Method and device for binarizing document images and document image processor
A document image, binarization technology, used in instruments, character and pattern recognition, computer parts and other directions, can solve the problems of exaggerating the change of the neighborhood grayscale, ignoring the edge features of the image, prone to artifacts, etc., to achieve stable Improve the performance and optimize the effect of the binarization effect
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2014-02-19
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
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...
Examples
Embodiment Construction
[0016] figure 1 A simplified flowchart of an embodiment of the method for binarizing a document image according to the present invention is shown. like figure 1 As shown, at step S100, at least one document image of the same type to be binarized is input. In step S110, through a predetermined first binarization algorithm, select a predetermined number of document images from the input document images as training samples for learning, so as to obtain the attributes of the binary images corresponding to the training samples, as the The public reference attribute of the binary image corresponding to the at least one document image to be binarized. In step S120, each of the input at least one document image to be binarized is subjected to binarization optimization processing according to the obtained common reference attribute through a predetermined second binarization algorithm, so that each The properties of the obtained binary image are consistent with the common reference ...