Statistical mixture model for documents skew angle estimation

• Published in: Pattern recognition letters Vol. 32; no. 14; pp. 1912 - 1921
• Main Authors: Egozi, Amir, Dinstein, Its’hak
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 15-10-2011; Elsevier
• Subjects: Applied sciences; Exact sciences and technology; Expectation Maximization (EM); Image processing; Information, signal and communications theory; Linear least squares; Signal processing; Skew detection; Statistical mixture models; Telecommunications and information theory; Skew detection; Statistical mixture models; Linear least squares; Expectation Maximization (EM); Performance evaluation; Image processing; Straight line; Mixture theory; Statistical method; Document image processing; Accuracy; Asymmetry; Gaussian noise; Least squares method; Statistical model; EM algorithm
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2011.07.004

► In this paper we present a novel approach for detecting the skew of document images. ► The proposed method is based on a special statistical mixture model. ► The model can be viewed as a GMM where the mean of each component is a straight line. ► The parameters of the statistical model are estimated using the EM algorithm.
We present a statistical approach to skew detection, where the distribution of textual features of document images is modeled as a mixture of straight lines in Gaussian noise. The Expectation Maximization (EM) algorithm is used to estimate the parameters of the statistical model and the estimated skew angle is extracted from the estimated parameters. Experiments demonstrate that our method is favorably comparable to other existing methods in terms of accuracy and efficiency.