作者: Chuanjun Li , Robert Zeleznik , Timothy Miller , Joseph J. LaViola
DOI: 10.1109/ICPR.2008.4761825
关键词: Symbol (chemistry) 、 Column (database) 、 Arithmetic 、 Ellipse 、 Artificial intelligence 、 Matrix decomposition 、 Handwriting recognition 、 Computer science 、 Context (language use) 、 Matrix (mathematics) 、 Pattern recognition
摘要: We present an online system for recognizing handwritten mathematical matrices in the context of interactive computational tool called MathPaper. Automatic segmentation and recognition multiple expressions are supported based on a spacing algorithm that leverages recognized symbol identities, sizes, relative locations individual symbols. Matrices with ellipses can be instantiated non-ellipsis elements. Both well- non-well-formed also recognized. Matrix elements any general including imbedded matrices. Our recognizer addresses poor column alignment problem matrices, allows slight horizontal overlaps between neighboring columns different rows.