https://github.com/birddevelper/scanneddocumentpreprocessing

Scanned document preprocessing python snippet code
https://github.com/birddevelper/scanneddocumentpreprocessing

classification denoising image-processing machine-learning ocr opencv preprocessing python

Last synced: about 1 year ago
JSON representation

Scanned document preprocessing python snippet code

• Host: GitHub
• URL: https://github.com/birddevelper/scanneddocumentpreprocessing
• Owner: birddevelper
• Created: 2023-02-12T08:45:11.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2024-10-25T08:42:44.000Z (over 1 year ago)
• Last Synced: 2025-03-30T08:41:30.822Z (about 1 year ago)
• Topics: classification, denoising, image-processing, machine-learning, ocr, opencv, preprocessing, python
• Language: Python
• Homepage:
• Size: 902 KB
• Stars: 6
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          

# Noisy Scanned Document Preproccessing

This snippet code denoise and align scanned documents to be used for any purpose including archiving, classification or OCR.

Sample result : 

![image](https://github.com/user-attachments/assets/cb338f98-8d0a-4396-8b2e-633d95a028a9)

**Left side document** : Noisy unaligned scanned document image.

**Right side document** : Denoised and aligned using the snippet code.

You can read article explaining the code :

[Scanned Document Preprocessing For Classification and Feature Extraction](https://mshaeri.com/blog/scanned-document-image-preprocessing-for-machine-learning-classification-feature-extraction/)