Y. Kurosu et H. Masuzaki, A METHOD OF AUTOMATIC SKEW NORMALIZATION FOR INPUT IMAGES, IEICE transactions on information and systems, E81D(8), 1998, pp. 909-916
It becomes essential in practice to improve a processing rate and to d
ivide an image into small segments adjusting a limited memory, because
image filing systems handle large images up to Al size. This paper pr
oposes a new method of an automatic skew normalization, comprising a h
igh-speed skew detection and a distortion-free dividing rotation. We h
ave evaluated the proposed method from the viewpoints of the processin
g rate and the accuracy for typed documents. As results, the processin
g rate is 2.9 times faster than that of a conventional method. A pract
ical processing rate for Al size documents can be achieved under the c
ondition 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 Al size documents is divided into 200 segments, w
hereas the conventional method cause the error angle of 1.68 degrees.