• Stars
    star
    181
  • Rank 212,110 (Top 5 %)
  • Language
    Python
  • License
    MIT License
  • Created over 7 years ago
  • Updated about 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Verify the authenticity of handwritten signatures through digital image processing and neural networks. ✍️

Signature Recognition ✍️

Verify the authenticity of handwritten signatures through digital image processing and neural networks.

This is an experimental project built during our research on the usage of AI throughout the most diverse fields.

Dataset

We got the dataset from ICDAR 2009 Signature Verification Competition (SigComp2009).

Usage

  • python sigrecog.py runs using our backpropagation neural network implementation
  • python sigrecogtf.py runs using a tensorflow model based on logistic regression

Built with

  • OpenCV
  • Tensorflow

Requirements

  • Python 3.6
  • OpenCV 3.2
  • Numpy
  • Tensorflow

Contributors

Guilherme's avatar
Guilherme Baron
Anisio's
Anisio Marques Junior