# Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching

arXiv: https://arxiv.org/abs/2409.03643 · HTML: https://mlsanity.com/paper/2409.03643/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 18 of 18)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning](https://mlsanity.com/paper/2402.12185/) (2024)
- [Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting](https://mlsanity.com/paper/2007.09482/) (2020)
- [Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models](https://mlsanity.com/paper/2312.06109/) (2023)
- [Image-to-Markup Generation with Coarse-to-Fine Attention](https://mlsanity.com/paper/1609.04938/) (2016)
- [Syntax-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2203.01601/) (2022)
- [M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis](https://mlsanity.com/paper/2305.08719/) (2023)
- [Symmetry-constrained Rectification Network for Scene Text Recognition](https://mlsanity.com/paper/1908.01957/) (2019)
- [UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition](https://mlsanity.com/paper/2404.15254/) (2024)
- [DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models](https://mlsanity.com/paper/2406.11633/) (2024)
- [When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2207.11463/) (2022)
- [Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer](https://mlsanity.com/paper/2105.02412/) (2021)
- [Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning](https://mlsanity.com/paper/2112.03603/) (2021)
- [Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions](https://mlsanity.com/paper/1901.06763/) (2019)
- [StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond](https://mlsanity.com/paper/2405.21013/) (2024)

## Built on by (most cited first, 30 of 41)

- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing](https://mlsanity.com/paper/2601.21957/) (2026)
- [olmOCR 2: Unit Test Rewards for Document OCR](https://mlsanity.com/paper/2510.19817/) (2025)
- [MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale](https://mlsanity.com/paper/2604.04771/) (2026)
- [PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training](https://mlsanity.com/paper/2606.03264/) (2026)
- [Multimodal OCR: Parse Anything from Documents](https://mlsanity.com/paper/2603.13032/) (2026)
- [Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild](https://mlsanity.com/paper/2603.04205/) (2026)
- [Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding](https://mlsanity.com/paper/2601.20430/) (2026)
- [DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM](https://mlsanity.com/paper/2512.10619/) (2025)
- [Logics-Parsing-Omni Technical Report](https://mlsanity.com/paper/2603.09677/) (2026)
- [MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios](https://mlsanity.com/paper/2603.28130/) (2026)
- [OvisOCR2 Technical Report](https://mlsanity.com/paper/2607.13639/) (2026)
- [Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs](https://mlsanity.com/paper/2512.09874/) (2025)
- [When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR](https://mlsanity.com/paper/2604.22774/) (2026)
- [How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings](https://mlsanity.com/paper/2605.07492/) (2026)
- [Infinity-Parser2 Technical Report](https://mlsanity.com/paper/2607.07836/) (2026)
- [MonkeyOCRv2: A Visual-Text Foundation Model for Document AI](https://mlsanity.com/paper/2607.11562/) (2026)
- [Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2505.23566/) (2025)
- [DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios](https://mlsanity.com/paper/2508.00311/) (2025)
- [Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing](https://mlsanity.com/paper/2603.24326/) (2026)
- [GutenOCR: A Grounded Vision-Language Front-End for Documents](https://mlsanity.com/paper/2601.14490/) (2026)
- [Efficient Document Parsing via Parallel Token Prediction](https://mlsanity.com/paper/2603.15206/) (2026)
- [ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats](https://mlsanity.com/paper/2606.01348/) (2026)
- [MORE: A Multilingual Document Parsing Benchmark and Evaluation](https://mlsanity.com/paper/2607.02956/) (2026)
- [LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR](https://mlsanity.com/paper/2607.22200/) (2026)
- [OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement](https://mlsanity.com/paper/2609.03445/) (2026)
- [Texo: Formula Recognition within 20M Parameters](https://mlsanity.com/paper/2602.17189/) (2026)
- [Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs](https://mlsanity.com/paper/2605.19043/) (2026)

## Abstract (arXiv)

Formula recognition presents significant challenges due to the complicated structure and varied notation of mathematical expressions. Despite continuous advancements in formula recognition models, the evaluation metrics employed by these models, such as BLEU and Edit Distance, still exhibit notable limitations. They overlook the fact that the same formula has diverse representations and is highly sensitive to the distribution of training data, thereby causing unfairness in formula recognition evaluation. To this end, we propose a Character Detection Matching (CDM) metric, ensuring the evaluation objectivity by designing an image-level rather than a LaTeX-level metric score. Specifically, CDM renders both the model-predicted LaTeX and the ground-truth LaTeX formulas into image-formatted formulas, then employs visual feature extraction and localization techniques for precise character-level matching, incorporating spatial position information. Such a spatially-aware and character-matching method offers a more accurate and equitable evaluation compared with previous BLEU and Edit Distance metrics that rely solely on text-based character matching. Experimentally, we evaluated various formula recognition models using CDM, BLEU, and ExpRate metrics. Their results demonstrate that the CDM aligns more closely with human evaluation standards and provides a fairer comparison across different models by eliminating discrepancies caused by diverse formula representations. Code is available at https://github.com/opendatalab/UniMERNet/tree/main/cdm.