We propose a novel algorithm for improving the quality of binarized document images captured with a mobile device under low light conditions. In such scenarios, images captured without a flash often result in blur artifacts and poor signal-to-noise ratio, while images taken with the flash may produce information loss due to specular reflection in a localized region termed a “flash spot”. Our algorithm automatically triggers the capture of a pair of images, one with and one without flash, in rapid succession. The flash spot region (FSR) is first detected. The two images are then accurately aligned within the FSR using a multiscale alignment technique. Finally the images are binarized and fused in the vicinity of the FSR using an intelligent technique that minimizes fusion boundary artifacts. The result is a binary image that is largely identical to the binarized flash image, except within the FSR where content from the no-flash image is selectively incorporated. To our knowledge this is the first attempt to employ flash/no-flash fusion to improve binarization of mobile document images. Results show superior qualitative and quantitative performance of the proposed algorithm when compared with standard binarization applied to either the flash or no-flash image.

The expanding sphere algorithm computes an alpha shape tetrahedralization of a point set. Starting with a seed tetrahedron, the circumscribing sphere is squeezed through each face until it either touches another point or exceeds a preset radius. If no point is found, that face of the tetrahedron is part of the surface of an object. If a point is found, a new tetrahedron is constructed. This process is iterated until all the faces of the tetrahedra have been processed and no more connected points can be found. If there are points left over, the process is iterated, creating additional objects. The algorithm generates a list of objects, with an alpha shape tetrahedralization and a surface triangulation for each. Any points that cannot be made part of a valid tetrahedron are also returned in the extra points list. The algorithm is efficient for uniformly distributed point sets, with a running time that is linear in the number of points for such sets. Since the operations are local, it is also robust.