Product and solution overview

CognitiveNude™ is a Cognitive Mill product that offers you a reliable nudity detection solution for any type of video.

The Automated nudity filtering for movies and user-generated video analyzes video content and, alongside the probability score of nudity detection, automatically marks the ‘unsafe’ parts of the video with exposed nudity. So that you can blur or cut them out.


  • You get the time markers for the video segments that contain nudity.
  • You can run the nudity detection process either via the UI or the API.
  • You just paste the video URL or upload a video from your device and hit the button — the rest is done automatically.
  • You get the JSON file with time markers and nudity detection score so that you can apply blur to the detected scenes or cut them out with third-party systems and software.

Output metadata

The JSON file you get after running the nude meta process is essential for Automated nudity filtering. It contains the metadata for internal use and the following data:

Id. The entity name.

Segments. Display the array of time segments containing unsafe content with their start and end time markers, the representative frame of the time segment, and the unsafety score.

  • End. The end time of the segment. Ms stands for milliseconds, and time shows when the episode appears in the video timeline.
  • Start. The start time of the segment. Ms stands for milliseconds, and time shows when the episode appears in the video timeline.
  • Repr_frame. The time marker of the representative frame for a segment containing nudity.
  • Score. The nudity detection score.
  • Scores. The detection scores specified for different types of nudity content.
  • Type. Marks the segments that contain unsafe data.

Metadata. Contains the information about the modules and versions for internal use.

Type. Indicates the type of meta, for example, nude meta.

Version. Displays the output format version of the JSON file.

        "data": [
            "id": "nude meta",
            "segments": [
                "end": {
                  "ms": 16500,
                  "time": "0:00:16"
                "repr_frame": {
                  "ms": 11000
                "score": 0.9122267663478851,
                "scores": {
                  "EXPOSED_BREAST_F": 0.9122267663478851,
                  "EXPOSED_BUTTOCKS": 0.5770045220851898,
                  "EXPOSED_GENITALIA_F": 0.4848068654537201
                "segments": [],
                "start": {
                  "ms": 9000,
                  "time": "0:00:09"
                "type": "unsafe"
            "type": "time segments"
        "metadata": {
          "description": {}
        "type": "nude meta",
        "version": ""

Demo case

This guide shows you how to run the nude meta process to get the result.json file via the UI.

Before running the nude meta process:

1. Sign in to your account at run.cognitivemill.com or register if it’s your first visit.

2. Check that you have the nude meta quota to run the process by clicking the name of your account in the top-right corner of the screen.

You land on the My Account page with the list of your quotas.

New users are provided with trial quotas. If you don’t have the required quotas, contact us at support@aihunters.com to get them.

Now you're all set.

1. Click the Run Process button on the top navigation bar.

The Run a New Process page opens.

2. Select nude meta from the Process type drop-down list.

3. In the Title field, enter a name for your process.

4. In the File source field, either paste a link to the video you want to process — the default File link option — or click the field > select Upload file > click Select file > pick the file from your device to upload.

5. Hit Run Process.

Your newly created process appears at the top of the Process List in its current status.

When the status changes to Completed, you can download metadata.

6. On the Process List page, click the three vertical dots icon next to the process.

7. In the pop-up menu that appears, click Download result.

The result.json file is downloaded to your device.

You can also preview the result in the Cognitive Mill visualizer.

1. On the Processes page, click the title of the completed nude meta process to open the video in the visualizer.

Here you can see the marked unsafe segments, where the nudity was detected.

2. Click the Play icon above the meta timeline to view only the segment marked as unsafe content.

We use cookies to ensure that we give you the best experience on our website. Read cookies policies.