Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fuzzy image integrated processing method and system

A blurred image, comprehensive processing technology, applied in the field of image processing, can solve the problems of image restoration providing perfect prior knowledge, difficult to restore clear images, unable to determine the direction and scale, etc., to reduce the ringing effect, blur kernel, etc. The effect of low accuracy requirements and fast recovery speed

Inactive Publication Date: 2018-07-20
SHANGHAI KANGFEI INFORMATION TECH CO LTD
View PDF11 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] This patent uses different methods to estimate the parameters necessary for restoration according to the blur type. However, when the defocus radius is estimated based on the disc model, the disc model has relatively large limitations. For the defocused blurred image actually taken, It is difficult to restore a clear image; in addition, in real life, many complex motions cannot determine the direction and scale, that is, they are not linear motions, so the motion blur parameter estimation algorithm based on cepstrum analysis is used to determine the blur direction and blur The scale cannot provide perfect and practical prior knowledge for image restoration; classic image restoration algorithms include Wiener filtering and LR filtering, Wiener filtering is not ideal when the peak signal-to-noise ratio of blurred images is small; It is more sensitive to noise, and the restored image has obvious ringing effect, that is, the scope of adaptation is not wide enough

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
  • Fuzzy image integrated processing method and system
  • Fuzzy image integrated processing method and system
  • Fuzzy image integrated processing method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] like figure 1 As shown, this embodiment provides a method for comprehensive processing of blurred images, including the following steps:

[0073] S10: Identify the blur type of the blurred image according to the elongation of the blurred image spectrogram, and the blur type includes defocus blur and motion blur;

[0074] Although the causes of defocus blur and motion blur are different, it is difficult to distinguish the two types of blurring from the naked eye. Therefore, it is necessary to find other breakthrough points to distinguish defocus blur and motion blur. After research, it is found that defocus blur and motion blur There is a big difference in the spectrograms of the fuzzy images of motion blur and motion blur. By extracting the relevant geometric features from the spectrogram and setting the threshold, the blur type can be distinguished. The method is simple and easy to implement; it should be noted that the distinction here is The fuzzy type is not simply...

Embodiment 2

[0086] like figure 2 As shown, the difference from Embodiment 1 is that this embodiment provides a method for comprehensive processing of blurred images, and the method further includes the following steps:

[0087] S40: Process the clear image using a super-resolution reconstruction technology to obtain a high-resolution image.

[0088] Specifically, if the blurred image is out-of-focus blur in the step S20, then using the edge method to estimate the blur kernel includes the following steps:

[0089] S201: Extracting an optimal edge image based on a gradient criterion;

[0090] S202: Estimate a point spread equation according to the optimal edge image, the point spread equation is the blur kernel, and the point spread equation is a point spread function, PSF for short, which is a spatial function representation of the blur kernel.

[0091] The step S201 includes the following steps:

[0092] Perform Canny edge detection on blurred images to obtain edge detection images. T...

Embodiment 3

[0142] like image 3 As shown, this embodiment provides a fuzzy image comprehensive processing system for providing the physical realization basis of the method described in Embodiment 2, including:

[0143] The blur type identification module 100 is used to identify the blur type of the blur image according to the elongation of the blur image spectrogram, and the blur type includes defocus blur and motion blur;

[0144] The estimation module 200 is used to estimate the blur kernel by using the edge method if the blurred image is defocus blur; if the blurred image is motion blur, then estimate the blur kernel by an adaptive preset algorithm, and the preset algorithm includes at least one kind of algorithm;

[0145] The image restoration module 300 is configured to obtain a clear image by using a super-Laplacian prior deconvolution algorithm based on the blur kernel.

[0146] Optionally, the system also includes:

[0147] A high-resolution processing module 400, using super-...

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 fuzzy image integrated processing method and system. The fuzzy image integrated processing method includes the steps: S10, according to the extension degree of a fuzzy imagespectrogram, identifying the fuzzy type of a fuzzy image, wherein the fuzzy type includes defocus fuzzy and motion fuzzy; S20, if the fuzzy image is defocus fuzzy, estimating the fuzzy kernel througha knife-edge method, and if the fuzzy image is motion fuzzy, adaptively presetting an algorithm to estimate the fuzzy kernel; and S30, based on the fuzzy kernel, by means of a hyper-Laplace prior deconvolution algorithm to obtain a clear image. The fuzzy image integrated processing method and system can distinguish according to difference of the fuzzy type of the fuzzy image, according to the degradation mechanism of different fuzzy type, can set a corresponding fuzzy kernel estimation algorithm so as to estimate a fuzzy kernel which is more realistic, and can perform accurate fuzzy kernel estimation based on a Gaussian model, specifically in allusion to the defocus fuzzy image. The fuzzy image integrated processing method and system have the advantages of being suitable for restoration ofmore real fuzzy images, being simple in the restoration method, being high in pertinency, being accurate and quick in restoration, and being high in quality of restoration.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for comprehensive processing of fuzzy images. Background technique [0002] When the image is acquired, due to inaccurate focus, or some uncertain factors such as the relative movement between the target and the camera, camera distortion, air diffraction, etc., the captured image is not satisfactory, and useful information in the image is lost, that is, image degradation phenomenon . It hinders subsequent processing and analysis, especially in the face of some unreproducible scenes, so for such cases, restoring the original appearance of the scene is an urgent problem to be solved. Although in actual design, hardware means such as adding optical devices and improving transmission equipment, such as electronic image motion compensation, optical image motion compensation, and mechanical image motion compensation can be used to improve the quality of ca...

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): G06T5/00G06T7/13G06T3/40
CPCG06T3/4053G06T7/13G06T2207/20201G06T2207/20061G06T5/73G06T2207/20192
Inventor 白海玲
Owner SHANGHAI KANGFEI INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com