Document image rectifying method based on local information

Abstract

The invention relates to a document image rectifying method based on local information. Firstly, the dimension of a text row is determined through an average gradient value of a document image. The self-similarity of a blank row is used for tracking the text row to obtain an upper border and a lower border of the text row. The borders of vertical strokes are determined according to an interval of strokes of a character and the text row is segmented. Afterwards, a quadrangle is obtained and defined by the upper border, the lower border and the vertical borders. Image content defined by the quadrangle is a character block processing unit. Finally, inclination deformation rectification and local bilinear interpolation rectification are sequentially performed on each character block processing unit, namely a whole document image is rectified. According to the document image rectifying method based on the local information, the processing speed and the complicated conditions of a distorted document image are comprehensively taken into consideration and the document image rectifying method based on the local information has the advantages of being rapid in speed of a rectification process and good in rectification effect.

Description

technical field [0001] The invention relates to a document image correction method, in particular to a document image correction method based on local information. Background technique [0002] There are already some methods and technologies for distortion correction of document images: Literature [1,2] proposed a thick product document image correction method based on a cylindrical model, which assumes that the surface of the document image is cylindrical, and then according to Fitting curves of text lines to restore cylinder models and restore document images. This method is easy to implement and has good effect, but it has strict requirements on the distortion form, that is, the generatrix of the cylinder is completely parallel to the image plane, and the adaptability is poor. Literature [3,4] proposed a document image correction technology based on segmentation. This method firstly segmented the upper and lower boundaries of the text line and the vertical stroke boundar...

AI Technical Summary

Problems solved by technology

This method is simple to implement and has a good effect, but it has strict requirements on the distortion form, that is, the generatrix of the cylinder is completely parallel to the image plane, and the adaptability is poor.

Literature [3,4] proposed a document image correction technology based on segmentation. This method firstly segmented the upper and lower boundaries of the text line and the vertical stroke boundaries of the text, and then based on the small boundaries formed by these upper and lower boundaries and numerical stroke boundaries, Quadrilaterals are corrected. This method is similar to the process of the method of the present invention, but this method relies too much on the cutting of vertical strokes, so the correction effect on Chinese characters and Japanese character document images is not ideal.

Images