Method and system for reconstruction of multiframe image super resolution

A super-resolution reconstruction and multi-frame image technology, which is applied in the field of image processing, can solve the problems of reconstruction effect and reconstruction speed reduction, and achieve the effect of improving reconstruction effect and reconstruction speed

Active Publication Date: 2016-04-20
JIMEI UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a multi-frame image super-resolution reconstruction method and its reconstruction system to solve the prob

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
  • Method and system for reconstruction of multiframe image super resolution
  • Method and system for reconstruction of multiframe image super resolution
  • Method and system for reconstruction of multiframe image super resolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as Figure 7 shown, where Figure 7 a, 7b, and 7c are the high-resolution source images of the lake, bridge, and Lena respectively. The above three high-resolution source images are degraded according to the image degradation model shown in formula (7):

[0058] g k = DHT k f+η k (7),

[0059] In formula (7), g k is the low-resolution image of frame k, D is the downsampling operator, H is the system transfer function of the image degradation model, T k is a geometric transformation, f is such as Figure 7 The high-resolution image shown, η k is the noise added to the low-resolution image of the kth frame.

[0060] The width and height of the degraded low-resolution image are 1 / 4 of the source image, and 32 geometric transformations T are randomly generated k , so as to randomly generate 32 frames of low-resolution images, and add Gaussian white noise with a standard deviation of 0.001 when the gray value is normalized to 0-1. During the degradation proces...

Embodiment 2

[0064] The selected high-resolution source image, the degradation process and the reconstruction process are the same as those in the first embodiment. In order to examine the robustness of the blur kernel misestimation, the standard deviation of the Gaussian blur kernel is set to 0.05, 0.1, ..., 0.95, 1 during reconstruction.

[0065] The SSIM evaluation index of the reconstruction result is as follows: Figure 9 shown. From the results, for these three images, they all reach the maximum when the standard deviation is 0.4, that is to say, when the Gaussian blur kernel in the reconstruction process is exactly the same as the blur kernel in degradation, the reconstruction effect is the best , which reflects the reliability of this reconstruction method. Additionally, from Figure 9 It can be seen that the technique is robust to the error estimation of the standard deviation of the Gaussian blur kernel.

Embodiment 3

[0067] Such as Figure 10 101a, 101b, 101c, and 101d are the high-resolution source image of the digital image, the multi-frame low-resolution image, the reference frame interpolation image and the reconstructed high-resolution image, respectively. Figures 102a, 102b, 102c, and 102d are the high-resolution source image, multi-frame low-resolution image, reference frame interpolation image, and reconstructed high-resolution image of the ship image, respectively. Figures 103a, 103b, 103c, and 103d are the high-resolution source image of the aircraft image, the multi-frame low-resolution image, the reference frame interpolation image and the reconstructed high-resolution image, respectively.

[0068] The high-resolution source images shown in Figs. 101a, 102a and 103a are respectively degenerated according to the method of Embodiment 1 to obtain three sets of low-resolution images. Each group contains 32 frames of low-resolution images, some of which are shown in Figures 101b, 1...

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 method and system for reconstruction of multiframe image super resolution and relates to the technical field of image processing. The method comprises the steps of using temporary results obtained according to geometric transformation and a filter transfer function obtained according to a fuzzy kernel to construct a transfer function for super resolution reconstruction, adopting a graph cut algorithm to perform minimization solving, and obtaining a final high-definition image, so that the reconstruction effect and reconstruction speed are improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a multi-frame image super-resolution reconstruction method and a reconstruction system thereof. Background technique [0002] Image resolution refers to the ability of the imaging system to distinguish image details, and it is one of the important indicators to measure image quality. High-resolution images can provide rich detailed information. With the continuous progress of economy, technology, and civilization, the demand for high-resolution images is increasing in various fields such as medicine, security, and entertainment. For example, doctors hope to identify lesions through high-resolution CT or B-ultrasound images; public security departments hope to identify suspects’ identities or vehicle information through high-resolution surveillance images; Visual effects. [0003] The most direct way to improve the resolution is to increase the hardware resolution of th...

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): G06T3/40
CPCG06T3/4053
Inventor 张东晓梁宗旗蔡国榕吴云东陈水利
Owner JIMEI 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