Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to select the filters? #3

Closed
Dandelion111 opened this issue Apr 6, 2020 · 10 comments
Closed

How to select the filters? #3

Dandelion111 opened this issue Apr 6, 2020 · 10 comments

Comments

@Dandelion111
Copy link

Hello, I am a little confused about the paper. After getting Sm, how to extract 5 filters, could you please explain in detail?Thank you very much!

@AngeloUNIMI
Copy link
Owner

hi, you probably want to take a look at this function
https://github.com/AngeloUNIMI/PalmNet/blob/master/functions_Gabor/findBestWaveletsTesting.m

@Dandelion111
Copy link
Author

Thank you for your reply!I've seen this function, another function within this function: "getMostUsedWavelets", there's one thing I've been wondering about, I think currX, currY, currO will be unique every time ind is added, when is tmpRes going to be equal to 1 in line 23 of the if statement?

@Dandelion111
Copy link
Author

How should I interpret this sentence that considering each filter at
most once for each position in the ROI.

@Dandelion111
Copy link
Author

In Sm of size Auv, each filter in Ga is used once. Why don't they have the same number in Sm?

@AngeloUNIMI
Copy link
Owner

in the function "getMostUsedWavelets", we cycle through the filter responses in decreasing order of magnitude. The variable tmpRes keeps track of whether we already considered the filter at a particular image position. A particular combination of currX, currY, curr might happen more times, after the first time the corresponding value of tmpRes will be = 1.

@Dandelion111
Copy link
Author

Can I understand that there are 114 currX, curries, currs at a particular location in ROI?

@Dandelion111
Copy link
Author

The size of Sm is Auv, while there are Auv positions in tmpRes, which are exactly one-to-one correspondence. Why do we repeatedly consider the same position?

@Dandelion111
Copy link
Author

Please forgive my stupidity!

@AngeloUNIMI
Copy link
Owner

The size of Sm is A_u_v, while there are A_u_v positions in tmpRes, which are exactly one-to-one correspondence. Why do we repeatedly consider the same position?

Feel free to optimize the code if possible ;)

@Dandelion111
Copy link
Author

Hello, may I ask why these unrecognized characters are added to the verification program?
<<<<<<< HEAD

5aa7404d46b056250a68745e148af098f5e8a28e

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants