Script Recovery from Scanned Document Image

Document digitization with scanner in text document images which have distortions that deteriorate the quality of the document. We propose a goal-oriented rectification methodology to recover the document from distorted document image. Our approach relies upon a coarse-to-fine strategy. First, a coarse rectification is accomplished with the projection of the curved surface on the plane which is guided by the textual content’s appearance in the document image while incorporating a transformation which does not depend on specific model primitives or scanner setup parameters. Secondly, normalization is applied on the word level aiming to restore all the local distortions of the document image. Experimental results on various document images with a variety of distortions demonstrate the robustness and effectiveness of the proposed rectification methodology that improves OCR accuracy. It finds its application widely in de-warping of document images, images captured from sculptures, from cursive handwritten text, text from palm leaves and so on...