# From Press to Pixels: Evolving Urdu Text Recognition

arXiv: https://arxiv.org/abs/2505.13943 · HTML: https://mlsanity.com/paper/2505.13943/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 29 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 5 of 5)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024)
- [Types, Tokens, and Hapaxes: A New Heap's Law](https://mlsanity.com/paper/1901.00521/) (2018)
- [Handwritten Urdu Character Recognition using 1-Dimensional BLSTM Classifier](https://mlsanity.com/paper/1705.05455/) (2017)

## Abstract (arXiv)

This paper presents a comparative analysis of Large Language Models (LLMs) and traditional Optical Character Recognition (OCR) systems on Urdu newspapers, addressing challenges posed by complex multi-column layouts, low-resolution scans, and the stylistic variability of the Nastaliq script. To handle these challenges, we fine-tune YOLOv11x models for article- and column-level text block extraction and train a SwinIR-based super-resolution module that enhances image quality for downstream text recognition, improving accuracy by an average of 50%. We further introduce the Urdu Newspaper Benchmark (UNB), a manually annotated dataset for Urdu OCR comprising 829 paragraph images with a total of 9,982 sentences. Using UNB and the OpenITI corpus, we conduct a systematic comparison between traditional CNN+RNN-based OCR systems and modern LLMs, presenting detailed insertion, deletion, and substitution error analyses alongside character-level confusion patterns. We find that Gemini-2.5-Pro achieves the best performance on UNB (WER 0.133), while fine-tuning GPT-4o on just 500 in-domain samples yields a 6.13% absolute WER improvement, demonstrating the adaptability of LLMs to low-resource, morphologically complex scripts like Urdu. The UNB dataset and fine-tuned models are publicly available at https://github.com/sameearif/urdu-newspaper-benchmark.