Skew Detection in Binary Document Images based on Boundary Growing Approach

摘要

Skew angle estimation is an important component of an Optical Character Recognition (OCR) and document analysis systems. In this paper, a novel and efficient (in terms of accuracy) method to estimate skew angle of a scanned document image is proposed. The proposed technique works based on fixing a boundary for connected components and growing boundaries of connected component until it reaches a pixel of neighbor connected component. The technique assumes that the space between the two adjacent text lines is greater than the space between the successive characters present in a text line. The proposed method is compared with other well known existing methods and the experimental results are also presented.