# SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models

arXiv: https://arxiv.org/abs/2107.09313 · HTML: https://mlsanity.com/paper/2107.09313/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 20 Jul 2021.

## Builds on (most cited first, 6 of 6)

- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Scene Text Detection and Recognition: The Deep Learning Era](https://mlsanity.com/paper/1811.04256/) (2018)
- [UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World](https://mlsanity.com/paper/2003.10608/) (2020)
- [SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds](https://mlsanity.com/paper/1907.06007/) (2019)

## Built on by (most cited first, 30 of 43)

- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models](https://mlsanity.com/paper/2402.05935/) (2024)
- [Improving Diffusion Models for Scene Text Editing with Dual Encoders](https://mlsanity.com/paper/2304.05568/) (2023)
- [DiffUTE: Universal Text Editing Diffusion Model](https://mlsanity.com/paper/2305.10825/) (2023)
- [Revisiting Scene Text Recognition: A Data Perspective](https://mlsanity.com/paper/2307.08723/) (2023)
- [DTrOCR: Decoder-only Transformer for Optical Character Recognition](https://mlsanity.com/paper/2308.15996/) (2023)
- [Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator](https://mlsanity.com/paper/2205.00146/) (2022)
- [Self-supervised Implicit Glyph Attention for Text Recognition](https://mlsanity.com/paper/2203.03382/) (2022)
- [ICDAR 2023 Competition on Hierarchical Text Detection and Recognition](https://mlsanity.com/paper/2305.09750/) (2023)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering](https://mlsanity.com/paper/2602.20903/) (2026)
- [Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis](https://mlsanity.com/paper/2310.17674/) (2023)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation](https://mlsanity.com/paper/2305.00795/) (2023)
- [A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data](https://mlsanity.com/paper/2209.02397/) (2022)
- [On Web-based Visual Corpus Construction for Visual Document Understanding](https://mlsanity.com/paper/2211.03256/) (2022)
- [TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model](https://mlsanity.com/paper/2403.10047/) (2024)
- [DocSynthv2: A Practical Autoregressive Modeling for Document Generation](https://mlsanity.com/paper/2406.08354/) (2024)
- [Analyzing Font Style Usage and Contextual Factors in Real Images](https://mlsanity.com/paper/2306.12050/) (2023)
- [CREPE: Coordinate-Aware End-to-End Document Parser](https://mlsanity.com/paper/2405.00260/) (2024)
- [Weakly Supervised Scene Text Generation for Low-resource Languages](https://mlsanity.com/paper/2306.14269/) (2023)
- [Selective Scene Text Removal](https://mlsanity.com/paper/2309.00410/) (2023)
- [PSGText: Stroke-Guided Scene Text Editing with PSP Module](https://mlsanity.com/paper/2310.13366/) (2023)
- [What Text Design Characterizes Book Genres?](https://mlsanity.com/paper/2402.16356/) (2024)
- [UnSupDLA: Towards Unsupervised Document Layout Analysis](https://mlsanity.com/paper/2406.06236/) (2024)
- [MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation](https://mlsanity.com/paper/2503.02799/) (2025)
- [synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier](https://mlsanity.com/paper/2601.16113/) (2026)
- [What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution](https://mlsanity.com/paper/2602.06450/) (2026)
- [GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts](https://mlsanity.com/paper/2604.12978/) (2026)
- [Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods](https://mlsanity.com/paper/2606.24484/) (2026)

## Abstract (arXiv)

For successful scene text recognition (STR) models, synthetic text image generators have alleviated the lack of annotated text images from the real world. Specifically, they generate multiple text images with diverse backgrounds, font styles, and text shapes and enable STR models to learn visual patterns that might not be accessible from manually annotated data. In this paper, we introduce a new synthetic text image generator, SynthTIGER, by analyzing techniques used for text image synthesis and integrating effective ones under a single algorithm. Moreover, we propose two techniques that alleviate the long-tail problem in length and character distributions of training data. In our experiments, SynthTIGER achieves better STR performance than the combination of synthetic datasets, MJSynth (MJ) and SynthText (ST). Our ablation study demonstrates the benefits of using sub-components of SynthTIGER and the guideline on generating synthetic text images for STR models. Our implementation is publicly available at https://github.com/clovaai/synthtiger.