RealScore – Scanning of Real-World Sheet Music for a Digital Music Stand
Beschreibung
ScorePad’s sheet music scanning service works for high quality input; to scale up business, it should work as well for smartphone pictures, used sheets etc. Project RealScore enhances the successful predecessor project by making deep learning adapt to unseen data through unsupervised learning.
Eckdaten
Co-Projektleitung
Projektteam
Raphael Emberger, Adhiraj Ghosh, Dr. Javier Montoya, Pascal Sager, Yvan Putra Satyawan, Lukas Tuggener
Projektpartner
ScorePad AG
Projektstatus
abgeschlossen, 09/2019 - 05/2022
Institut/Zentrum
Institut für Informatik (InIT); Centre for Artificial Intelligence (CAI)
Drittmittelgeber
Innovationsprojekt / Projekt Nr. 34301.1 IP-ICT
Projektvolumen
870'000 CHF
Weiterführende Dokumente und Links
Publikationen
-
Is it enough to optimize CNN architectures on ImageNet?
2024 Tuggener, Lukas; Schmidhuber, Jürgen; Stadelmann, Thilo
-
The DeepScoresV2 dataset and benchmark for music object detection
2024 Tuggener, Lukas; Satyawan, Yvan Putra; Pacha, Alexander; Schmidhuber, Jürgen; Stadelmann, Thilo
-
Real world music object recognition
2024 Tuggener, Lukas; Emberger, Raphael; Ghosh, Adhiraj; Sager, Pascal; Satyawan, Yvan Putra; Montoya, Javier; Goldschagg, Simon; Seibold, Florian; Gut, Urs; Ackermann, Philipp; Schmidhuber, Jürgen; Stadelmann, Thilo