Pixel Feature Framework
- Dominant language
- Java
- Stars
- 94
- Forks
- 44
- PR merge metrics
- No merged PRs in 30d
Description
Pixel features that would be great to have implemented in Ops:
- [ ] Gaussian filter
- [ ] Sobel filter
- [ ] Hessian-related features (trace, determinant, eigenvalues, orientation, Gamma-normalized square eigenvalue difference, Square of Gamma-normalized eigenvalue difference)
- [ ] Difference of Gaussian
- [ ] First order statistics: mean, variance, maximum, minimum, median
- [ ] High order derivatives
- [ ] Laplacian filter
- [ ] Structure tensor filter (see FeatureJ)
- [ ] Gabor filters
- [ ] Membrane projections (see Trainable Weka Segmentation)
- [ ] Anisotropic diffusion
- [ ] Entropy filter
- [ ] Frangi filter
- [ ] Min
- [ ] Max
- [ ] Avg
- [ ] StdDev.
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points. Start by breaking the checklist into separately scoped features and review FeatureJ and Trainable Weka Segmentation for the referenced structure and projections. Done would require implementing and validating the agreed subset of filters and checking off the corresponding items.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100