A robust document skew estimation algorithm using mathematical morphology

Abstract

The most common problem of all document skew estimation methods using morphological operators is the limitation of skew angles and choosing the appropriate size for structuring elements. This paper introduces an improvement for methods based on mathematical morphology to estimate the skew of document images with arbitrary angles of orientation. Our proposed method can take advantages in being free with user parameters and adaptive with arbitrary skew angles of document images. Moreover, the experimental results and comparison with other methods reveal the potential of our proposed method in skew estimation not only for Latin documents but also for documents of other languages such as Japanese, Chinese, Thai, etc. © 2007 IEEE.