OCR Document Scanner

Overview

A Flutter application that extracts text and entities from images using Google ML Kit. It processes images from camera captures or gallery selections to provide accurate text recognition and entity extraction capabilities.

Demo

ocr_app_demo.mp4

Features

• Text Recognition: Uses google_mlkit_text_recognition package to extract text from images
• Entity Extraction: Implements google_mlkit_entity_extraction to identify and extract specific entities like websites, phone numbers, addresses, emails from recognized text
• Multiple Image Sources: Supports capturing images with device camera or selecting from gallery
• User-Friendly Interface: Simple UI for easy interaction with the OCR functionality

Tech Stack

• Flutter (3.5.4+)
• State Management: Riverpod
• ML APIs: Google ML Kit (Text Recognition, Entity Extraction)

Installation

1. Clone the repository

   git clone https://github.com/adilazhar/ocr-document-scanner.git
   

2. Navigate to the project directory

   cd ocr-document-scanner
   

3. Get all dependencies

   flutter pub get
   

4. Run the app on your preferred device

   flutter run
   

Learning Experience

This project was built as an exploration of Google ML Kit libraries, providing practical experience with text recognition and entity extraction capabilities in mobile applications.