Subject-Aware Scoring
Unlike simple sharpness filters, Kestrel detects the bird first, ignoring busy backgrounds or foreground branches to give you a true quality score.
Project Kestrel
AI Culling and Organization for Bird Photographers.
The Culling Problem, Solved.
Every bird photographer knows the pain: returning from a lovely birding outing with 3,000 photos, realizing that for every few hours you spent in the field, you'll need to spend another hour squinting at pixels to find the ones with the perfect focus.
Kestrel automates this by ranking every photo by objective subject sharpness, letting you jump straight to the sharpest frames.
New in Kestrel
A dedicated accept/reject workflow built to help you finish large culls in minutes, not hours.
How Culling Works
Unlike simple sharpness filters, Kestrel detects the bird first, ignoring busy backgrounds or foreground branches to give you a true quality score.
Select a burst and see it instantly sorted from sharpest to blurriest. Double-click any photo to open it immediately in Darktable, Lightroom, or Photoshop.
Kestrel's machine learning model is trained to take into account noise, motion blur, and sharpness to create a normalized quality score that can accurately differentiate between each frame in a scene.
Project Kestrel is free, open-source, and runs entirely on your machine. Your photos never leave your computer.