© The Institution of Engineering and Technology
Skew estimation of scanned document is important for document analysis and recognition. Owing to the complexity inherent in the document, some methods only process the documents with a small skew angle or specified content, layout and have high computational cost. A fast and robust skew estimation method is proposed based on a bilinear filtering model, which is used to detect edges existing in the document. Some foreground areas in the document have been extracted without considering document layouts or contents. The proposed approach enhances the structure of the document and reduces the effects of the noises in the document. It combines filtering operators into a single approach, so noise filtering which is an unavoidable pre-processing in the previous skew detection methods has been overcome. A dominant angle has been estimated based on the detected edges. According to the estimated dominant angle, a skew angle can be determined efficiently without confining the search space or making assumptions including skew angle range and layout of the document in advance. The proposal greatly reduces the computational time and works in an unsupervised style. Comparative tests with the state-of-the-art skew estimation methods indicate the superior performance of the developed approach.
References
-
-
1)
-
Zhang, R., Hu, Y., Fang, Z., Zhang, L.: `Skew detection and correction method of fabric images based on Hough transform', Proc. Intelligent Computation Technology and Automation, 2009, p. 340–343.
-
2)
-
Arvind, K.R., Kumar, J., Ramakrishnan, A.G.: `Entropy based skew correction of document images', Proc. Int. Conf. on Pattern Recognition and Machine Intelligence, 2007, p. 495–502.
-
3)
-
Ávila, B.T., Lins, R.D.: `A fast orientation and skew detection algorithm for monochromatic document images', Proc. ACM Symp. on Document Engineering, 2005, p. 118–126.
-
4)
-
C.-T. Lin ,
K.-W. Fan ,
C.-M. Yeh
.
High-accuracy skew estimation of document images.
Int. J. Fuzzy Syst.
,
3 ,
119 -
226
-
5)
-
J. Weickert ,
H. Scharr
.
A scheme for coherence-enhancing diffusion filtering with optimized rotation invariance.
J. Vis. Commun. Image Represent.
,
103 -
118
-
6)
-
Egozi, A., Dinstein, I., Chapran, J., Fairhurst, M.C.: `An EM based algorithm for skew detection', Proc. Int. Conf. on Document Analysis and Recognition, 2008, p. 277–281.
-
7)
-
C.H. Chou ,
S.Y. Chu ,
F. Chang
.
Estimation of skew angles for scanned documents based on piecewise covering by parallelograms.
Pattern Recognit.
,
2 ,
443 -
455
-
8)
-
Marashi, N., Shanbezadeh, J., Sarafzadeh, A.: `A fast and efficient skew estimation of cheque images using physical structure of image and projection profile', Proc. Int. Conf. on Mechatronics and Machine Vision in Practice, 2008, p. 243–247.
-
9)
-
M.E. Celebi
.
Real-time implementation of order statistics based directional filters.
IET Image Process.
,
1 ,
1 -
9
-
10)
-
S. Kay ,
G. Lemay
.
Edge detection using the linear model.
IEEE Trans. Acoust., Speech Signal Process.
,
5 ,
1221 -
1227
-
11)
-
A. Chaudhuri ,
S. Chaudhuri
.
Robust detection of skew in document images.
IEEE Trans. Image Process.
,
2 ,
344 -
349
-
12)
-
Scharr, H.: `Optimal operators in digital image processing', 2000, PhD, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Germany.
-
13)
-
Sadri, J., Cheriet, M.: `A new approach for skew correction of documents based on particle swarm optimization', Proc. Int. Conf. on Document Analysis and Recognition, 2009, p. 1066–1070.
-
14)
-
S. Li ,
Q. Shen ,
J. Sun
.
Skew detection using wavelet decomposition and projection profiles.
Pattern Recognit. Lett.
,
5 ,
555 -
562
-
15)
-
S. Lakshmi ,
D.V. Sankaranarayanan
.
A study of edge detection techniques for segmentation computing approaches.
IJCA Spec. Issue on CASCT
,
35 -
41
-
16)
-
Y. Hong
.
Skew correction of document images using interline cross-correlation.
Graph. Models Image Process.
,
6 ,
538 -
543
-
17)
-
Liang, J., Tan, G.: `An efficient algorithm for skew-correction of document image based on cyclostyle matching', Proc. Int. Conf. on Computer Science and Software Engineering, 2008, p. 1267–1270.
-
18)
-
C. Singh ,
N. Bhatia ,
A. Kaur
.
Hough transform based fast skew detection and accurate skew correction methods.
Pattern Recognit.
,
12 ,
3528 -
3546
-
19)
-
A.A. Mascaro ,
G.D.C. Cavalcanti ,
C.A.B. Mello
.
Fast and robust skew estimation of scanned documents through background area information.
Pattern Recognit. Lett.
,
11 ,
1403 -
1411
-
20)
-
Fan, H.J., Zhu, L.L., Tang, Y.D.: `Skew detection in document images based on rectangular active contour', Proc. Int. Journal on Document Analysis and Recognition, 2010, p. 261–269.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2011.0236
Related content
content/journals/10.1049/iet-ipr.2011.0236
pub_keyword,iet_inspecKeyword,pub_concept
6
6