Document Capturing Method with a Camera Using Robust Feature Points Detection

This paper presents a method of capturing a document with a single camera based on the Hough transform with reduced angle domain. Document image capturing with a camera has some advantages over traditional flatbed scanners. A problem of capturing a document with a camera is to find a paper region in an image and find robust features to remove perspective distortions. If we have boundary information of a paper with a document to extract feature points, a homography could be estimated to remove perspective distortions. In this paper, text regions in a document are removed with edge plane decomposition to detect the region and the boundary of a paper in an image from a camera, because characters in a document make outliers, which make it difficult to find features. After removing text regions in a document, feature points to remove perspective distortions are extracted by the Hough transform in reduced angle domain from each decomposed edge plane. The experimental results show that the proposed method successfully removes text regions, which are outliers of finding line features to eliminate perspective distortions. A document region is extracted from the image successfully.