Correcting page curl in scanned books

摘要

A computer implemented method for correcting distortion in an image of a page includes identifying a set of high quality (HQ) words in undistorted regions of one or more images of pages having content related to the content of the page. At least one distorted word in the image the page is identified such that each distorted word corresponds to a high quality word of the set. A global transformation function is generated for application to the image of the page so as to transform the distorted word into its corresponding high quality word. The global transformation function is applied to pixels of the image of the page.