Image processing method, image processing device and scanner

Abstract

An image processing method generally includes: obtaining a vanishing point on a curve surface in a two-dimension image; extracting all the straight line segments between a top contour line and a bottom contour line of the curve surface by the vanishing point; removing a perspective distortion to get parallel straight line segments; obtaining the lengths of the straight line segments, obtaining the true width of each of the straight line segments in a three-dimension space and the depth increment of the straight line segments according to the lengths; obtaining the expanded width of each straight line segment according to the true width and the depth increment; obtaining the total expanded width of the curve surface to transform it into a flat surface; transforming image contents on the curve surface onto the flat surface. The method can be applied when scanning an open book.

Description

technical field

[0001] The invention relates to the field of image processing, in particular to an image processing method for de-distorting captured images. Background technique

[0002] When an image of a book is captured by a non-contact scanner or camera, the book will have a certain curvature due to its thickness. As a result, the image captured by the scanner or camera will have geometric distortions caused by the curvature. Figure 1a An example of an image of a book scanned by a non-contact scanner with distortion caused by bending is shown. It is difficult to read the content in this book, and using such distorted images for subsequent operations, the recognition accuracy is also low.

[0003] Various methods have been proposed to correct distortions in distorted book images. Traditional book image correction methods can be divided into two categories: content-independent correction methods and content-based correction methods.

[0004] For a content-independent ...

Images