Click here to Skip to main content
15,895,782 members
Please Sign up or sign in to vote.
1.00/5 (1 vote)
See more:
hi

I please tell me after orientation fiels estimation of the image what will be the dimension of the image.

like i have 384x384 image i hv divided it into 16x16 blocks so 24 blocks will make
now how i these values place on the image. it is 24x24
Posted
Comments
Sergey Alexandrovich Kryukov 21-Oct-13 1:47am    
Not clear what do you want to achieve. And why would you divide the image in blocks? Divided by what? Internal representation of data, or the image itself?
—SA
Member 10348471 22-Oct-13 0:58am    
sir actually i read the reserch paper n follow the steps but i stuk now.
actually what i am doing is
Take the fingerprint image.
Convert the image into grayscale then binary image.
Divide binary image data into blocks of size wxw. Where w=16.
Compute the gradient in x and y direction by using sobel operator (in my program) at each pixel of the block.
Estimate local orientation of block.The angle range is [0, pi].
Now the image is again divided into blocks of non overlapping window 3x3 and poincare index value method is used to detect core point.
If P(x,y)=0.5 then that will be the core point.

but the problem is when i store the values of the angle in a matrix it stores at places like
0 0 0 16 0 32 because block is of 16x16

now tell me is it rit what i m doing.the values are stored at rit position???
Plz help me ...
Sergey Alexandrovich Kryukov 22-Oct-13 1:25am    
Hard to say. So far, the problem is not clear. Still not clear the purpose of 16x16 blocks "Gradient in X" or Y direction is not gradient but a partial derivative... You say "the problem is when", but what's the problem... You really need to elaborate.
—SA
Member 10348471 22-Oct-13 2:33am    
so what is gradient then...? i just read that by using sobel operator u can find gradient.
ok u r not geting me
hv u any idea how to find core point in fingrprint.???

help me in finding this i stuk for 5 months....
Sergey Alexandrovich Kryukov 22-Oct-13 2:37am    
Gradient is strictly defined and is something quite different but related to derivatives:
http://en.wikipedia.org/wiki/Gradient#Gradient_and_the_derivative_or_differential
—SA

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900