SELECTIVE DISPLAY OF OCR'ED TEXT AND CORRESPONDING IMAGES FROM PUBLICATIONS ON CLIENT DEVICE

摘要

PROBLEM TO BE SOLVED: To enable readers of OCR'ed text to toggle between a segment of the OCR'ed text and a segment of a source image containing the text segment.SOLUTION: Text is extracted from a source image of a publication using an Optical Character Recognition (OCR) process to generate a document containing a plurality of text segments. In response to a user selection, a source image corresponding to a displayed text segment is retrieved from the source image of the text and rendered in place of the selected text segment. The user can again toggle the display back to the text segment. Each text segment can be tagged with a garbage score indicating its quality. If the garbage score of a text segment exceeds a threshold value, the corresponding image segment can be automatically displayed instead.