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 input anchor: Use the D input anchor to connect the PDF image you want to convert.
• T input anchor: Use the T input anchor to connect annotations from the Image Template tool.
• Output anchor: Use the output anchor to pass the converted text 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.