https://github.com/Erfaniaa/Persian-OCR

Optical character recognition of Farsi and Arabic letters
https://github.com/Erfaniaa/Persian-OCR

computer-vision convolutional-neural-networks deep-learning delphi farsi image-processing neural-networks ocr optical-character-recognition persian persian-ocr

Last synced: about 2 months ago
JSON representation

Optical character recognition of Farsi and Arabic letters

• Host: GitHub
• URL: https://github.com/Erfaniaa/Persian-OCR
• Owner: Erfaniaa
• Created: 2018-06-18T22:35:55.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2021-01-14T22:54:27.000Z (over 3 years ago)
• Last Synced: 2024-05-29T03:26:39.392Z (4 months ago)
• Topics: computer-vision, convolutional-neural-networks, deep-learning, delphi, farsi, image-processing, neural-networks, ocr, optical-character-recognition, persian, persian-ocr
• Language: Pascal
• Homepage:
• Size: 11.2 MB
• Stars: 49
• Watchers: 5
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Persian OCR

> Offline optical character recognition of Persian letters, using deep learning and feature extraction

This project was done in 2010. No special libraries have been used in that, so it was a good practice for us to learn image processing and convolutional neural networks from scratch.

Read [this document](https://github.com/Erfaniaa/Persian-OCR/blob/master/Persian-OCR.pdf) for more details (in Persian).

## Screenshots

![ocr1](https://user-images.githubusercontent.com/7780269/46572355-46332d00-c991-11e8-8f00-8296636efc1d.JPG)

![ocr2](https://user-images.githubusercontent.com/7780269/46572356-46332d00-c991-11e8-9c89-8bbc7b9e2dd7.JPG)

![ocr3](https://user-images.githubusercontent.com/7780269/46572357-46332d00-c991-11e8-8f3f-8b8fe971f5ed.JPG)

![ocr4](https://user-images.githubusercontent.com/7780269/46572358-46cbc380-c991-11e8-9833-b884f4374901.JPG)

![ocr5](https://user-images.githubusercontent.com/7780269/46572359-46cbc380-c991-11e8-8fc1-955f379e0290.JPG)

![ocr6](https://user-images.githubusercontent.com/7780269/46572360-46cbc380-c991-11e8-8628-6d50326be4a5.JPG)

## Development

Open the project using Embarcadero RAD Studio Delphi.

## Run

Clone the project and run OCR.exe (in Windows).