Single-image super-resolution reconstruction method based on edge difference constraint

A technology for super-resolution reconstruction and single image, which is applied in graphics and image conversion, image data processing, instruments, etc., and can solve problems such as blurred details

Active Publication Date: 2017-04-05
上海厉鲨科技有限公司
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Adding image edge difference constraints in the image super-resolution reconstruction process can effectively solve the blurring and smoothing of details caused by the single image super-resolution recon

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
  • Single-image super-resolution reconstruction method based on edge difference constraint
  • Single-image super-resolution reconstruction method based on edge difference constraint
  • Single-image super-resolution reconstruction method based on edge difference constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Below in conjunction with accompanying drawing and embodiment the present invention is described in further detail:

[0054] figure 1 It is the realization block diagram of the method of the present invention, and this method mainly is made of following steps:

[0055] Step 1: Extract the main texture direction features of the training image through the Gabor filter, and divide the feature image into blocks and K-means clustering, and conduct Principal Component Analysis (PCA) dictionary training for each type of image block to obtain Can reflect the texture feature training dictionary of the image.

[0056] This step consists of the following four parts:

[0057] ① Randomly select 70 high-resolution images from the general BSDS300 (The Berkeley Segmentation Data Set 300) image library as training images, such as figure 2 shown.

[0058] ② Use the image edge information to perform image texture main direction θ on the training image m The judgment, and through the...

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

Provided is a single-image super-resolution reconstruction method based on edge difference constraint. The method includes following three steps: step 1, extracting a texture principal direction characteristic of a training image through a Gabor filter, and performing a principal component analysis dictionary training to obtain a training dictionary; step 2, constructing a reconstruction model by employing the dictionary, and obtaining an initial reconstruction high-resolution image with a good edge structure through iterative threshold shrinkage; and step 3, describing an operator, a spatial distance, a pixel intensity, and edge orientation information by employing a histogram of oriented gradients between image blocks, establishing a non-local structure tensor optimization model, further optimizing and processing the initial reconstruction high-resolution image, and obtaining a final reconstruction high-resolution image with a substantial edge structure and abundant detail information. According to the method, by considering the difference between the initial reconstruction high-resolution image and an original clear image, the post-processing optimization method is further proposed, and the detail information of image edges and textures is abundant.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and relates to a method for super-resolution reconstruction of a single image. Background technique [0002] With the rapid development of intelligent video image processing technology and network technology, high-resolution images are required in application fields such as video surveillance, satellite remote sensing imaging, military reconnaissance, medical imaging, and multimedia entertainment. In the process of acquiring visual images, due to the existence of system aberration, defocus, air disturbance and noise, the obtained images or sequences often have certain degradation or degradation, such as deformation, blurring, downsampling or noise. In order to obtain high-resolution images, the most direct and effective method is to increase the resolution level of hardware imaging equipment, that is, to increase the sensor element density per unit area. On the one hand, the un...

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): G06T3/40G06K9/62
CPCG06T3/4053G06F18/23213
Inventor 龚卫国唐永亮陈雪梅李伟红易前娥
Owner 上海厉鲨科技有限公司
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