Local and Global Graph Modeling with Edge-weighted Graph Attention Network for Handwritten Mathematical Expression Recognition

TEX), handwritten mathematical expressions offer greater ease of use for humans but pose a greater challenge for machine recognition due to variations in individual writing styles and writing habits. Handwritten Mathematical Expression Recognition (HMER), which involves converting handwritten math into markup language for easier computer processing and rendering, is a challenging promising field with various of potential applications. Compared to Optical Character Recognition (OCR), recognizing handwritten manuscripts is more challenging due to the wide variation in handwriting styles. HMER not only faces the common challenges of handwriting recognition but also has to deal with the added complexity of interpreting the 2D structure of mathematical expressions. According to different processing objective, HMER can be categorized into Online HMER and Offline HMER. Online HMER processes a sequence of temporal trajectories captured by digital devices like tablets and digital pens. Online data is segmented into individual strokes based on pen-down and pen-up interruption. While offline expressions are static images collected by scanner, camera or smartphone.