Checking for non-preferred file/folder path names (may take a long time depending on the number of files/folders) ...

GRIME AI Image Triage Validation Using Synthetically Generated Images


Authors:
Owners: This resource does not have an owner who is an active HydroShare user. Contact CUAHSI (help@cuahsi.org) for information on this resource.
Type: Resource
Storage: The size of this resource is 40.3 MB
Created: Mar 30, 2026 at 1:19 a.m. (UTC)
Last updated: May 28, 2026 at 3:21 p.m. (UTC) (Metadata update)
Published date: May 28, 2026 at 3:21 p.m. (UTC)
DOI: 10.4211/hs.d0381011dbb044f3bd22aa7256ccb911
Citation: See how to cite this resource
Content types: CSV Content 
Sharing Status: Published
Views: 365
Downloads: 63
+1 Votes: 1 other +1 this
Comments: No comments (yet)

Abstract

Validation evidence for the GRIME AI image triage module. Synthetic test images with known blur and brightness properties are processed through GRIME AI and results are compared against expected classifications. Includes validation of blur threshold detection, brightness lower and upper bound detection, and combined condition handling across six test cases. Contains the validation script, formal test plan, synthetic test images organized by test case, and CSV results from a validation run conducted on 2026-03-27

Subject Keywords

Content

README.md

GRIME AI Triage Validation

Overview

Validation evidence for the image triage module of the GaugeCam Remote Image Manager Educational Artificial Intelligence (GRIME AI) framework. This resource contains the validation script, test plan, synthetic test images organized by test case, and CSV results from a validation run conducted on 2026-03-27.

Contents

  • test_triage.py — Python script that generates the synthetic test images and implements the GRIME AI triage algorithm as of 2026-03-27
  • GRIME_AI_Triage_Test_Plan - Rev 1.0 - 2026_03_27.docx — Formal test plan
  • data/triage_test_images/ — Synthetic test images organized by test case, generated by the validation script
  • results/ — CSV outputs from GRIME AI triage run against the synthetic test images

Validation Approach

Synthetic test images with known blur and brightness properties are loaded into GRIME AI. GRIME AI triage output is compared against known expected classifications to confirm correct detection behavior across six test cases covering blur threshold, brightness lower bound, brightness upper bound, and combined conditions.

Cross-Validation

The validation script implements the same triage algorithm as GRIME AI as of 2026-03-27. Running the script against the synthetic test images provides an independent reference result that can be compared directly against GRIME AI output to cross-validate results.

Generating the Test Images

python test_triage.py generate

License

Apache License 2.0

Related Resources

GRIME AI source code: https://github.com/JohnStranzl/GRIME-AI

Additional Metadata

Name Value
License Apache License 2.0

Related Resources

This resource is described by GRIME AI source code. Available at: https://github.com/JohnStranzl/GRIME-AI

Credits

Funding Agencies

This resource was created using funding from the following sources:
Agency Name Award Title Award Number
U.S. National Science Foundation Innovative Resources: Cyberinfrastructure and community to leverage ground-based imagery in ecohydrological studies 2411065

How to Cite

Stranzl Jr., J. E. (2026). GRIME AI Image Triage Validation Using Synthetically Generated Images, HydroShare, https://doi.org/10.4211/hs.d0381011dbb044f3bd22aa7256ccb911

This resource is shared under the Creative Commons Attribution CC BY.

http://creativecommons.org/licenses/by/4.0/
CC-BY

Comments

There are currently no comments

New Comment

required