Method and device for binarizing document images and document image processor

Abstract

The invention relates to a method for binarizing document images, comprising the following steps of: learning: selecting a predetermined number of document images from at least one document image to be binarized in same types through a predetermined first binaryzation algorithm as training samples for learning so as to obtain the attribute of the binary images which correspond to the training samples, wherein the obtained attribute istaken as the public reference attribute of binary images which correspond to the at least one document image to be binarized; and optimal binaryzation processing: carrying out the optimal binaryzation processing on each of the at least one document image to be binarized according to the public reference attribute through a predetermined second binaryzation algorithm so that the attribute of an obtained final binary image of each document image to be binarized is consistent with the public reference attribute. The invention also provides a device capable of executing the method and binarizing the document images and a document image processor assembled with the same. The method and the device can obtain more optimal binaryzation effects and enhance the stability of binaryzation quality.

Description

technical field [0001] The invention relates to the technical field of image processing and pattern recognition, more specifically, to a method and device for binarizing document images, and an image processor including the device for binarizing images. Background technique [0002] Binarization of document images refers to converting color or grayscale document images into binary images. During the binarization process, the usual binarization method only uses the information of a single image to achieve optimal binarization, so there is often a defect that the binarization effect is not optimized, especially when the binarization quality is low. Poor performance on stability. Even for different image copies of the same document, there are often obvious differences in binary document images obtained by using common binarization methods. [0003] In the binarization process of document images, it is especially important to improve the binarization effect and binarization qu...

AI Technical Summary

Problems solved by technology

For example, the local threshold method can handle more complex situations, but it often ignores the edge features of the image, and is prone to artifacts

For another example, the dynamic threshold method fully considers the neighborhood characteristics of the pixel, and can adaptively change the threshold according to the different background conditions of the image, and can extract the binary image more accurately, but it excessively exaggerates the neighborhood of the pixel The change of gray level will divide the background with uneven gray level distribution into the target, which will bring many false targets that should not appear.

Images