Unlock instant, AI-driven research and patent intelligence for your innovation.

A binary method of ancient document images

An image binarization and document image technology, which is applied in the field of image processing, can solve the problems of algorithm noise sensitivity and the influence of binarization results, etc., and achieve the effect of suppressing noise and performing well

Inactive Publication Date: 2019-01-11
GANSU INST OF POLITICAL SCI & LAW
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The local threshold method overcomes the defect that the global threshold method cannot handle unevenly illuminated images well, but the algorithm is very sensitive to noise, and the change of algorithm parameters has a great impact on the binarization result

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A binary method of ancient document images
  • A binary method of ancient document images
  • A binary method of ancient document images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In an embodiment of the present invention, a method for binarizing an image of an ancient book document, specifically including character stroke edge extraction combining high and low contrast, local threshold calculation, and image binarization;

[0031] Combining high-contrast and low-contrast character stroke edge extraction: low-quality document images have more degradation, character handwriting is of different shades, and the background is rough and disturbed. When only high-contrast areas are used to process images, low-contrast is easy to lose. Foreground information, therefore, needs to be processed simultaneously by combining high and low contrast information. The whole method can be divided into the following three steps:

[0032] S1. Acquisition of high-contrast areas: firstly, median filtering is performed on the image; secondly, all pixels of the image are traversed, and in a window of 3*3 size, the contrast of each pixel is calculated using formula (1) to...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a binary method of ancient document images. The method includes high- and low-contrast character stroke edge extraction, local threshold calculation, and image binarization. The invention provides a binarization method of ancient document images, which uses contrast information of edge region to carry out adaptive calculation of local threshold value, and can keep foreground information of lower contrast while suppressing noise. Ink stains, page fouling and uneven texture background in low-quality document images can be processed effectively. On the DIBCO database, by comparing with other algorithms, the algorithm behaves well in the performance indexes of Fm, p-Fm, PSNR and DRD.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a binarization method for images of ancient book documents. Background technique [0002] Document image binarization is the primary work of ancient book document recognition. Its goal is to divide the document image into two parts, the foreground and the background, and provide a good foundation for subsequent line word segmentation and recognition. In traditional optical character recognition applications, usually printed or handwritten document images with better quality are processed, and better binarization results can be obtained by using some classical methods. However, for ancient book documents, there is a lot of degradation. Degradation factors mainly include time (excessive storage time leads to yellowing of pages and lower text contrast), technical (early book printing technology is backward), physical (ink stains, water stains) and various human-induced factors. Sta...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/38G06K9/34G06K9/40
CPCG06V10/26G06V10/28G06V10/30
Inventor 李振江王维兰
Owner GANSU INST OF POLITICAL SCI & LAW