Ok - so these are image files that are not in readable format (OCRed). Alfresco does not provide those tools out of the box, but there are plenty of options. You can integrate with another tool, like AWS Textract (I am not sure of your architecture - on premise or cloud, etc.). You can also use transformations to perform OCR with other tools.
However, based on what you are trying to do, the best method might be a capture (ingestion) provider - like Ephesoft. These tools can be trained to find specific information (by zone or surrounded text) and then optical character recognize the information and either save that at full text or apply the information found into particular custom metadata fields.
However, you will need another product to work in conjunction with Alfresco - or at least that is my experience.
