Boutros, Fadi ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan (2019)
Eye-MMS: Miniature Multi-Scale Segmentation Network of Key Eye-Regions in Embedded Applications.
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea (South) (27.10.2019-28.10.2019)
doi: 10.1109/ICCVW.2019.00452
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Segmentation of the iris or sclera is an essential processing block in ocular biometric systems. However, humancomputer interaction, as in VR/AR applications, requires multiple region segmentation to enable smoother interaction and eye-tracking. Such application does not only demand highly accurate and generalizable segmentation, it requires such segmentation model to be appropriate for the limited computational power of embedded systems. This puts strict limits on the size of the deployed deep learning models. This work presents a miniature multi-scale segmentation network consisting of inter-connected convolutional modules. We present a baseline multi-scale segmentation network and modify it to reduce its parameters by more than 80 times, while reducing its accuracy by less than 3%, resulting in our Eye-MMS model containing only 80k parameters. This work is developed on the OpenEDS database and is conducted in preparation for the OpenEDS Semantic Segmentation Challenge.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2019 |
| Autor(en): | Boutros, Fadi ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan |
| Art des Eintrags: | Bibliographie |
| Titel: | Eye-MMS: Miniature Multi-Scale Segmentation Network of Key Eye-Regions in Embedded Applications |
| Sprache: | Englisch |
| Publikationsjahr: | 2019 |
| Veranstaltungstitel: | 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) |
| Veranstaltungsort: | Seoul, Korea (South) |
| Veranstaltungsdatum: | 27.10.2019-28.10.2019 |
| DOI: | 10.1109/ICCVW.2019.00452 |
| URL / URN: | https://ieeexplore.ieee.org/document/9022048 |
| Kurzbeschreibung (Abstract): | Segmentation of the iris or sclera is an essential processing block in ocular biometric systems. However, humancomputer interaction, as in VR/AR applications, requires multiple region segmentation to enable smoother interaction and eye-tracking. Such application does not only demand highly accurate and generalizable segmentation, it requires such segmentation model to be appropriate for the limited computational power of embedded systems. This puts strict limits on the size of the deployed deep learning models. This work presents a miniature multi-scale segmentation network consisting of inter-connected convolutional modules. We present a baseline multi-scale segmentation network and modify it to reduce its parameters by more than 80 times, while reducing its accuracy by less than 3%, resulting in our Eye-MMS model containing only 80k parameters. This work is developed on the OpenEDS database and is conducted in preparation for the OpenEDS Semantic Segmentation Challenge. |
| Freie Schlagworte: | Biometrics Head mounted displays Image segmentation |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 17 Apr 2020 10:01 |
| Letzte Änderung: | 17 Apr 2020 10:01 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum