luizgh/sigver_wiwd

Learned representation for Offline Handwritten Signature Verification. Models and code to extract features from signature images.

41
/ 100
Emerging

Pre-trained CNN models extract fixed-size feature vectors (2048-dim) from variable-sized signature images using SigNet and SigNet-SPP architectures, with the latter employing spatial pyramid pooling to handle signatures of different resolutions. Built on Theano/Lasagne with TensorFlow compatibility, the framework includes image preprocessing pipelines, batch processing utilities, and pre-extracted feature datasets for GPDS, MCYT, CEDAR, and Brazilian PUC-PR benchmarks to support offline signature verification research.

156 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

156

Forks

52

Language

Jupyter Notebook

License

BSD-2-Clause

Last pushed

Feb 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/luizgh/sigver_wiwd"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.