EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Comparison of Yolo26 and RT-DETR-L for Manga Visual Element Detection on The Manga109 Dataset

Daniel Sande Bona, Tindia Febriyati

IDEALIS : InDonEsiA journaL Information System · 31.07.2026 · 9 (2) · 314-325

DOI: 10.36080/idealis.v9i2.3842 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IDEALIS : InDonEsiA journaL Information System, online erschienen am 31.07.2026. Verfasst von Daniel Sande Bona und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic comic element detection is a critical prerequisite for manga digital analysis applications such as indexing, translation, and accessibility enhancement. Manga109 is a widely used benchmark for this task, yet the rapid progress of real-time object detectors has not been matched by a systematic comparison among state-of-the-art models in this domain, particularly between YOLO-family detectors employing Small-Target-Aware Label assignment (STAL) and transformer-based detectors such as RT-DETR. This study benchmarks YOLO26 (nano, small, and medium variants) against RT-DETR-L for detecting four comic element classes (panel, character, text, and face) on Manga109. All models were trained for 100 epochs at 1024×1024 pixels and evaluated using mAP and per-size AP following COCO conventions. YOLO26m achieves the best performance (mAP@0.5:0.95 of 0.7471), while RT-DETR-L obtains the lowest (0.7001) despite the largest parameter count and slowest inference. For small text detection, YOLO26m outperforms RT-DETR-L by 42.7% relatively, and the AP gap across object sizes narrows monotonically as model size grows, supporting the STAL design claim. RT-DETR-L also exhibits significant training instability. The main contribution is a systematic, multi-dimensional benchmark of YOLO26 against RT-DETR-L on Manga109 that evidence STAL effectiveness for small-text detection and offers practical guidance for selecting real-time detectors in manga image analysis.

Zitieren

APA

Bona, D. S., & Febriyati, T. (2026). Comparison of Yolo26 and RT-DETR-L for Manga Visual Element Detection on The Manga109 Dataset. IDEALIS : InDonEsiA journaL Information System, 9(2), 314-325. https://doi.org/10.36080/idealis.v9i2.3842

Vancouver

Bona DS, Febriyati T. Comparison of Yolo26 and RT-DETR-L for Manga Visual Element Detection on The Manga109 Dataset. IDEALIS : InDonEsiA journaL Information System. 2026;9(2):314-325. doi:10.36080/idealis.v9i2.3842

BibTeX
@article{Bona2026,
  author = {Bona, Daniel Sande and Febriyati, Tindia},
  title = {Comparison of Yolo26 and RT-DETR-L for Manga Visual Element Detection on The Manga109 Dataset},
  journal = {IDEALIS : InDonEsiA journaL Information System},
  year = {2026},
  volume = {9},
  number = {2},
  pages = {314--325},
  doi = {10.36080/idealis.v9i2.3842}
}
Kostenlos starten →