QuantumAdsLab Logo Quantum Ads Lab
How Google detects overlaid text in Google Ads image creatives
The automated system that reads the text in your ad images before you even submit them

Overlaid Text Google Ads: How the Detection System Works

What you'll find in this article

  • How automatic text detection works in Google Ads, OCR and computer vision, official sources and inferences clearly separated
  • Exactly what the system detects: promotional text, watermarks, logos, prices, badges, QR codes
  • The 20% rule for Responsive Display Ads, officially confirmed, often misread
  • Shopping disapprovals for text on image, "Promotional overlay" and "Text on image" explained
  • Patterns observed directly on live campaigns, clearly flagged as inferences
  • How to structure creatives to pass detection without losing your message

You upload an image to your Google Ads campaign with the product price in plain sight, "€49.90, Today Only". The system rejects it or lowers the asset score. You remove the price, re-upload, and the problem disappears.

No human looked at the image. An automated system scanned every pixel to identify what was written on it. This system runs across all Display, Shopping, Performance Max, and Demand Gen campaigns that use images. It works silently, often without any error message, and Google has never published a full technical description of how it operates.

This article keeps official documentation and direct observations strictly separate.

How Automatic Text Detection Works: OCR and Computer Vision

Google's ad review system uses two distinct technologies to find text in uploaded images. Both appear in Google's public technical documentation, though neither has been described in detail specifically for ad review.

✅ Confirmed by Google Ads: Google has stated that it uses automated systems to detect promotional text, watermarks, logos, and overlays in images, for both Responsive Display Ads and Shopping campaigns via Merchant Center. Review completes within 24–72 hours for most assets. Sources: Google Ads Help, Best practices for responsive display ads and Google Merchant Center, How to fix: Text on image.

The two technologies that make up the detection system:

📝 OCR Optical Character Recognition reads text in the image the way a human would. It identifies characters, words, and phrases, prices, claims, URLs, phone numbers.
👁 Computer Vision Measures the share of the image area covered by non-image elements. It checks contrast between text and background, where text sits within the frame, and how dense the text is relative to the main subject.
🔍 Semantic Analysis Reads the meaning of the detected text. It separates text that belongs to the original scene (a licence plate, a shop sign) from promotional copy added on top (e.g. "50% OFF").
✅ Confirmed by Google Vision AI (public API): Google Vision AI, the underlying technology behind Google's image analysis, includes Document Text Detection, Logo Detection, and Object Detection as distinct features. These three capabilities form the technical basis of ad image review. Source: Google Cloud Vision AI, Detecting text in images.

The process is fully automated. For the vast majority of assets, even those with clear text overlays, the system decides on approval or rejection with no human in the loop. A person only steps in if the advertiser files an appeal, and that covers a small share of cases.

What the System Detects Exactly

The official documentation lists the overlay categories the system flags. The section below combines confirmed information with patterns observed directly. Each source is clearly labelled.

Officially confirmed categories

✅ Confirmed by Google Merchant Center and Google Ads: The system automatically flags these overlay types:
  • Overlaid promotional text, prices, discount percentages, claims ("Today Only", "Free Shipping"), calls to action ("Buy Now", "Learn More")
  • Watermarks and photo signatures, brand logos, copyright notices, photographer credits
  • Corporate logos placed on top of the product
  • Badges and graphic stickers, "NEW", "SALE" icons, star ratings built into the image
  • Contact details, phone numbers, URLs, email addresses
⚠️ Inference, not confirmed by Google as a named category: The system also appears to flag QR codes and barcodes placed on the image. I saw disapprovals on Shopping images with QR codes added for "more information" , the system labelled them "Promotional overlay on image" even though the QR code had no visible text. My best reading: the system treats any dense graphic element placed on the main subject as an overlay, whether or not it contains readable characters.

What is NOT flagged as a problematic overlay

✅ Text that is part of the real scene

A licence plate on a car, text printed on a T-shirt, a logo on a photographed product, a sign in the background of a lifestyle shot. These are part of the subject, not digital overlays. The system may detect them but does not treat them as a violation.

✅ Brand name built into the design

When the brand name is a design element, not a watermark on top, but part of the visual layout, the system tends not to flag it. Text woven into the composition differs from text sitting above the image.

❌ Promotional text added in post-production

Any text placed on top of the product image after shooting, prices, discounts, claims, CTAs. The system catches both the content (via OCR) and the overlay nature (position, contrast). For Shopping this almost always triggers a disapproval. For Display it lowers the asset score.

⚠️ Small text at the image edge

A small copyright line in the bottom-right corner or a minimal watermark in a peripheral zone. In practice the system seems more tolerant here. This is a pattern observed, not a published exception, so treat it as a data point, not a safe harbour.

The 20% Text Rule for Google Display Campaigns

The 20% rule is the most-cited, and most-misread, requirement for Display image creatives.

✅ Confirmed by Google Ads: For Responsive Display Ads, images must not contain text that covers more than 20% of the image area. This rule applies to the image the advertiser uploads. Google may reduce distribution of ads that cross this threshold, even without issuing a formal disapproval. Source: Google Ads Help, Best practices for responsive display ads.

The most common misconception: many advertisers assume the 20% rule covers the final ad, the version the user sees, with Google's headline and description on top. It does not. The rule covers the uploaded image only. The text Google adds in the assembled ad is handled by a separate system and is not counted in this calculation.

⚠️ Inference on how the percentage is calculated, not in Google's public documentation: The calculation appears to use total pixel area identified as text, divided by total image area, not character count or text length. A single large bold headline on a light background can push past 20% more easily than four lines of small text on a dark background. The visual impression is not what matters: pixel area is.

One more factor worth noting: the 20% check runs on the cropped version of the image, not just the original. If Smart Cropping converts a landscape image to square, the text area share can shift. Text that covered 18% of the landscape original might cover 28% of the square crop.

Text Disapprovals: Display vs Shopping vs PMax

The detection system behaves differently across formats, and so does the consequence when it fires.

Format Consequence Error code Recoverable
Google Shopping (Merchant Center) Immediate product disapproval, product stops showing in ads "Promotional overlay on image" / "Text on image" Yes, fix the image and update the URL
Responsive Display Ads Reduced distribution, lower asset quality score, no formal disapproval Warning in Asset Report Yes, replace the asset
Performance Max asset group "Low" rating in Asset Report, reduced reach on sensitive placements Low rating, no explicit error Yes, update the asset
Demand Gen / Discovery Reduced distribution without formal disapproval Asset Report warning Yes, replace the asset
✅ Confirmed by Google Merchant Center: Images with overlaid promotional content receive the disapproval code "Promotional overlay on image" or "Text on image". The disapproval targets the individual product, not the account. To recover: remove the text from the image and update the image URL in the feed. Keeping the same URL delays re-processing by up to 6 weeks. Source: Google Merchant Center, How to fix: Text on image.

The key difference between Shopping and Display: Shopping issues a formal disapproval that cuts product visibility immediately. Display never formally disapproves, but quietly reduces distribution. The damage builds slowly and often stays invisible in standard reports unless you actively monitor individual asset ratings.

Patterns Observed Directly: Cases Not in the Documentation

⚠️ Everything in this section comes from patterns observed on real campaigns. None of it is confirmed by Google as guaranteed system behaviour.

The system tells readable text from decorative text, but the line is not fixed. Images with highly stylised type, distorted decorative fonts, layered italics, elaborate handwriting sometimes pass without being flagged. OCR likely struggles with fonts that look very different from standard characters. That said, this is not a reliable workaround, results vary font by font.

Detection seems more sensitive on white backgrounds than on dark or textured ones. Light text on a dark background is harder for standard OCR to catch. In practice, images with light text on dark backgrounds tend to receive fewer penalties than images with dark text on light backgrounds, same font size, same content. Use with caution before building it into your creative process.

Text inside geometric shapes gets flagged more consistently. A claim placed inside a circle, a hexagon, or a coloured rectangle triggers detection more reliably than the same text on an open background. The system appears to recognise "text inside a shape" as a strong signal of an artificial overlay, a badge looks like a badge, regardless of what it says.

💡 The result that surprised me most: I found that the same image produced different ratings depending on which campaign it was placed in. An image with 18% text coverage got a "Good" rating in one campaign and a warning in another, different audiences, different placements, same asset. My hypothesis, impossible to verify without internal data, is that the system weighs the asset in context relative to other assets in the same campaign.

Google Shopping's detection is stricter than competing platforms. The same images, same amount of text on top, consistently get flagged on Google Shopping while passing on social ad platforms. Google Merchant Center introduced progressively tighter image requirements from 2022 onward, with further tightening in 2024–2025.

How to Structure Creatives to Pass Detection

The goal is not to fool the system, it is to route the commercial message through the right channels so the image itself stays clean.

  1. Move promotional text out of the image. Prices, discounts, claims, and CTAs belong in the ad's headline and description fields. Google places them on the image in the final format, the user sees the same result, but the system does not count them as overlays on the uploaded image.
  2. For Shopping: keep the main image clean and use additional_image_link for lifestyle variants. The primary image (image_link) must have no overlays. Additional images via additional_image_link face slightly looser requirements.
  3. Turn on Automatic Image Improvements to fix existing overlays at scale. Google Merchant Center can automatically remove watermarks and overlays from your main image. Enable it under Growth → Manage Programs. It works well on the most common overlay types but will not handle every case.
  4. Check detection before launch with Google Vision AI. The Google Cloud Vision Text Detection API returns a bounding box for every text element it finds. Add up those boxes and divide by the total image area to get an estimate of text coverage. It is not identical to Google's internal calculation, but it is the closest publicly available tool.
  5. For Display banner assets, apply the visual-fifth check. If the text in the image takes up more than roughly one fifth of the frame by eye, it is likely over the 20% limit. A rough guide, not a measurement tool, but useful as a fast pre-upload check.
  6. Update the image URL every time you correct an overlay. Keeping the old URL after editing the image means waiting up to 6 weeks for a re-crawl. Adding even a version tag to the URL (e.g. ?v=2) triggers re-processing within 24–72 hours.
⚠️ What not to do: Do not try to beat the system by matching text colour to the background, rotating text, or using decorative fonts to confuse OCR. The model updates regularly. These tricks give inconsistent results and can trigger retroactive disapprovals after a model update. The correct approach is to separate the text from the image using the ad's built-in fields, not to hide text inside the image.

FAQ: Overlaid Text Detection in Google Ads

How does Google detect overlaid text in images?
Google's automated review combines OCR (which reads the text), computer vision (which measures the area text covers), and semantic analysis (which distinguishes promotional copy from text native to the original image). The infrastructure is the same as Google Cloud Vision AI. For the vast majority of assets, the decision is fully automated with no human review.
What is the 20% rule for text in Display ads?
For Google Display campaigns using Responsive Display Ads, text in the uploaded image must not cover more than 20% of the total image area. Text that Google adds in the assembled ad, headlines, descriptions, is not counted. Crossing the threshold does not trigger a formal disapproval, but it does reduce distribution and lower the asset's quality score.
Does text in the image cause automatic disapproval?
It depends on the format. For Shopping on Merchant Center, promotional text on the image triggers an automatic disapproval labelled "Promotional overlay on image" or "Text on image". For Responsive Display Ads and Display formats, there is no formal disapproval, but distribution drops and the asset rating falls. For Performance Max, the asset is accepted but rated "Low" if text covers a significant area.
Is a brand watermark treated as a problematic overlay?
Yes. The system flags brand watermarks, logos placed on top of the product, photo credits, and copyright notices. For Shopping, a visible watermark on the product almost always leads to disapproval. For Display, it adds to the text coverage percentage. Adding brand watermarks to ad images is not compatible with the requirements of any major Google Ads format.
How can I test whether my image is over the 20% text limit?
Google does not offer a pre-upload measurement tool. Your options are: run the image through Google Cloud Vision AI Text Detection to get bounding boxes and calculate the covered area; apply the visual-fifth rule (if text fills more than roughly one fifth of the frame, it is likely over the threshold); or upload the asset, check the Asset Report rating, and replace it if needed. Changing the image URL at the same time cuts re-processing time to 24–72 hours.
Can Automatic Image Improvements remove overlaid text automatically?
Yes, for Shopping via Merchant Center. Enable Automatic Image Improvements under Growth → Manage Programs. The feature removes watermarks and overlays from the main image in many common cases. It does not cover all overlay types and struggles with text tightly integrated into the product shot. It is most useful as a bulk fix for large catalogues, not as a replacement for manual corrections on complex images.

All articles

See all →