AIbase
EN
Home
Horus OCR
H

Horus OCR

Developed by TeeA
Donut is a Transformer-based image-to-text model capable of extracting and generating textual content from images.
Image-to-Text
Transformers
#Image-to-Text#Document Understanding#Visual Question Answering
Downloads 21
Release Time : 6/12/2024

Model Overview

Donut is a vision-language model primarily designed for extracting textual information from images, suitable for tasks like document understanding and table recognition.

Model Features

Image-to-Text
Capable of extracting and generating textual content from images, suitable for document and table recognition.
Transformer-Based
Utilizes Transformer architecture with robust visual and language processing capabilities.

Model Capabilities

Image-to-Text
Document Understanding
Table Recognition

Use Cases

Document Processing
Prescription Recognition
Extracts textual information from medical prescription images.
Accurately extracts medication names and dosages from prescriptions.
Table Recognition
Table Data Extraction
Extracts structured data from tables in images.
Generates editable table-formatted data.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase