.. _auto_image_compare:

*COMPUTE PIXEL BASED COMPARISON FROM TWO IMAGES*
================================================

Computes a pixel-based similarity score between two input images. Use this worker to quantitatively compare simulation contour plots, test images, or any raster outputs for visual correlation or regression checks.

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

Classification: **process**.

Tagged: ``image_compare``, ``image_diff``, ``pixel_comparison``, ``raster``, ``similarity_score``, ``visual_regression``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Image1
     - image1
     - text
     - —
     - 
     - Path or URL to the first input image (reference image); accepts standard raster formats (PNG, JPEG, BMP). Must be the same resolution as Image2 for a valid pixel-level comparison.
   * - Image2
     - image2
     - text
     - —
     - 
     - Path or URL to the second input image (candidate/comparison image); must match the resolution and color depth of Image1 for accurate pixel-based scoring.

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - image_compare_output_1
     - image_compare_output_1
     - scalar
     - Scalar similarity score resulting from the pixel-based comparison (e.g., SSIM, RMSE, or percentage match); higher values typically indicate greater visual similarity between the two images.

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

- ai_ml.vision
- data.correlation

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>image_compare</code>. Schema hash: <code>99344d62dc44</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>