Method for processing optical character recognition (ocr) data, wherein the output comprises visually impaired character images

A method for resolving contradicting output data from an Optical Character Recognition (OCR) system, wherein the output data comprises at least one visually impaired character instance due to at least one overlaid object in a document being processed by the OCR system, the method comprises:

• d) searching through the output data identifying images of characters having an image quality above a predefined level, and using these character images as a set of template images for characters,
• e) identifying location and region of a visually impaired section of the at least one visually impaired character instance,
• f) using the information about the location and the region from the visually impaired character instance to locate corresponding regions in template images, before comparing the respective template images with the at least one visually impaired character instance disregarding image content in the respective located regions when comparing, and using the template image providing the highest similarity with the visually impaired character image as a correct identification of the visually impaired character instance.