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

TL;DR

This paper introduces the Character Detection Matching (CDM) metric for formula recognition evaluation, which improves fairness and accuracy by matching visual character features rather than relying solely on text-based metrics.

Contribution

The paper proposes a novel image-level evaluation metric, CDM, that enhances fairness and accuracy in formula recognition assessment by incorporating spatially-aware character matching.

Findings

CDM aligns more closely with human evaluation standards.

CDM provides a fairer comparison across different models.

Experimental results show improved evaluation accuracy.

Abstract

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.