Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition

TL;DR

This paper introduces a stroke constrained attention network (SCAN) that leverages stroke-level information for improved online and offline handwritten mathematical expression recognition, achieving state-of-the-art results.

Contribution

The novel SCAN model uses stroke-level units for better alignment and recognition in HMER, integrating multi-modal data at the encoder stage for enhanced performance.

Findings

Achieves state-of-the-art accuracy on CROHME benchmark.

Effectively fuses multi-modal information at the encoder level.

Reduces symbol segmentation difficulty through stroke grouping.

Abstract

In this paper, we propose a novel stroke constrained attention network (SCAN) which treats stroke as the basic unit for encoder-decoder based online handwritten mathematical expression recognition (HMER). Unlike previous methods which use trace points or image pixels as basic units, SCAN makes full use of stroke-level information for better alignment and representation. The proposed SCAN can be adopted in both single-modal (online or offline) and multi-modal HMER. For single-modal HMER, SCAN first employs a CNN-GRU encoder to extract point-level features from input traces in online mode and employs a CNN encoder to extract pixel-level features from input images in offline mode, then use stroke constrained information to convert them into online and offline stroke-level features. Using stroke-level features can explicitly group points or pixels belonging to the same stroke, therefore reduces the difficulty of symbol segmentation and recognition via the decoder with attention mechanism. For multi-modal HMER, other than fusing multi-modal information in decoder, SCAN can also fuse multi-modal information in encoder by utilizing the stroke based alignments between online and offline modalities. The encoder fusion is a better way for combining multi-modal information as it implements the information interaction one step before the decoder fusion so that the advantages of multiple modalities can be exploited earlier and more adequately when training the encoder-decoder model. Evaluated on a benchmark published by CROHME competition, the proposed SCAN achieves the state-of-the-art performance.