Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Fingerprint Recognition Help Please

Status
Not open for further replies.

basimdcs

Newbie level 1
Joined
Dec 16, 2006
Messages
1
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Activity points
1,301
Hello ,
Firstly just wanted to say what a great forum this is, so lucky to have found it!
Well, i have a university project that i need to implement fingerprint feature extraction sing C#, after reading "Fingerprint Classification and Matching Using a Filterbank" By Salil Prabhakar, i understood that need to first find a refrence point


What i did was:

1. Divide I (NxM) , the input fingerprint image, into non-overlapping blocks of size wXw.
2. Compute the gradients @ x(i; j) and @ y(i; j) at each pixel (i; j). Depending on
the computational requirement, the gradient operator may vary from the simple
Sobel operator to the more complex Marr-Hildreth operator

3. Estimate the local orientation of each block centered at pixel (i; j)

Then

1. Estimate the orientation field O as described above using a window size of wXw.
2. Smooth the orientation field in a local neighborhood. Let the smoothed orientation field be represented as Ox. In order to perform smoothing (low-pass
filtering), the orientation image needs to be converted into a continuous vector
field


Should apply the low-pass filter on the orginal picture(NxM) or the orientation matrix (PXQ) where P=N/Blocksize ?
May image does not look like int the book at all

i think i'm lost somewhere :| could anyone help me with how i can implement easier fingerprint extraction?

Thanks
 

I'm not really well about this, but you can test it out by filtering the original image, and later filtering the orientation matrix...

For another way to compute the orientation image, you can refer to Raymond Thai's paper. The paper and code can be found in other topics in this forum as well....Try to search, there're a lot of topic discussing fingerprint recognition....
 

yes, there are many experts here.
right now, I also do the same project with you. So if you have any questions, you can send me by mail. we can discuss the questions.

my email: kejunconsult@gmail.com
 

Yes, there are few ebook which are very good in this forum:
 

Palmprint recognition

isnt there anything on palmprint recognition here?...im struggling out here.....

Added after 31 minutes:

for information, im thinking of using Wavelet Transform and Pseudo Zernike Moments for palmprint extraction, Directional Projection Alg and Hamming Distance for representation and matching....im not sure if its the best algorithm for this, im still researching. im open for suggestion though....please send your thoughts....
 

hi it's me again...i would like to ask if anyone knows where can i find samples of palmprints....i appreciate your help....
 

basimdcs said:
Should apply the low-pass filter on the orginal picture(NxM) or the orientation matrix (PXQ) where P=N/Blocksize ?


you should apply a simple low-pass filter on the orientation image....
 

Status
Not open for further replies.

Similar threads

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top