.. _auto_image_to_text:

*IMAGE TO TEXT WORKER*
======================

Runs Tesseract OCR on a supplied image file to extract any embedded text. Use this worker whenever you need to convert a screenshot, scanned document, or annotated plot image into a machine-readable string within a d3VIEW workflow.

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

Tagged: ``image``, ``ocr``, ``tesseract``, ``text-extraction``, ``user``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Image
     - image_file
     - file
     - —
     - ✓
     - Image file (PNG, JPEG, TIFF, etc.) containing the text to be extracted; must be attached to the workflow — required, no default.
   * - Options
     - options
     - textarea
     - - -l eng -psm 6 digits
     - 
     - Tesseract CLI flags passed verbatim after the image path (e.g. `--l eng --psm 6 digits`); leave at default `--l eng --psm 6 digits` for standard English single-block digit recognition.

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - Text Output
     - text_output
     - text
     - Plain-text string produced by Tesseract, with newlines preserved between lines detected in the image.

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

- ai_ml.vision

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>platform</code> schema. Worker id: <code>image_to_text</code>. Schema hash: <code>38b84d490596</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>