MFH: Marrying Frequency Domain with Handwritten Mathematical Expression Recognition

2025/07/01 by Huanxin Yang, Yang, Huanxin, Qiwen Wang +1
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image Retrieval and Classification Techniques #Mathematics, Computing, and Information Processing

paper · pdf · doi:10.48550/arxiv.2507.00430

openalex publication_date 2025/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Handwritten mathematical expression recognition (HMER) suffers from complex formula structures and character layouts in sequence prediction. In this paper, we incorporate frequency domain analysis into HMER and propose a method that marries frequency domain with HMER (MFH), leveraging the discrete cosine transform (DCT). We emphasize the structural analysis assistance of frequency information for recognizing mathematical formulas. When implemented on various baseline models, our network exhibits a consistent performance enhancement, demonstrating the efficacy of frequency domain information. Experiments show that our MFH-CoMER achieves noteworthy accuracyrates of 61.66%/62.07%/63.72% on the CROHME 2014/2016/2019 test sets. The source code is available at https://github.com/Hryxyhe/MFH.

Citations

• DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding
• Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition
• Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
• PatchDCT: Patch Refinement for High Quality Instance Segmentation
• When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
• CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition
• Deep Frequency Filtering for Domain Generalization
• Syntax-Aware Network for Handwritten Mathematical Expression Recognition
• Resolution-robust Large Mask Inpainting with Fourier Convolutions
• Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer
• MLP-Mixer: An all-MLP Architecture for Vision
• FcaNet: Frequency Channel Attention Networks
• DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
• Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention
• End-to-End Object Detection with Transformers
• Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are\n Failing to Reproduce Spectral Distributions
• Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition
• Watch, attend and parse: An end-to-end neural network based approach to handwritten mathematical expression recognition
• Attention Is All You Need
• Densely Connected Convolutional Networks
• Modeling Coverage for Neural Machine Translation
• A Bayesian model for recognizing handwritten mathematical expressions
• Speech Recognition with Deep Recurrent Neural Networks
• On discrete cosine transform

Related

• MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition
• Offline Handwritten Mathematical Recognition using Adversarial Learning and Transformers
• NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition
• Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions
• MathWriting+