Model-Based Book Dewarping Method for Content-Independent Document Images

Abstract

This paper proposes a novel dewarping technique for document images based on digital cameras, from which images are warped on the curve surface of the book bound volume. Our technique transforms pixels in the curve coordinate system into the planar coordinate system. In the experiments, the test document images composed various font styles and sizes printed in common text books. The validity of our methods compares with the program's curvature correction of Abby FineReader Professional 9.0. Our technique outperforms the other up to 49 percent for word and character precisions. Nevertheless, our technique is independent on document contents, page layout, and font styles. The concept of our approach is based on dewarping the whole document pages by using the function obtained from experiments.