cd /news/artificial-intelligence/government-agencies-use-image-recogn… · home topics artificial-intelligence article
[ARTICLE · art-102927] src=publictechnology.net ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Government agencies use image recognition AI to tackle EV grant fraud

The UK Department for Transport, along with the Office for Zero Emission Vehicles and the Driver and Vehicle Licensing Agency, has deployed a deep learning image recognition model based on Google Vision technology to detect fraudulent photos in electric vehicle chargepoint grant applications, which offer up to £500 per socket. The tool checks for duplicate images across claims and for images downloaded from the web, saving over 100 years of manual review time and delivering financial benefits of tens of thousands of pounds.

read2 min views3 publishedAug 19, 2026
Government agencies use image recognition AI to tackle EV grant fraud
Image: Publictechnology (auto-discovered)
Based on Google Vision technology, an algorithmic tool is being used to check whether photos submitted with applications for funding have already been used elsewhere or cribbed from the internet

Government organisations administering grant funding for electric vehicle charging points have deployed artificial intelligence image-recognition technology to help crack down fraud.

EV chargepoint grants – which offer government backing of up to £500 per socket – can be applied for via the Office for Zero Emission Vehicles, with the Driver and Vehicle Licensing Agency helping to administer the provision of funding. The agencies have deployed “a deep learning image recognition model” based on the Google Vision technology, according to a newly published algorithmic transparency record.

The document reveals that the AI-based tool was developed by OZEC and DVLA parent organisation the Department for Transport and “is being used to detect and prevent fraudulent [or] erroneous photos being submitted as evidence in multiple EV chargepoint grant schemes”.

Once an application has been submitted, the algorithm performs two checks on photos, the first of which is designed to ascertain whether an image of one installation has been used in multiple grant claims. The second test is intended to determine whether an image has been downloaded from the web and then used in an application.

Related content

What is the cost of DWP’s UC anti-fraud algorithm?HMRC algorithm for automated council tax valuations offers ‘greater consistency and quality’Major AI models go rogue in government watchdog’s cyber tests

“We look for duplicate installations using a deep learning image recognition model to extract image representations and we calculate a similarity score for each pair of images in the database,” the record adds. “Image pairs with a similarity score above a threshold are labelled as ‘similar’ and returned to colleagues in the DVLA… to follow up with, [and] determine if the images are of the same installation and, if so, whether there is a legitimate reason for them to appear on separate grant applications.”

The transparency notice indicates that government believes the tool is delivering financial benefits of tens of thousands of pounds “from companies paying back falsely approved grant funding or not receiving it in the first place”.

The tech tool has also enabled “very large time savings compared to [the] manual labour cost of running the same level of detailed checks – far in excess of 100 years would be required to run the same checks manually”, according to the record.

“These fraud checks could not be done at the same level of detail without this tool,” it adds. “Earlier approaches to fraud risk identification relied on manual reviews and subjective assessments, which were resource intensive and less efficient.”

In order to apply for a chargepoint grant, claimants must first obtain a quote from an installation firm authorised by OZEV, before then submitting their application along with all applicable documents via an online GOV.UK service.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @department for transport 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/government-agencies-…] indexed:0 read:2min 2026-08-19 ·