Skip to content

Realistic Fingerprint Generator based on DCGAN architecture. This work was done as part of a master's thesis, as the first stage of our algorithm that will be published later.

License

Notifications You must be signed in to change notification settings

rafaelbou/-Realistic-Fingerprint-Generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Realistic Fingerprint Generator

Tensorflow implementation of realistic fingerprint generator based on DCGAN Deep Convolutional Generative Adversarial Networks.

result

Prerequisites

For training:

  • Download NIST Special Database 14.
  • Move to "./data" folder

For testing:

  • Download Pre trained model
  • Extract checkpoint folder to the main root (under "-Realistic-Fingerprint-Generator").

Usage

Generate fingerprint with pre-trained model (NIST14):

$ python main.py --input_height=650 --output_height=650 --test

To train a model with NIST14 dataset:

$ python main.py --dataset nist14 --input_height=650 --output_height=650 --train --crop=True

Or, you can use your own dataset (without central crop) by:

$ mkdir data/DATASET_NAME
... add images to data/DATASET_NAME ...
$ python main.py --dataset DATASET_NAME --train
$ python main.py --dataset DATASET_NAME
$ # example
$ python main.py --dataset=Fimages --input_fname_pattern="*.tif" --train

Evaluation

Use state-of-the-art fingerprint feature extractor fingerNet to extract some statistics from real and generated images

Data set Mean number of minute STD number of minute Mean orientation of minute STD orientation of minute
Nist14 123.39 30.63 3.30 1.85
Generated 123.87 30.53 3.29 1.88

Related works

Author

Rafael Bouzaglo / [@rafaelbou]

About

Realistic Fingerprint Generator based on DCGAN architecture. This work was done as part of a master's thesis, as the first stage of our algorithm that will be published later.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages