Image correcting method and device

An image correction and image technology, applied in the field of image processing, can solve problems such as limited application scenarios, low accuracy, and large amount of calculation for image correction schemes, achieve high correction accuracy, and achieve easy results

Inactive Publication Date: 2013-09-25
北京智诺英特科技有限公司
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of large amount of calculation, low accuracy, and limited application scenarios in the image correction scheme in the related art, the present invention proposes an image correction method and device, which can avoid the use of a large number of calculations, achieve high correction accuracy, and require no history data, it is easier to implement

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
  • Image correcting method and device
  • Image correcting method and device
  • Image correcting method and device

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0053] Example 1: Human eye rotation correction

[0054] refer to Figure 4 , the specific process is as follows:

[0055] Step 1: Use the SUSAN algorithm to extract the detailed information SUSAN_F of the image F of the human eye area. The principle of the SUSAN algorithm is: use a circular area with a radius of r pixels as a mask, and examine the location of each point in the image in this area The degree of agreement between the values ​​of all pixels in the range and the current point, that is:

[0056] c ( r , r 0 ) = 1 , if | I ( r ) - I ( ...

example 2

[0066] Example 2: License plate rotation correction

[0067] see Figure 5 , the specific correction process is as follows:

[0068] Step 1: Use the Canny operator to obtain the edge map Canny_F of the license plate image;

[0069] Step 2: Obtain the horizontal projection curve of Canny_F;

[0070] Step 3: Calculate the information entropy of the curve;

[0071] Step 4: Rotate the image sequentially according to a certain angle, and obtain the rotation angle of the image when the minimum information entropy is obtained, as the angle of image rotation correction;

[0072] Step 5: Perform in-plane image rotation correction according to the angle in step 4 to obtain the corrected image (Rotated_F).

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 an image correcting method and device. The method comprises the following steps of: with a predetermined angle as a step length, rotating an original image in a horizontal plane; after rotating the image each time, projecting a target image in the currently rotated image in a predetermined direction to obtain a projection curve, and determining the correcting probability of the target image according to the projection curve under the condition that the image is rotated to the current angle; with the rotating angle of the image when the correcting probability of the target image is highest as a correcting angle, rotating the non-rotated original image according to the angle. According to the method, the image is rotated for multiple times and the correcting probability of the image after the image is rotated each time is estimated, so that a large amount of complicated calculations can be prevented and high correcting accuracy can be achieved; in addition, the technical scheme provided by the invention is easy and convenient to implement without need of historical data and can be flexibly applied to various scenes.

Description

technical field [0001] The present invention relates to the field of image processing, and in particular, to an image correction method and device. Background technique [0002] In the image processing system, the image obtained by the acquisition device will inevitably appear tilted, which makes it relatively difficult to carry out many processes. Therefore, image tilt detection and correction is a very important link in the image processing process. [0003] At present, common image rotation correction methods mainly include the following: (1) methods based on Hough transform, (2) methods based on cross-correlation, (3) methods based on projection, (4) methods based on Fourier transform and (5) KNN method. However, all of the above-mentioned methods have obvious disadvantages. For example, (1) methods based on Hough transform, (2) methods based on cross-correlation and (4) methods based on Fourier transform are very computationally intensive, resulting in low processing...

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): G06T5/00G06T3/60
Inventor 李习华刘玉宇
Owner 北京智诺英特科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap