Better document understanding without OCR using Donut transformer

Better document understanding without OCR using Donut transformer

Donut: Document Understanding Transformer without OCR
arXiv paper abstract https://arxiv.org/abs/2111.15664
arXiv PDF paper https://arxiv.org/pdf/2111.15664.pdf

Understanding document images (e.g., invoices) has been an important research topic

… current Visual Document Understanding (VDU) systems have come to be designed based on OCR.