przemekpastuszka/biometrics

fingerprint recognition, etc.

Fingerprint recognition algorithms

Active development year: 2012

Summary

Some implementations of fingerprint recognition algorithms developed for Biometric Methods course at University of Wrocław, Poland.

Usage

Prerequisites

• python 2.7
• python imaging library (PIL)

How to use it

Simply do python filename.py --help to figure out how to execute filename algorithm

Algorithms

Poincaré Index

Finds singular points on fingerprint.

How it works (more detailed description here):

• divide image into blocks of block_size
• for each block:
  • calculate orientation of the fingerprint ridge in that block (i.e. what is the rigde slope / angle between a ridge and horizon)
  • sum up the differences of angles (orientations) of the surrounding blocks
  • there are 4 cases:
    • sum is 180 (+- tolerance) - loop found
    • sum is -180 (+- tolerance) - delta found
    • sum is 360 (+- tolerance) - whorl found

The python script will mark the singularities with circles:

• red for loop
• green for delta
• blue for whorl

Example: python poincare.py images/ppf1.png 16 1 --smooth

Images:

• Original

• With singular points marked by algorithm:

Note: algorithm marked singular points not only inside fingerprint itself, but on its edges and even outside. This is a result of usage of non-preprocessed image - if the image was enhanced (better contrast, background removed), then only singular points inside fingerprint would be marked.

Thinning (skeletonization)

How it [works] (http://bme.med.upatras.gr/improc/Morphological%20operators.htm#Thining)

Example: python thining.py images/ppf1_enhanced.gif --save

Images:

• Before

• After:

Minutiae recognition (crossing number method)

Crossing number methods is a really simple way to detect ridge endings and ridge bifurcations.

First, you'll need thinned (skeleton) image (refer to previous section how to get it). Then the crossing number algorithm will look at 3x3 pixel blocks:

• if middle pixel is black (represents ridge):
  • if pixel on boundary are crossed with the ridge once, then we've found ridge ending
  • if pixel on boundary are crossed with the ridge three times, then we've found ridge bifurcation

Example: python crossing_number.py images/ppf1_enhanced_thinned.gif --save

biometrics's Issues

output extraction

@rtshadow Is it possible to extract x coordinate, ycoordinate, and angles of minutiae?

result image is 180 degree by original image

I don't know why, all script output 180 degree image.

Thinning.py and Sobel.py leads to an error: SystemError: new style getargs format but argument is not a tuple

$ python gabor.py images/ppf1.png 16 --save
calculating orientation done
smoothing angles done
computing local ridge frequency done
Traceback (most recent call last):
File "gabor.py", line 71, in
result = gabor(im, W, angles)
File "gabor.py", line 45, in gabor
j * W + l)
SystemError: new style getargs format but argument is not a tuple

And

$ python thining.py images/ppf1_enhanced.gif --save loading phase done
single thining phase done
single thining phase done
single thining phase done
single thining phase done
single thining phase done
single thining phase done
single thining phase done
thining done
Traceback (most recent call last):
File "thining.py", line 77, in
make_thin(im)
File "thining.py", line 59, in make_thin
utils.load_pixels(im, loaded)
File "/home/habib/Documents/Projects/biometrics/utils.py", line 111, in load_pixels
im_load[i, j] = pixels[i][j]
SystemError: new style getargs format but argument is not a tuple

the following arguments are required: image

how do i solve this?

errors

hi sir,
I have getting these errors from your code of crossing_number.py
crossing_number.py [-h] image
crossing_number.py: error: too few arguments
cloud you please slove it

Thining keeps repeating

Hello, I was using your code which is amazing and I noticed when doing the thining part the script outputs the same image and keeps printing:

"single thining phase done"

Is it because of the image?

Problem while recreating the given 'enhanced' image

Hi, i have been studying your code from the past several weeks and i am not able to create the 'enhanced' version of the image that you created as a sample using 'gabor.py' file. Can you show me the steps needed to recreate the results. it would be of great help for me.

Thank you.

Are there any requirements of the fingerprint image?

Are there any requirements of the fingerprint image? I use the FVC database, after thining, there are no prints on the image, what's the matter?

finding poincare loop/whorl co-ordinates

Can anyone help me in finding the co-ordinates of the loop/whorl extracted by the poincare.py so that I can crop out the core part of the finger image for my analysis. I am able to detect the singular points but not all are genuine can some suggest a method so that I can crop out the genuine core point of the finger image.?

Any suggestion would also help.

Thinning link broken

Do you have a new link on how you implemented skeletonization? What algorithm did you use, how can I know about it?

crossing number.py error

#@hi sir i just excute your code sir..but i have some errors sir
please fix it sir...these are following errors sir.
SyntaxError: invalid syntax
1.>>> crossing_number.py
Traceback (most recent call last):
File "", line 1, in
NameError: name 'crossing_number' is not defined

2.usage: crossing_number.py [-h] image
crossing_number.py: error: too few arguments

Traceback (most recent call last):
File "C:\Users\PRADEEP-PC\Desktop\resource\biometrics-master\crossing_number.py", line 51, in
args = parser.parse_args()
File "C:\Python27\lib\argparse.py", line 1656, in parse_args
args, argv = self.parse_known_args(args, namespace)
File "C:\Python27\lib\argparse.py", line 1688, in parse_known_args
return self._parse_known_args(args, namespace)
File "C:\Python27\lib\argparse.py", line 1901, in parse_known_args
self.error(('too few arguments'))
File "C:\Python27\lib\argparse.py", line 2311, in error
self.exit(2, _('%s: error: %s\n') % (self.prog, message))
File "C:\Python27\lib\argparse.py", line 2299, in exit
_sys.exit(status)
SystemExit: 2