segmenteverygrain review

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

segmenteverygrain is an open-source Python package for detecting, editing, measuring, and classifying grains or grain-like objects in images. It is aimed at geomorphology and sedimentary-geology workflows, making it a specialized option for researchers who need grain-level segmentation rather than a general-purpose image annotation system. Its workflow combines a U-Net first pass with SAM 2.1, followed by interactive tools for creating, deleting, merging, and editing grain regions. Annotation includes instance segmentation masks, polygon editing, point prompts, and grain classification labels.

The package goes beyond drawing boundaries: it supports scale-bar calibration, grain size distributions, individual grain extraction, feature extraction, clustering, and interactive classification. Large images can be processed in patches with resumable checkpoints, and users can fine-tune or train U-Net models with custom masks. Export options include GeoJSON, CSV, PNG or JPEG masks, and a labeled-image directory. That breadth suits studies where segmentation is only one step in a measurement and classification workflow. The tradeoff is its narrow focus: teams annotating unrelated image types may find a general image annotation tool a better fit.

segmenteverygrain is distributed as an Apache-2.0 Python package, with Windows, macOS, and Linux listed as platforms. Deployment is self-hosted, so it is not presented as a hosted annotation service. Documentation and community are the listed support channels; the package also lists API access. These characteristics make it a plausible fit for solo researchers and small teams comfortable with a Python package and local deployment. Choose it when grain-specific analysis, model-assisted segmentation, and research exports matter; look elsewhere if you need a broad annotation platform or hosted deployment.

segmenteverygrain pros and cons

• Where it wins
  • Combines U-Net and SAM 2.1 for model-assisted grain segmentation
  • Supports interactive edits, measurement, calibration, and classification
  • Exports grain boundaries, measurements, masks, and labeled images
• Where it doesn't
  • Focused on grains and grain-like objects, not general image annotation
  • Self-hosted deployment requires running the Python package locally
  • The documented image formats are limited to JPEG and PNG

segmenteverygrain fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated 7 Oct 2026 · How we research and update