# KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark

arXiv: https://arxiv.org/abs/2410.18277 · HTML: https://mlsanity.com/paper/2410.18277/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Recursive Recurrent Nets with Attention Modeling for OCR in the Wild](https://mlsanity.com/paper/1603.03101/) (2016)
- [Text-Attentional Convolutional Neural Networks for Scene Text Detection](https://mlsanity.com/paper/1510.03283/) (2015)
- [Sequence-to-Label Script Identification for Multilingual OCR](https://mlsanity.com/paper/1708.04671/) (2017)
- [YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision](https://mlsanity.com/paper/2407.02988/) (2024)
- [TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild](https://mlsanity.com/paper/1604.02619/) (2016)
- [End-to-End Interpretation of the French Street Name Signs Dataset](https://mlsanity.com/paper/1702.03970/) (2017)
- [Cascaded Segmentation-Detection Networks for Word-Level Text Spotting](https://mlsanity.com/paper/1704.00834/) (2017)

## Built on by (most cited first, 4 of 4)

- [KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document](https://mlsanity.com/paper/2512.11849/) (2025)
- [Towards Universal Khmer Text Recognition](https://mlsanity.com/paper/2603.00702/) (2026)
- [Towards Khmer Scene Document Layout Detection](https://mlsanity.com/paper/2603.00707/) (2026)
- [Towards a Joint Khmer Text Recognition and Word Segmentation](https://mlsanity.com/paper/2608.30213/) (2026)

## Abstract (arXiv)

Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced languages. Conventional methods tailored for Latin characters often falter with non-Latin scripts due to challenges like character stacking, diacritics, and variable character widths without clear word boundaries. In this paper, we introduce the first Khmer scene-text dataset, featuring 1,544 expert-annotated images, including 997 indoor and 547 outdoor scenes. This diverse dataset includes flat text, raised text, poorly illuminated text, distant and partially obscured text. Annotations provide line-level text and polygonal bounding box coordinates for each scene. The benchmark includes baseline models for scene-text detection and recognition tasks, providing a robust starting point for future research endeavors. The KhmerST dataset is publicly accessible at https://gitlab.com/vannkinhnom123/khmerst.