A fast page outline detection and dewarping method based on iterative cut and adaptive coordinate transform

In camera-based document capture systems, page outline detection and dewarping are used to improve the readability and optical character recognition (OCR) accuracy of documents. This paper presents a robust book page outline detection and dewarping method with low hardware resource requirements that can handle pages with various layouts. We propose an iterative method to detect page outlines in the presence of occlusion and clutter. Further, we propose a method based on an adaptive coordinate transform model for page dewarping. This method can dewarp documents with complex layouts that contain short text lines, graphical contents, etc., while avoiding the unpleasant image distortion induced by dewarping.