Check patentability & draft patents in minutes with Patsnap Eureka AI!

Deblurring method for text image based on gradient fitting

A text image and deblurring technology, which is applied in image enhancement, image data processing, instruments, etc., can solve the problem of poor image restoration effect, improve the deblurring effect, reduce computational complexity, and speed up the deblurring process Effect

Active Publication Date: 2013-10-02
JINAN UNIVERSITY
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for images whose gradient distribution does not completely obey the heavy-tailed distribution, for example, for text images, the gradient distribution is as follows figure 2 As shown, the image restoration effect is not very good

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
  • Deblurring method for text image based on gradient fitting
  • Deblurring method for text image based on gradient fitting
  • Deblurring method for text image based on gradient fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Compared with the prior art, the biggest innovation of the present invention is that according to the characteristics of the gradient distribution map of the text image, a prior probability model of the gradient distribution is constructed through linear fitting. The model is a piecewise function, and the deblurred image is processed according to the model recovery. combine image 3 The specific details of the flow chart are as follows.

[0042] S1: Input the blurred text image to be processed.

[0043] Such as Figure 4 , whose size is 185*846. The blur degradation process of a clear image is expressed by the following formula (1), where B(x,y) represents the blurred image, I(x,y) represents the original image, and N(x,y) represents noise (the main consideration of camera shooting Gaussian noise effect), H(x,y) represents the blur kernel.

[0044] B ( x , y ) = ...

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 deblurring method for a text image based on gradient fitting, which comprises the following steps: inputting a to-be-processed blurring text image; selecting a clear text image similar to the to-be-processed text image; performing the statistics of gradient distribution probability of the selected clear text image, and determining a gradient distribution prior probability model; initializing a blurring kernel; calculating the gradient distribution probability of the to-be-processed image, comparing the gradient distribution probability with the model, if the model is not similar to the gradient distribution probability, performing deconvolution operation on the to-be-processed text image and the blurring kernel, then determining whether secondary iteration processing is performed or not according to the recovery effect, if needed, adjusting the size and direction of the blurring kernel to continue comparison with the model, and once the gradient distribution probability is similar to the model or the recovery effect is reached, performing de-noising processing on the recovery text image, and outputting the processed text image. The method performs modeling according to the gradient distribution characteristics of the clear text image, effectively utilizes prior information of the text image, and facilitates recovery processing of the blurring text image.

Description

technical field [0001] The invention relates to the research field of image restoration in image processing, in particular to a text image deblurring method based on gradient fitting. Background technique [0002] The motion blur of the image is mainly caused by the camera shaking or the rapid movement of the shooting object during shooting, which makes the high-frequency information of the blurred image lost, resulting in blurred edges, which is not conducive to the preservation and use of the image. At present, image deblurring has applications in many fields such as remote sensing images and traffic monitoring, and its research has become a research hotspot in the field of image processing. [0003] The image blur degradation process can be understood as the convolution operation and noise addition process of the original image and the point spread function (that is, the blur kernel, which represents the displacement vector function expression of the imaging system), whil...

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
IPC IPC(8): G06T5/00
Inventor 石敏郑宜鹏易清明
Owner JINAN UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com