Image to Text

Use Image to Text to extract text from BLOB image files. You can also use this tool to perform automatic table detection.

Tool Components

The Image to Text tool has 3 anchors.

• D anchor: Use the D anchor to connect to the image data you want to convert to text.
• T anchor: Use the T anchor to use automatic table detection. You don't have to configure anything to use that feature.
• Output anchor: Pass text you've extracted, either from raw text data like PDFs or from tables the tool has detected, downstream.

Configure the Tool

1. Add an Image Input to the canvas and connect it to the Image to Text tool.
2. Select the Image you want to extract text from.
3. Identify the Language of the text contained in the image.
4. Run the workflow to convert the image to text.

Output

If you are converting images to text using the D anchor, Image to Text creates a column in the dataset. Each row in the column contains text from the pages of the PDF image. If you use the T anchor, the tool outputs a table that matches the table detected in the image files you provide.