PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer

10 Jul 2024  ·  Tongkun Guan, Chengyu Lin, Wei Shen, Xiaokang Yang ·

Handwritten Mathematical Expression Recognition (HMER) has wide applications in human-machine interaction scenarios, such as digitized education and automated offices. Recently, sequence-based models with encoder-decoder architectures have been commonly adopted to address this task by directly predicting LaTeX sequences of expression images. However, these methods only implicitly learn the syntax rules provided by LaTeX, which may fail to describe the position and hierarchical relationship between symbols due to complex structural relations and diverse handwriting styles. To overcome this challenge, we propose a position forest transformer (PosFormer) for HMER, which jointly optimizes two tasks: expression recognition and position recognition, to explicitly enable position-aware symbol feature representation learning. Specifically, we first design a position forest that models the mathematical expression as a forest structure and parses the relative position relationships between symbols. Without requiring extra annotations, each symbol is assigned a position identifier in the forest to denote its relative spatial position. Second, we propose an implicit attention correction module to accurately capture attention for HMER in the sequence-based decoder architecture. Extensive experiments validate the superiority of PosFormer, which consistently outperforms the state-of-the-art methods 2.03%/1.22%/2.00%, 1.83%, and 4.62% gains on the single-line CROHME 2014/2016/2019, multi-line M2E, and complex MNE datasets, respectively, with no additional latency or computational cost. Code is available at https://github.com/SJTU-DeepVisionLab/PosFormer.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Handwritten Mathmatical Expression Recognition CROHME 2014 PosFormer ExpRate 60.45 # 4
Handwritten Mathmatical Expression Recognition CROHME 2016 PosFormer ExpRate 60.94 # 1
Handwritten Mathmatical Expression Recognition CROHME 2019 PosFormer ExpRate 62.22 # 1
Handwritten Mathmatical Expression Recognition HME100K PosFormer ExpRate 69.51 # 1

Methods


No methods listed for this paper. Add relevant methods here