---
title: 'AWS Rekognition image analysis'
description: 'Automatically add labels, text, celebrities, face attributes and content moderation results to your images with AWS Rekognition, and choose which results end up in your metadata.'
url: https://www.medialab.co/support/core/metadata/aws-rekognition
---

# AWS Rekognition image analysis

With AWS Rekognition, MediaLab analyzes your uploaded images and fills in metadata automatically, so images are easier to find and organize from the moment they are uploaded. It is one of the options for [AI metadata detection](https://www.medialab.co/support/core/metadata/ai-metadata-detection).

AWS Rekognition is available on request. [Contact us](https://www.medialab.co/contact) to enable it for your account.

### What it detects

| Detection | What it adds |
|---|---|
| **Label detection** | Objects, scenes and concepts in the image, such as "car", "beach" or "crowd". |
| **Text detection** | Text visible in the image, such as signs, captions or product names. |
| **Celebrity detection** | Well-known people recognized in the image. |
| **Face detection** | Faces in the image and their attributes. |
| **Content moderation detection** | Potentially unsafe or inappropriate content, so it can be reviewed before it is published. |

The results are saved in metadata fields of your metadata template. Like other metadata, they can be used to search and filter, for example in a [smart collection](https://www.medialab.co/support/core/organizing-media/collections) of all images showing a specific product. The complete analysis is also kept with the file.

### Choosing which results end up in your metadata

You decide which results are saved by adding fields with these short names to your template in the [Metadata Template Editor](https://www.medialab.co/support/core/metadata/metadata-template-editor). Only the fields you add are filled in; you can give them any label you like. Use the field type shown in the table: results that can contain several values, such as labels, need a **Select (lookup)** field.

| Field short name | Field type | Contents |
|---|---|---|
| `aws_rekognition_labels` | Select (lookup) | Detected labels, most confident first |
| `aws_rekognition_labels_aliases` | Select (lookup) | Alternative names for the detected labels |
| `aws_rekognition_labels_categories` | Select (lookup) | Categories of the detected labels, such as "Vehicles and Automotive" |
| `aws_rekognition_text_lines` | Select (lookup) | Lines of text found in the image |
| `aws_rekognition_celebrities` | Select (lookup) | Names of recognized celebrities |
| `aws_rekognition_faces_age_range_low` / `aws_rekognition_faces_age_range_high` | Number | Estimated age range of the people in the image |
| `aws_rekognition_faces_genders` | Select (lookup) | Estimated genders |
| `aws_rekognition_faces_emotions` | Select (lookup) | Detected emotions, such as happy or calm |
| `aws_rekognition_faces_has_smile`, `aws_rekognition_faces_has_eyes_open`, `aws_rekognition_faces_has_mouth_open`, `aws_rekognition_faces_has_sunglasses` | Checkbox | Yes/no per face attribute |
| `aws_rekognition_moderation_has_moderation` | Checkbox | Yes when potentially unsafe content was found |
| `aws_rekognition_moderation_l1`, `aws_rekognition_moderation_l2`, `aws_rekognition_moderation_l3` | Select (lookup) | Moderation labels, from broad (level 1) to specific (level 3) |

Detected values never overwrite metadata that was already filled in, so manual input is kept.

### Fine-tuning the results

Administrators can adjust the analysis under **Settings → Extensions → AWS Rekognition**:

- Switch each type of detection on or off.
- **Minimum confidence**: only keep results the AI is sufficiently sure about.
- **Maximum labels** and **Maximum lines of text**: limit how many results are saved per image.
- **Label categories excluded** and **Labels excluded**: leave out labels you don't need, such as entire categories.

Changes apply to images analyzed after saving.

### Good to know

- AWS Rekognition analyzes images. For video and audio, see the enterprise options in [AI metadata detection](https://www.medialab.co/support/core/metadata/ai-metadata-detection).
- AI detection is not perfect. Users with edit rights can correct or remove detected values like any other metadata.
- The analysis runs after upload, so results appear shortly after an image has been processed.

### References

- [AI metadata detection](https://www.medialab.co/support/core/metadata/ai-metadata-detection)
- [Metadata Template Editor](https://www.medialab.co/support/core/metadata/metadata-template-editor)
- [Collections and smart collections](https://www.medialab.co/support/core/organizing-media/collections)
