Preprint
Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil
Nevidu Jayatilleke, arXiv, 2025
Read the originalRead on October 17, 2026
- What it is
- A preprint comparing OCR systems on Sinhala and Tamil text. It defines the character error rate and the word error rate it uses for scoring OCR output.
- How much weight it carries
- Single preprint on two low-resourced scripts. Its metric definitions are standard and match the edit-distance arithmetic used elsewhere, but the study's results should not be generalized to other languages.
Facts taken from this source
- For OCR evaluation, character error rate is based on Levenshtein distance: the minimum number of character substitutions, deletions and insertions needed to turn the ground truth text into the OCR output, divided by the number of characters in the ground truth.
“It is based on the concept of Levenshtein distance, which measures the minimum number of character-level operations (substitutions, deletions, and insertions) necessary to transform the ground truth text into the output generated by OCR.” (Evaluation Mechanism)