Camera-Based Document Image Mosaicing

In this paper we present an image mosaicing method for camera-captured document images. Our method is unique in not restricting the camera position, thus allowing greater flexibility than scanner-based or fixed-camera-based approaches. To accommodate for the perspective distortions introduced by varying poses, we implement a two-step image registration process that relies on accurately computing the projectivity between any two document images with an overlapping area as small as 10%. In the overlapping area, we apply a sharpness based selection process to obtain seamless blending across the border and within. Experiments show that our approach can produce a very sharp, high resolution and accurate full page mosaic from small image patches of a document.