[Python] AWS Textract OCR Issue: Troubleshooting and Resolving OCR Errors or Limitations

I have a PDF document with a 'Cover Details' section. Under this section, there are lines with either a check mark or an unchecked mark image related to them. How can I extract this information using AWS Textract OCR? I can currently only read the text.

I have attached the image file for reference.

I uploaded the PDF file to AWS Textract, but it only extracted the text. The check mark or unchecked mark images were not extracted. I need to determine if a check mark image is present in the row, it should be marked as true. If an unchecked mark image is present, it should be marked as false.

Continue reading...