Abstract

At present, handwriting recognition is making rapid progress, and accurate recognition of complex formulas has always been a difficulty, among which mathematical formulas are one of the representative examples. Due to the two-dimensional distribution of mathematical formulas, how to improve their accuracy has been a hot topic in handwritten recognition research. The research direction of this paper is to establish a structural system for better recognition of complex formulas in images, which is suitable for offline image recognition. The first part of this paper summarizes the methods of mathematical expression recognition and the application of various grammars. The second part introduces the system designed in this paper, including grammar, participle hypothesis generator, parsing algorithm and spatial relations.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call