TR-IIS-05-011    Fulltext

Estimation of Skew Angles for Scanned Documents Based on Piecewise Covering by Parallelograms

Fu Chang, Chien-Hsing Chou, and Shih-Yu Chu


Abstract

We propose a fast and robust skew estimation method for scanned documents that estimates skew angles based on piecewise covering of objects, such as textlines, figures or tables. The method first divides a document image into a number of non-overlapping slabs in which each object is covered by parallelograms. It then estimates the skew angle based on these parallelograms or, equivalently, their complementary regions. Putting this method to a systematic test and comparing it with a few alternatives, we find favorable results for our method in terms of accuracy rates, sensitivity to non-textual objects, effectiveness in dealing with documents of unspecified reading order, and computational efficiency. Some work is also conducted to find an effective way to further shorten its computation time at the expense of an extremely small loss of accuracy.

Keywords: Document image analysis, piecewise covering, skew angle, skew angle estimation