LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration
Not on the map. Why?
Abstract (arXiv)
Maltese has substantial text corpora and pretrained language models, but paragraph-scale OCR training data remains scarce; NOMOCRAT provides 57 verified annotated pages. LV-ROVER-MLT combines synthetic fine-tuning of Tesseract~5 with five complementary recognition streams and lexicon-gated word-level arbitration adapted to Maltese diacritics and hyphenation. In the DocEng~2026 Maltese OCR competition, the system placed first with held-out CER 0.0074; the next-ranked submission scored 0.0161 and NOMOCRAT scored 0.0163. The same approach produced a significant improvement over stock Tesseract on Luxembourgish, while the Hungarian result was inconclusive. A 36,803-pair Maltese OCR corpus constructed from EUR-Lex and Wikipedia provides an additional paragraph-level resource. Code, model weights, and corpus data are public.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 26 references that are in the map. First posted on arXiv 30 Jun 2026.
Builds on
8 of 26 references.
References · 8
- 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
- 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
- 2021SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Modelscited by 43
- 2018Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognitioncited by 15
- 2022Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltesecited by 14
- 2017Morphological Analysis for the Maltese Language: The Challenges of a Hybrid Systemcited by 2
- 2017LV-ROVER: Lexicon Verified Recognizer Output Voting Error Reductioncited by 1
- 2025Synthetic Document Question Answering in Hungariancited by 1
Built on by
Not cited yet.