What actually changes in your routine.

Phase 1

Your bursts become scenes

Kestrel compares your images with each other to identify high-speed bursts and groups them into scenes. By grouping these into scenes, you can compare nearly identical frames against each other using Kestrel's quality algorithms.

Phase 2

Find the bird, ignore the background.

Using a specialized object detection model, Kestrel identifies birds within the frame. It then creates precise masks around the subjects, ensuring that background detail never influences the quality score.

Phase 3

Every frame gets a sharpness score

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.

Phase 4

Each bird gets a species tag

Kestrel tags every photo with a species and family classification. Load your full library and search across all your folders and outings by what's in the frame — not just when you shot it.

On accuracy: North American birds only, currently. Family-level classification is fairly reliable and a solid primary search tool. Species-level is a useful starting point for narrowing results — treat it as a helpful filter, not a definitive ID. Even with occasional misclassifications, it's dramatically faster than browsing folder by folder. Improved accuracy and broader species support are planned.