retinalysis-registration
Easy, robust registration of retinal fundus images using classical computer vision: keypoint detection and SIFT matching. No GPU is required, and dependencies are lightweight (OpenCV, scikit-image, and related scientific Python packages).
The method achieves state-of-the-art performance on the FIRE dataset; see the FIRE evaluation notebook for details.
Installation
pip install retinalysis-registration
Dependencies
This package depends on retinalysis-fundusprep (>=1.1.0) for fundus bounds detection and cropping.
Usage
See the Example notebook for a minimal walkthrough.
Reference
Abstract presented at ARVO 2026: Investigative Ophthalmology & Visual Science.
1 maintainer
Metadata
1 maintainer
Release files for retinalysis-registration 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| retinalysis_registration-1.0.0.tar.gz | 7.1 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| retinalysis_registration-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 7.1 MB
Release files / retinalysis_registration-1.0.0.tar.gz
| Download URL | retinalysis_registration-1.0.0.tar.gz |
|---|---|
| Size | 7.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4df17a67cb347c3e69ff6ddd0ef3515d5e7789f34e86776c58085da23e40c56e
|
|
BLAKE2b-256 checksum How to use checksums |
86cfaa9a56162dd5ff35ae9eac7279decb0d2e411791b15576ff7bdc8eba4be3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / retinalysis_registration-1.0.0-py3-none-any.whl
| Download URL | retinalysis_registration-1.0.0-py3-none-any.whl |
|---|---|
| Size | 42.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a0c087daafb9d07f0497817d965c4a1ca3f9eb5ffaabda3f64dd466216f10108
|
|
BLAKE2b-256 checksum How to use checksums |
9ec129fb729c2ff8ba758282437e5f74dd7036a7b13e7c0ccb9d0037cd2c8007
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
