A Method of Skew Detection and Correction in Document Images for Personal Computers

概要

論文の詳細を見る
In order to normalize the skew angles of an input image using a personal computer, it becomes necessary to improve the processing rate and to divide an image into small segments adjusting a limited memory. This paper proposes a new method of an automatic skew normalization, comprising a high-speed skew detection and a distrotion-free dividing rotation. We have evaluated the proposed method from the viewpoints of the processing rate and the accuracy for typed documents. As result, the processing rate is 2.9 times faster than that of a conventional method. A practical processing rate for software processed on a personal computer can be achieved under the condition that the accuracy of a normalized angle is controlled within ±0.3 degrees. Especially, the rotation with dividing can have no error angle, even when the work memory size is reduced to 1/100.
一般社団法人情報処理学会の論文
1998-08-15