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

Degenerated text image recovery method

A text image and restoration method technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as poor restoration effect, inability to provide clear images through image processing, and achieve the effect of ensuring accuracy

Active Publication Date: 2021-08-06
CHONGQING NORMAL UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to accurately identify these text images, it is necessary to restore these degraded text images. Although the restoration of degraded text images in the prior art can achieve the purpose of restoration to a certain extent, the restoration effect is not good. Does not provide a clear image for subsequent image processing

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
  • Degenerated text image recovery method
  • Degenerated text image recovery method
  • Degenerated text image recovery method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Below in conjunction with accompanying drawing, the present invention is described in further detail:

[0031] A kind of degradation text image processing method provided by the present invention comprises the following steps:

[0032] S1. Collect the degraded text image to be restored, and perform binarization processing on the degraded text image;

[0033] S2. Extract the transition region R of the degraded text image that has been processed by binarization, and then determine the gray mean value of the transition region R;

[0034] S3. Perform normalization processing on the degraded text image after binarization, so that each pixel value of the degraded text image after binarization is in the interval [-1, 1];

[0035] S4. Build an image restoration model:

[0036] Among them, u is the evolution function, v is the evolution auxiliary function;

[0037] F(u)=sign(M-u), M is the gray mean value in the transition region R; λ is a normal number, set according to th...

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 provides a degraded text image recovery method, which comprises the following steps of S1, acquiring a degraded text image to be recovered, and carrying out binarization processing on the degraded text image, S2, extracting a transition region R of a degraded text image subjected to binarization processing, S3, performing normalization processing on the binarized degraded text image to enable each pixel point value of the binarized degraded text image to be in an interval [-1, 1], S4, constructing an image recovery model, and S5, inputting the normalized degraded text image into an image recovery model for recovery, and outputting a recovered image. According to the method, the degraded text image can be effectively recovered, clear image information is provided for subsequent image processing and recognition, and the accuracy of subsequent processing and recognition is ensured.

Description

technical field [0001] The invention relates to an image restoration method, in particular to a degraded text image restoration method. Background technique [0002] Binarization of text images is an important step before optical character recognition (OCR). However, text images, especially historical text images, are more or less degraded due to their age, such as uneven illumination, low contrast, transparent background, stain pollution, weak handwriting, etc. Among them, background degradation is a ubiquitous and difficult text degradation phenomenon (see figure 1 ), these degradations may be caused by stains, infiltration, damage, etc. [0003] In order to accurately identify these text images, it is necessary to restore these degraded text images. Although the restoration of degraded text images in the prior art can achieve the purpose of restoration to a certain extent, the restoration effect is not good. Does not provide a clear image for subsequent image processin...

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): G06T5/00G06T17/00
CPCG06T17/00G06T2207/30176G06T5/77
Inventor 王艳
Owner CHONGQING NORMAL UNIVERSITY