.. _auto_cvision_classifyimages:

*COMPUTER VISION. CLASSIFY THE IMAGES BASED ON A TRAINING SET*
==============================================================

Classifies a collection of images using a supervised computer-vision model trained on a provided labelled training set. Use this worker when you need to assign category labels to new images based on examples of known classes.

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

Classification: **process**.

Tagged: ``computer_vision``, ``cvision``, ``image_classification``, ``supervised``, ``training_set``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - File Name
     - filename
     - collection
     - —
     - 
     - Collection pointing to the image file(s) to be classified; accepts any common raster format (PNG, JPEG, BMP). Leave unset if images are supplied indirectly via the training-set collection.
   * - Training Set
     - trainingset
     - collection
     - —
     - 
     - Collection of labelled reference images used to train or configure the classifier; each entry should associate an image file with its ground-truth class label.

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - cvision_classifyimages_output_1
     - cvision_classifyimages_output_1
     - text
     - Text result containing the predicted class label(s) for each input image, typically formatted as a JSON or delimited string mapping filename to classification outcome.

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

- ai_ml.supervised.classification
- 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_classifyimages</code>. Schema hash: <code>00b9b42807e2</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>