We provide here a benchmark dataset for glottis segmentation (BAGLS). It features the following specifications:

• 55750 training images and their corresponding segmentation
• 3500 test images and their corresponding segmentation

If you are interested in the dataset, please write to Prof. Dr. Michael Döllinger.

Citation of the BAGLS dataset:
P. Gomez, A. M. Kist, P. Schlegel, D. A. Berry, D. K. Chhetri, S. Dürr, M. Echternach, A. M. Johnson, S. Kniesburges, M. Kunduk, Y. Maryn, A. Schützenberger, M. Verguts, M. Döllinger. BAGLS, a multihospital benchmark for automatic glottis segmentation. Scientific Data, 7(1):186; 2020.