Szczegóły publikacji
Opis bibliograficzny
Fingerspelling recognition using synthetic images and deep transfer learning / Nguyen Tu Nam, Shinji Sako, Bogdan KWOLEK // W: ICMV 2020 : thirteenth International Conference on Machine Vision : 2–6 November 2020, Rome, Italy / eds. Wolfgang Osten, Dmitry P. Nikolaev, Jianhong Zhou. — Bellingham : SPIE, cop. 2020. — (Proceedings of SPIE / The International Society for Optical Engineering ; ISSN 0277-786X ; vol. 11605). — ISBN: 9781510640405 ; e-ISBN: 9781510640412. — S. 116051U-1–116051U-8. — Bibliogr. s. 116051U-7–116051U-8, Abstr.
Autorzy (3)
- Nguyen Tu Nam
- Sako Shinji
- AGHKwolek Bogdan
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 135382 |
|---|---|
| Data dodania do BaDAP | 2022-01-14 |
| Tekst źródłowy | URL |
| DOI | 10.1117/12.2587592 |
| Rok publikacji | 2020 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | SPIE - The International Society for Optics and Photonics |
| Konferencja | International Conference on Machine Vision 2020 |
| Czasopismo/seria | Proceedings of SPIE / The International Society for Optical Engineering |
Abstract
Although gesture recognition has been intensely studied for decades, it is still a challenging research topic due to difficulties posed by background complexity, occlusion, viewpoint, lighting changes, the deformable and articulated nature of hands, etc. Numerous studies have shown that extending the training dataset with real images about synthetic images improves the recognition accuracy. However, little work is devoted to demonstrate what improvements in recognition can be achieved thanks to transferring the style onto synthetically generated images from the real gestures. In this paper, we propose a novel method for Japanese fingerspelling recognition using both real and synthetic images generated on the basis of a 3D hand model. We propose to employ a neural style transfer to include information from real images onto synthetically generated dataset. We demonstrate experimentally that neural style transfer and discriminative layer training applied to training deep neural models allow obtaining considerable gains in the recognition accuracy.
