Skip to content
xFaronPublic

About

An OCR built for the Pulse Quest Hackathon ground up (custom CNN). Achieved an accuracy of 96.67%

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

Repository files navigation

OCR Name Recognition

A handwritten OCR pipeline built for the Pulse Quest Kaggle Competition.

The project combines classical computer vision with a Convolutional Neural Network (CNN) to recognize handwritten names. Built from ground up without extenral models.

Pipeline

Input Image
    ↓
Character Segmentation (OpenCV)
    ↓
Character Classification (CNN)
    ↓
Word Reconstruction

Segmentation

  • Connected Components Analysis
  • Handcrafted filtering to remove noise
  • Character extraction
  • Automatic space detection

Model

  • 4-layer Convolutional Neural Network
  • Trained using PyTorch
  • Cross-Entropy Loss + Adam Optimizer
  • Mixed Precision (AMP) training

Results

  • Character segmentation correctly matches the ground truth for 96.7% of the test dataset.

Tech Stack

  • Python
  • PyTorch
  • OpenCV
  • NumPy
  • Pandas

About

An OCR built for the Pulse Quest Hackathon ground up (custom CNN). Achieved an accuracy of 96.67%

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages