In short: Image features describe visual elements, such as official packaging or a cheap imitation, so Zeal can recognise them and use them in filters and Auto-Moderation rules, once the AI model has been trained on them.
Understanding Image Feature Detections
Image Feature Detections let you tag and describe visual elements that appear in listings, posts or product images. You can then use them in Auto-Moderation rules, for example to automatically flag listings that show counterfeit packaging or unauthorised variants.
You configure them under Settings > Image Features.
Important: Custom features are not detected automatically until the AI model has been trained on those visuals; adding a label alone doesn't trigger detection. Contact your Account Manager to set this up first.
1. How to configure a new image feature
Each feature you configure gives the model, and your team, a clear definition of what to look for. The example below uses the DualSense controller box.
Go to Settings > Image Features.
Upload a reference image: choose a clear image that represents the visual feature you want to detect (e.g. the official DualSense box). This image helps the detection model learn what to look for.
Define the feature name: for example
Box - DualSense. Use a descriptive, consistent naming convention, such asBox - [Product Name],Logo - [Brand]orTag - [Type].Select the Object Category: choose the right visual category for what you're defining, for example
Packaging, since the box is part of the product's packaging.Select the Type: this decides how the system interprets the visual cue in moderation (see the table below). For example
Info, as this is an authentic packaging reference.Add a Description: briefly explain what the detection represents and any visual cues to recognise it. For example: “DualSense box — Controllers will always have the term ‘LIMITED EDITION’ and the trademark of the featured title on the packaging.”
Link related features (parent/child relationship): group related detections, for example Parent:
Box - DualSenseand Child:Image feature – Blister Packaging – Cheap. This lets Auto-Moderation rules compare expected features (authentic packaging) against known risky ones (cheap blister packaging).Submit and test: click Submit to save the configuration. The feature can then be selected in Auto-Moderation rules, for example “If image shows Blister Packaging – Cheap and not Box – DualSense, flag as potential counterfeit”.
Feature types
Type | Use it for |
Info | Neutral or reference visuals (e.g. official packaging, standard logos) |
Logo | Any recognisable brand or trademark image |
Suspicious Feature | Elements that might indicate an issue (e.g. low-quality box print, missing label) |
Highly Suspicious | Strong indicators of infringement or counterfeiting, but not definitive |
Obvious Counterfeit | Features that clearly identify a fake product (e.g. “PlayStation” misspelled, wrong colour scheme) |
Learn more: AI Image Feature Detection · Building Auto-Moderation Rules
2. Using image features in Zeal
Once configured, image features help you find and act on items that show them.
Filtering: users can filter for these image reasons with the Reasons filter, across all views.
Auto-Moderation: the feature can be selected as a condition in Auto-Moderation rules.
Learn more: Reasons Filter · Auto-Moderation Rule Examples
3. Best practices
Well-defined features are easier for the model to learn and for your team to use.
Names: keep feature names short and consistent.
Reference images: always include a clear visual reference.
Parent-child links: use them to reflect authenticity hierarchies (e.g. "Official box" → "Fake box variant").
Descriptions: add detailed descriptions so others understand what the system is detecting and why.
Learn more: Auto-Moderation
Quick reference
If you want to know… | Look at… |
Why a new feature isn't being detected | Understanding Image Feature Detections |
How to set up a feature | 1. How to configure a new image feature |
Which Type to choose | Feature types |
How to find items showing a feature | 2. Using image features in Zeal |
How to use features in rules |