Optical Character Recognition (OCR)

It seems that they split it in two stages:

• Text Detection (using some sort of Semantic Segmentation)
• Text Recognition

https://huggingface.co/docs/transformers/model_doc/trocr#inference

I need to do this project to detect LateX.

Image to LateX

image to latex, writing my notes here

• Image-to-Markup Generation with Coarse-to-Fine Attention
• Image to Latex
• https://guillaumegenthial.github.io/sequence-to-sequence.html
• https://guillaumegenthial.github.io/image-to-latex.html