Staff Layout Analysis Using the YOLO Platform

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492854" target="_blank" >RIV/00216208:11320/24:10492854 - isvavai.cz</a>

Výsledek na webu

<a href="https://sites.google.com/view/worms2024" target="_blank" >https://sites.google.com/view/worms2024</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2411.15741" target="_blank" >10.48550/arXiv.2411.15741</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Staff Layout Analysis Using the YOLO Platform

Popis výsledku v původním jazyce

Detecting staffs, systems, and measures, collectively known as layout analysis, matters for Optical Music Recognition (OMR), both because most systems today expect staff-level inputs, and because even if these are replaced by systems that can process the whole page, the staffs and systems are useful elements of OMR user interfaces and applications. It receives comparatively litle attention, which is justified, as it avoids many class imbalance, small object, and object assembly phenomena, which is what makes OMR difficult and interesting. However, the main publicly available tool for layout analysis, the MeasureDetector, is starting to age out, and off-the-shelf object detection has progressed: not just in accuracy, but also in speed. Therefore, in this paper, we bring an update on the performance of OMR layout analysis with the state-of-the-art YOLO platform. Compared to the MeausreDetector, it achieves a similar or better accuracy across both in-domain and out-of-domain tests over three different da

Název v anglickém jazyce

Staff Layout Analysis Using the YOLO Platform

Popis výsledku anglicky

Detecting staffs, systems, and measures, collectively known as layout analysis, matters for Optical Music Recognition (OMR), both because most systems today expect staff-level inputs, and because even if these are replaced by systems that can process the whole page, the staffs and systems are useful elements of OMR user interfaces and applications. It receives comparatively litle attention, which is justified, as it avoids many class imbalance, small object, and object assembly phenomena, which is what makes OMR difficult and interesting. However, the main publicly available tool for layout analysis, the MeasureDetector, is starting to age out, and off-the-shelf object detection has progressed: not just in accuracy, but also in speed. Therefore, in this paper, we bring an update on the performance of OMR layout analysis with the state-of-the-art YOLO platform. Compared to the MeausreDetector, it achieves a similar or better accuracy across both in-domain and out-of-domain tests over three different da

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů