Welcome to BIRL’s documentation!

Contents

• BIRL: Benchmark on Image Registration methods with Landmark validation
  • Features
  • Structure
  • Installation
  • Before benchmarks (pre-processing)
  • Experiments with included methods
  • License
  • References
  • Appendix - Useful information
• birl package
  • Subpackages
  • Submodules
• bm_dataset package
  • Submodules
• bm_experiments package
  • Submodules
• ANHIR challenge
  • Submission statistic
  • ANHIR: Evaluation Board

Indices and tables

• Index
• Module Index
• Search Page

BIRL: Benchmark on Image Registration methods with Landmark validation

The project aims at automatic evaluation of state-of-the-art image registrationmethods based on landmark annotation for given image dataset. In particular,this project is the main evaluation framework for ANHIR challenge.

Main Features

• automatic execution of image registration on a sequence of image pairs
• integrated evaluation of registration performances
• integrated visualization of performed registration
• running several image registration experiment in parallel
• resuming unfinished sequence of registration benchmark
• handling around dataset and creating own experiments
• rerun evaluation and visualisation for finished experiments

References

Borovec, J., Munoz-Barrutia, A., & Kybic, J. (2018). Benchmarking of imageregistration methods for differently stained histological slides.In IEEE International Conference on Image Processing (ICIP) (pp. 3368-3372),Athens. DOI: 10.1109/ICIP.2018.8451040