Skip to content

Conversation

@AhmedFatthy1040
Copy link
Owner

...

- Add support for 11+ image format categories beyond basic JPEG/PNG/TIFF
- Implement FormatProcessor class for specialized format handling
- Add support for:
  * Modern formats: WebP, HEIC/HEIF, JPEG2000
  * Camera RAW: CR2, NEF, ARW, DNG (Canon, Nikon, Sony, Adobe)
  * Medical: DICOM for medical imaging
  * Astronomy: FITS for telescope data
  * Scientific: NetCDF and HDF5 for research datasets
- Install required dependencies: pillow-heif, rawpy, pydicom, astropy, xarray, netcdf4
- Update frontend validation to accept all new format types
- Add automatic format detection and metadata extraction
- Implement web-compatible conversion pipeline for specialized formats
- Add comprehensive error handling with graceful fallbacks
- Create documentation and demo scripts
- Update image processing pipeline integration
- Enhance upload workflow to handle format-specific metadata
- All changes tested and working with FastAPI server
- Modified session_segmentation.py to only return segmentation polygon without creating annotation files
- Annotations are now only created when user explicitly clicks Export button
- Updated annotations.py to properly detect AI-generated vs manual annotations based on annotation_id
- AI-generated annotations are marked as auto_generated=True only when exported
- Manual annotations remain marked as auto_generated=False
- Implement Douglas-Peucker simplification algorithms in sam_model.py
- Add adaptive simplification to target specific point counts (10-50)
- Update API endpoints to accept simplification parameters
- Add frontend UI controls for polygon simplification settings
- Create comprehensive documentation and demo script
- Enhance user experience by reducing polygon complexity for easier editing
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

Successfully merging this pull request may close these issues.

2 participants