Image local structure self-adaption recovery method based on non-continuity indicator

A local structure and indicator technology, applied in the field of image processing, can solve problems such as inability to distinguish edge points from noise points, and inability to remove noise

Active Publication Date: 2014-02-05
SOUTHEAST UNIV
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Through the research on the existing restoration technology, it is found that the existing methods are all controlled by the gradient, which cannot

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 local structure self-adaption recovery method based on non-continuity indicator
  • Image local structure self-adaption recovery method based on non-continuity indicator
  • Image local structure self-adaption recovery method based on non-continuity indicator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] In a specific implementation manner, the detailed process of the method for adaptive restoration of image local structure based on discontinuity indicators will be clearly and completely described with reference to the accompanying drawings.

[0070] A method for adaptive restoration of local structure of an image based on a discontinuity indicator, performed according to the following steps:

[0071] Step 1: Initialize, read in a frame size M 1 × M 2 ×3 degraded color image u 0 , where M 1 and M 2 are positive integers, representing the number of rows and columns of the image matrix respectively, and M is taken in the application test 1 =240 and M 2 =306, then convert the input color image from RGB color space to YCbCr color space, and the converted image is denoted as u 1 , size M 1 × M 2 ×3, take u 1 In the Y component image, denoted as f, the size is M 1 × M 2 , the specific process of converting from RGB color space to YCbCr color space is:

[0072] ...

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 an image local structure self-adaption recovery method based on a non-continuity indicator. The image local structure self-adaption recovery method based on the non-continuity indicator comprises the first step that a read image is initialized and an input RGB image is converted to a YCbCr color space; the second step that a trilateral scatter matrix is built and robustness to noise is improved; the third step that the non-continuity indicator is built to represent image local structure characteristics dynamically; the fourth step that an image degradation model is built; the fifth step that an image recovery optimization model is built according to the built non-continuity indicator, and the built model depends on the image local structure characteristics continuously; the sixth step that the recovery optimization model is resolved through a variational method, a gradient descent flow corresponding to the optimization model is obtained and is discretized through the half-point format, and an optimal recovery image is obtained. According to the image local structure self-adaption recovery method based on the non-continuity indicator, the recovery process can be controlled in a self-adaption mode according to the image local structure characteristics, more detailed structures of the image can be recovered, and the quality of the image is improved remarkably.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a self-adaptive restoration method of image local structure based on a discontinuity indicator. Background technique [0002] Image restoration technology is a key issue in image processing and low-level vision. It is the basis for subsequent pattern recognition and high-level understanding. It has a wide range of application requirements. This technology can be applied to many fields such as traffic monitoring, military, and medicine. In terms of monitoring, due to the low resolution of the camera and the poor shooting environment, the quality of the captured image is degraded, and it is difficult to obtain the required detailed features from the image, such as the license plate information of the vehicle, which is not conducive to machine recognition or human identification. Therefore, improving image quality through image restoration technology has important theoret...

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): G06T5/00G06T5/20
Inventor 曾维理路小波李聪费树岷陈林
Owner SOUTHEAST UNIV
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