basimdcs
Newbie level 1
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
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