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

Border Energy classifier for region filtering #9

Open
CattleProdigy opened this issue Jan 25, 2014 · 1 comment
Open

Border Energy classifier for region filtering #9

CattleProdigy opened this issue Jan 25, 2014 · 1 comment
Assignees

Comments

@CattleProdigy
Copy link
Contributor

Border energy attempts to find a measure of a region with high feature-to-background contrast in an attempt to discard homogeneous, less-salient regions. Regions with border energy below some threshold are discarded.

Border energy is defined as the average Sobel Edge Magnitude of all border pixels in a region.

The paper proposes a "simple adaptive threshold" not based on std-dev or variance.

See: http://en.wikipedia.org/wiki/Sobel_operator#Formulation
for Sobel Edge detection and magnitude.

@CattleProdigy CattleProdigy self-assigned this Feb 6, 2014
@CattleProdigy CattleProdigy modified the milestones: Calculation, Threshold Feb 6, 2014
@CattleProdigy
Copy link
Contributor Author

The calculation for Border Energy is done. The paper mentions a 'simple adaptive threshold' as the actual decision for this region classifier. The paper is vague. Right now the decision is a dumb threshold set to an empirically chosen number

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

No branches or pull requests

1 participant