Miura et al. vein extraction methods

Two vein extraction methods as described by Miura et al. for finger vein authentication.

Description

Maximum curvature:
This method will try to extract the centre lines of the veins. This is done by calculating local maximum curvatures in cross-sectional profiles of a vein image. The method is supposed to be robust against varying vein widths and non-uniform brightness.

Repeated line tracking:
This algorithm will start at several random points and will try to track a line. If a pixel has been visited by the line tracking algorithm multiple times it is likely to be a vein. A movie showing the algorithm in action can be found here:
https://vimeo.com/51757793
 
Literature:
 - N. Miura, A. Nagasaka, and T. Miyatake "Feature extraction of finger vein patterns based on repeated line tracking and its application to personal identification" Machine Vision and Applications.
doi: 10.1007/s00138-004-0149-2
 - N. Miura, A. Nagasaka, and T. Miyatake "Extraction of finger-vein patterns using maximum curvature points in image profiles." IAPR conference on machine vision applications 9 (2005).

Usage:
The file "miura_usage.m" gives an impression of how to use the feature extraction methods. Finger region localisation can be found here:
http://www.mathworks.in/matlabcentral/fileexchange/35752-finger-region-localisation

Comments:
Please leave a comment, if you like it, find a bug, or know (made) good improvements to the code.

• MATLAB release: MATLAB 7.13 (R2011b)

[Smart]

Hi,
Thx a lot
can u explain how can i calculate FAR and FRR plz
Thx

[Mohamed]

Dear Dr. Bram Ton,

would I ask you for an implementation for this simple and efficient paper for vein extraction

http://www.sciencedirect.com/science/article/pii/S0167865512000748

I already sent the paper to your e-mail account

thank you very much for your help and support

[Bram Ton]

@Adem Trey & Bo
I have added an updated 'miura_usage.m' script, which should be foolproof now ;)

[bo]

Hello, Bram Ton:
I am a new beginner to study vein extract. Thanks you for the great work. miura usage is our main function or not?
I have download your code, when I am trying to run your code, here the error information:
??? Undefined function or method 'finger_region' for input arguments of
type 'double'.

Error in ==> miura_usage at 11
fvr = finger_region(img,'mask',40); % Get finger region
when I try to modify to the function finger_region to lee_region. then I got the following information:
??? Error using ==> zeros
Leading inputs must be numeric.

Error in ==> lee_region at 36
mask = zeros(mask_h,mask_w);

Error in ==> miura_usage at 10
fvr = lee_region(img,'mask',40); % Get finger region
I am wondering May I get help from you to send me send me an correct version of your code.Here is my email:
[e-mail]

[Adam Trey]

Is finger_region() the same as lee_region()?

I got an error when I run miura_usage.m

Error in ==> miura_usage at 11
fvr = lee_region(img,'mask',40); % Get finger region

??? Error using ==> zeros
Leading inputs must be numeric.

Error in ==> lee_region at 37
mask = zeros(mask_h,mask_w);

And, what about the full binarize() function? Thanks.

[Bram Ton]

@Nourul
Miura et al. his paper is not clear about the binarisation method. I have used binarisation based on the median value with good results:
md = median(img(img>0));
BW = img > md;

[nourul]

what about binarize function? Thanks.

[Bram Ton]

@Suhan:
Please see my recently submitted work:
http://www.mathworks.in/matlabcentral/fileexchange/35752-finger-region-localization

[Suhan Shetty]

cannot find fingerregion function.Please pass it.Thanks a ton.