Catalog record · Operations & Efficiency
Stage as of Jul 30, 2026 · historical report, not live reconfirmation.
Duplicate and web-sourced grant-evidence image triage
Primary workflow source. A named organization's workflow supported by a reviewed primary source. Stage is reported separately; this label does not establish measured outcomes or independent validation.
Last researched Oct 29, 2026. Source access and reported stage are recorded below; deployment evidence does not establish ROI.
What the research supports
The tool extracts deep image representations, compares image-pair similarity and uses Google Vision web matches to flag potentially reused installation photos. Several large backlogs have been processed. Reviewers receive image links, scores and web URLs and decide whether reuse is legitimate. Real-time checks before approval remain planned.
- Reported stage
- Pilot
- Technology
- Computer Vision
- Business function
- Not assessed
- Impact (legacy label)
- Not labeled
- Catalog date · unconfirmed
- Not reported
- Imported
- Oct 29, 2026
- Last researched
- Oct 29, 2026
Measures & evidence
No quantified measure recorded. This is a gap in the evidence, not a finding of no value.
Documented vendor relationships
No vendor relationship has been linked to this specific workflow in the curated overlay. This does not mean it was built without vendors.
See the company’s documented relationshipsDeployment evidence & limits
Private Beta; actual retrospective backlog processing; real-time checks planned Status as of 2026-07-30.
Stage is as reported in the cited evidence. Current operating status has not been independently reconfirmed; the research date is an editorial review date.
Record is Private Beta and explicitly distinguishes current retrospective processing from planned pre-disbursement use. Detailed model/performance information is withheld to reduce gaming; false-positive and false-negative rates are unavailable. Similarity is not fraud; repeated stock views or legitimate repeat submissions can match. Insurance-specific base rates, image transformations, privacy and image-sharing rights need validation. Do not import claimed manual-comparison years or grant savings into FS ROI.
Potential FS application · inferred
Inferred: insurance claim photo reuse and asset-finance evidence duplication checks across applications.
Inferred: insurance claim photo reuse and asset-finance evidence duplication checks across applications.
Original industry: Transport grant administration. Transfer limits: Similarity is not fraud; repeated stock views or legitimate repeat submissions can match. Insurance-specific base rates, image transformations, privacy and image-sharing rights need validation. Do not import claimed manual-comparison years or grant savings into FS ROI.
Source register
- DfT: EV Chargepoint Grant Photos Fraud Toolgov.uk · opens in a new tab
Department for Transport / GOV.UK · issuer · full-text · Published 2026-07-30
Research lanes: public_science_transfer · Batch global-discovery-2026-10-29. Coverage and remaining gaps