# Run OCR on Image

This activity is used to perform OCR on a user-specified image.

### Input

* **Image:** <mark style="color:red;">`Required`</mark>\
  Specifies the file path of the target image on which the mouse pointer is to hover.

### Configure

#### OCR Options

* **Crop Region:**\
  Specifies the region on the document to apply the OCR.
* **Intermediate Save Path:**\
  Specifies the location where intermediate files are stored. If not specified files will be stored in Windows Temp folder.
* **Language:**\
  Specifies the text language present in the document.
* **Profile:**\
  Specifies a set of optimized preprocessing steps for a given task. By default the value is set to SceenScrape.
* **Save Intermediate Files?:**\
  If set to **True** all intermediate images created during preprocessing will be saved to disk.
* **Timeout:**\
  Specifies the timeout in milliseconds to wait for the OCR operation to complete.

#### Timeout

Specifies the amount of time (in milliseconds) to wait until the specified element is found. By default the value is set to 1000 milliseconds (10 sec)

### Output

* **Extracted Text:** [`String Variable`](/getting-started/rpa-studio/variables/user-defined-variables-1.md#string)\
  Specify a variable name that stores the extracted text from the given image.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.visualyze.ai/rpa-studio/automation/vision/run-ocr-on-image.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.