D

Donutlicenses3v3

Developed by felipebandeira
This model is used to extract structured information from EU driver's license images and return the results in JSON format.
Downloads 54
Release Time : 8/16/2023

Model Overview

A vision-language model based on Transformer or OCR technology, specifically designed to process EU driver's license images, extract key information, and convert it into structured data.

Model Features

High-Precision Information Extraction
Achieves 98% accuracy on the validation set, accurately identifying key information on driver's licenses.
Standardized Output
Returns extracted information in JSON format for easy integration into various systems.
Optimized Image Processing
Specially optimized for high-resolution driver's license images of 1192x772 size.

Model Capabilities

Driver's License Image Analysis
Text Information Extraction
Structured Data Conversion

Use Cases

Identity Verification
Online Driver's License Verification
Automatically verifies user driver's license information in online services.
Reduces manual verification time and improves processing efficiency.
Data Entry
Driver's License Information Digitization
Automatically converts paper driver's license information into digital records.
63.93% accuracy in real driver's license recognition.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase