Metraipolis › archive › dc_a5bd7e2e390d
Confidence-Aware Ensemble and Long-Word Refinement for Artistic Text Recognition — arXiv:2608.29970
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29970
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:16.188Z
- SHA-256 of the archived text
f32ab71788c392c5d21c1dd59ca066df6156221db09432320fff9666edeb0941- Stable URL of this page
https://metraipolis.com/documento/dc_a5bd7e2e390d
How to cite
Confidence-Aware Ensemble and Long-Word Refinement for Artistic Text Recognition — arXiv:2608.29970 — arXiv (en), https://arxiv.org/abs/2608.29970 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5bd7e2e390d (Metraipolis archive dc_a5bd7e2e390d, sha256 f32ab71788c392c5d21c1dd59ca066df6156221db09432320fff9666edeb0941)
BibTeX
@misc{dca5bd7e2e390d,
title = {Confidence-Aware Ensemble and Long-Word Refinement for Artistic Text Recognition — arXiv:2608.29970},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29970},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5bd7e2e390d; sha256 f32ab71788c392c5d21c1dd59ca066df6156221db09432320fff9666edeb0941},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29970. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Artistic Text Recognition (ATR) remains challenging because word images often combine decorative fonts, curved layouts, object-like characters, clutter, and severe distortions. This paper studies WordArt-V1.5 as a standardized benchmark for this setting and evaluates recent scene and artistic text recognizers under a common protocol. We propose a confidence-aware ensemble that combines SVTRv2, PARSeq, and MAERec after fine-tuning on the official training split. The ensemble selects predictions using the minimum confidence over disagreement positions, emphasizing characters that separate competing hypotheses. For long words, where a single character error can invalidate the whole prediction, we add a targeted refinement stage based on Needleman-Wunsch alignment and lexicon-guided correction. On the WordArt-V1.5 Test B split, the proposed system reaches 89.90% Word Recognition Accuracy, improving the best individual fine-tuned model by 1.77 percentage points. The long-word refinement produces a modest global gain, but improves the targeted long-word subset by 2.72 percentage points. Finally, an error analysis of all remaining mistakes shows that 48.8% are associated with labeling issues, visual ambiguity, or illegible samples, highlighting the value of diagnostic reporting for future ATR benchmarks and models. Our source code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29970 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:48.097Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).