Capture and Dewarping of Page Spreads with a Handheld Compact 3D Camera

This paper describes a system for capturing images of books with a handheld 3D stereo camera, which performs dewarping to produce images that are flattened. A Fuji film consumer grade 3D camera provides a highly mobile and low-cost 3D capture device. Applying standard computer vision algorithms, camera calibration is performed, the captured images are stereo rectified, and the depth information is computed by block matching. Due to technical limitations, the resulting point cloud has defects such as splotches and noise, which make it hard to recover the precise 3D locations of the points on the book pages. We address this problem by computing curve profiles of the depth map and using them to build a cylinder model of the pages. We then employ meshes to facilitate the flattening and rendering of the cylinder model in virtual space. We have implemented a prototype of the system and report on a preliminary evaluation based on measuring the straightness of resulting text lines.