Open access
2026
Typeset Replacement of Handwritten Text and Mathematics on Lecture Slides Using Vision-Language Models
This work asks whether a general vision-language model (VLM) can outperform purpose-built OCR and handwritten-mathematics recognisers in this data-scarce setting, and drives a pipeline that typesets the recognised annotations back onto the slide.
N. Ragavenderan, Judith Jakob, S. Manonmani
· IEEE Access · 0 citations