.. _auto_cvision_clusterimages:

*CREATE A CLUSTER BASED ON THE IMAGES*
======================================

Groups a collection of images into clusters using computer-vision techniques, enabling unsupervised organization of visual assets by similarity. Provide an image file collection and receive a cluster assignment output. Use this worker when you need to automatically categorize or explore patterns across a set of images.

When to use
-----------

Classification: **process**.

Tagged: ``clustering``, ``computer_vision``, ``image_clustering``, ``transformations``, ``unsupervised``, ``vision``.

Inputs
------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20 20 20

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - File Name
     - filename
     - collection
     - —
     - 
     - Collection of image file paths or references to be clustered; leave empty/null to defer file selection to a preceding worker in the workflow.

Outputs
-------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20

   * - Label
     - ID
     - Type
     - Description
   * - cvision_clusterimages_output_1
     - cvision_clusterimages_output_1
     - text
     - Text payload containing cluster assignment results (e.g. JSON or CSV mapping each image file to its cluster label/ID).

Disciplines
-----------

- ai_ml.unsupervised.clustering
- ai_ml.vision

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>cvision_clusterimages</code>. Schema hash: <code>5f2060fe0b59</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>