H. (2022). Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks. The European Journal of Research and Development. https://doi.org/10.56038/ejrnd.v2i2.23

Vancouver

Temiz H. Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks. The European Journal of Research and Development. 2022. doi:10.56038/ejrnd.v2i2.23

BibTeX
@article{Temiz2022,
  author = {Temiz, Hakan},
  title = {Effects of Data Enrichment with Image Transformations on the Performance of Deep Networks},
  journal = {The European Journal of Research and Development},
  year = {2022},
  doi = {10.56038/ejrnd.v2i2.23}
}
Kostenlos starten →