DeepScores : a dataset for segmentation, detection and classification of tiny objects

Tuggener, Lukas; Elezi, Ismail; Schmidhuber, Jürgen; Pelillo, Marcello; Stadelmann, Thilo

doi:10.1109/ICPR.2018.8545307

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-4255

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	DeepScores : a dataset for segmentation, detection and classification of tiny objects
Authors:	Tuggener, Lukas Elezi, Ismail Schmidhuber, Jürgen Pelillo, Marcello Stadelmann, Thilo
DOI:	10.1109/ICPR.2018.8545307 10.21256/zhaw-4255
Proceedings:	2018 24th International Conference on Pattern Recognition (ICPR)
Page(s):	1 3704
Pages to:	6 3709
Conference details:	24th International Conference on Pattern Recognition (ICPR 2018), Beijing, China, 20-28 August 2018
Issue Date:	2018
Publisher / Ed. Institution:	IEEE
ISBN:	978-1-5386-3788-3
Language:	English
Subjects:	Optical music recognition; Deep learning; Computer vision; Data set
Subject (DDC):	005: Computer programming, programs and data
Abstract:	We present the DeepScores dataset with the goal of advancing the state-of-the-art in small object recognition by placing the question of object recognition in the context of scene understanding. DeepScores contains high quality images of musical scores, partitioned into 300,000 sheets of written music that contain symbols of different shapes and sizes. With close to a hundred million small objects, this makes our dataset not only unique, but also the largest public dataset. DeepScores comes with ground truth for object classification, detection and semantic segmentation. DeepScores thus poses a relevant challenge for computer vision in general, and optical music recognition (OMR) research in particular. We present a detailed statistical analysis of the dataset, comparing it with other computer vision datasets like PASCAL VOC, SUN, SVHN, ImageNet, MS-COCO, as well as with other OMR datasets. Finally, we provide baseline performances for object classification, intuition for the inherent difficulty that DeepScores poses to state-of-the-art object detectors like YOLO or R-CNN, and give pointers to future research based on this dataset.
URI:	https://digitalcollection.zhaw.ch/handle/11475/6082
Fulltext version:	Submitted version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Computer Science (InIT)
Published as part of the ZHAW project:	DeepScore: Digitales Notenpult mit musikalischem Verständnis durch Active Sheet Technologie
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
ICPR_2018a.pdf		1.62 MB	Adobe PDF	View/Open

Show full item record

Tuggener, L., Elezi, I., Schmidhuber, J., Pelillo, M., & Stadelmann, T. (2018). DeepScores : a dataset for segmentation, detection and classification of tiny objects [Conference paper]. 2018 24th International Conference on Pattern Recognition (ICPR), 1–3704. https://doi.org/10.1109/ICPR.2018.8545307

Tuggener, L. et al. (2018) ‘DeepScores : a dataset for segmentation, detection and classification of tiny objects’, in 2018 24th International Conference on Pattern Recognition (ICPR). IEEE, pp. 1–3704–6–3709. Available at: https://doi.org/10.1109/ICPR.2018.8545307.

L. Tuggener, I. Elezi, J. Schmidhuber, M. Pelillo, and T. Stadelmann, “DeepScores : a dataset for segmentation, detection and classification of tiny objects,” in 2018 24th International Conference on Pattern Recognition (ICPR), 2018, pp. 1–3704–6–3709. doi: 10.1109/ICPR.2018.8545307.

TUGGENER, Lukas, Ismail ELEZI, Jürgen SCHMIDHUBER, Marcello PELILLO und Thilo STADELMANN, 2018. DeepScores : a dataset for segmentation, detection and classification of tiny objects. In: 2018 24th International Conference on Pattern Recognition (ICPR). Conference paper. IEEE. 2018. S. 1–3704–6–3709. ISBN 978-1-5386-3788-3

Tuggener, Lukas, Ismail Elezi, Jürgen Schmidhuber, Marcello Pelillo, and Thilo Stadelmann. 2018. “DeepScores : A Dataset for Segmentation, Detection and Classification of Tiny Objects.” Conference paper. In 2018 24th International Conference on Pattern Recognition (ICPR), 1–3704. IEEE. https://doi.org/10.1109/ICPR.2018.8545307.

Tuggener, Lukas, et al. “DeepScores : A Dataset for Segmentation, Detection and Classification of Tiny Objects.” 2018 24th International Conference on Pattern Recognition (ICPR), IEEE, 2018, pp. 1–3704, https://doi.org/10.1109/ICPR.2018.8545307.