Szczegóły publikacji
Opis bibliograficzny
Deep neural image denoising / Michał Koziarski, Bogusław CYGANEK // W: Computer vision and graphics [Dokument elektroniczny] : international conference : ICCVG 2016 : Warsaw, Poland, September 19–21, 2016 : proceedings / eds. Leszek J. Chmielewski [et al.]. — Wersja do Windows. — Dane tekstowe. — [Cham] : Springer International Publishing, cop. 2016. — Dysk Flash. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 9972). — ISBN: 978-3-319-46417-6; e-ISBN: 978-3-319-46418-3. — S. 163–173. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 171–173, Abstr.
Autorzy (2)
- Koziarski Michał
- AGHCyganek Bogusław
Dane bibliometryczne
| ID BaDAP | 101463 |
|---|---|
| Data dodania do BaDAP | 2016-12-05 |
| DOI | 10.1007/978-3-319-46418-3_15 |
| Rok publikacji | 2016 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | International Conference on Computer Vision and Graphics 2014 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Presence of noise poses a common problem in image recognition tasks. In this paper we propose and analyse architecture of convolutional neural network capable of image denoising. We evaluate its performance with various types of artificial distortions present, with both known and unknown noise conditions. Finally, we measure how including denoising procedure in image recognition pipeline influences classification accuracy.
