Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-textual Document Images: A Novel Approach

Skew angle estimation and correction of a document page is an important task for document analysis and optical character recognition (OCR) applications. Many approaches of skew detection can process pure textual document images successfully. But it is a challenging problem to process documents like handwritten, large areas of non-textual contents. In this direction, a novel approach for textual, large area of non-textual, handwritten document skew detection is presented in this paper. Estimation of skew angle is based on finding centroid of each connected component (CC) and plotting the major axis of the ellipse of each connected component. The proposed technique was tested on variety of images including handwritten and machine printed documents. The testing results showed a successful rate more than 98% of the data set.