A Robust and Fast Dewarping Method of Document Images

Abstract

Document image distortion often appears when captured by the camera; this may induce recognition mistakes by OCR. In this paper, a robust and fast dewarping method of document images is proposed. Compared with traditional method, the computation of the correction baseline and the distance for vertical displace in this method is independent of the document's content, so it can guarantee the precision of words' slope and make all words be align with the same line. The computation complexity of the algorithm is discussed at the end of this paper, and comparative experiments with traditional method are made. The experimental results show that the proposed algorithm is efficient and robust.