Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Dictionary database-based adaptive image super-resolution reconstruction method

A super-resolution reconstruction and database technology, applied in the field of image processing, can solve the problems of high-resolution image quality degradation

Inactive Publication Date: 2015-04-08
SHANGHAI JIAO TONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both of these factors lead to a loss of quality in the resulting high-resolution image

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
  • Dictionary database-based adaptive image super-resolution reconstruction method
  • Dictionary database-based adaptive image super-resolution reconstruction method
  • Dictionary database-based adaptive image super-resolution reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0150] A specific embodiment of the present invention applied to super-resolution reconstruction of a face image will be described in detail below in conjunction with the accompanying drawings.

[0151] In this embodiment, a face image is selected from the "Georgia Tech" face database. The "Georgia Tech" face database contains face images of 40 people, and each person contains face images from different angles. In this embodiment, 40 frontal images of these 40 people are selected. Since the images in the "Georgia Tech" face database have a large non-face area, it is necessary to cut these 40 images in advance, select the face part, and the cut images are all 300×300 in size. From these 40 images, 30 are randomly selected as training images; the test images are randomly selected from the remaining 10 images, and this embodiment selects figure 2 (b) as a test image. The desired magnification in this embodiment is set to 3, and the specific process is as follows:

[0152] 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 dictionary database-based adaptive image super-resolution reconstruction method in the field of image processing. The dictionary database-based adaptive image super-resolution reconstruction method comprises the steps of: adaptively selecting a matched dictionary from a dictionary database according to a characteristic vector of each low-resolution image block, if the matching fails, re-training to obtain a proper dictionary, updating the dictionary into the dictionary database, then carrying out super-resolution reconstruction on the blocks by using the dictionary to obtain image blocks with high resolution, and finally, recombining all blocks to obtain a high-resolution image. The dictionary database-based adaptive image super-resolution reconstruction method is test in a face image, results prove that the method is superior to a method using a single dictionary in term of the image reconstructing effect, training image blocks with higher matching degree can be screened out in a process of training a local adaptive dictionary; and since many matched image blocks exist, prior information of a training set is sufficient amd a reconstructing effect is greatly improved compared with that of the method using the single dictionary.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an adaptive image super-resolution reconstruction method based on a dictionary database. Background technique [0002] With the progress of society, people have higher and higher requirements for image quality. Image resolution is an important indicator to measure the quality of an image, and it indicates the level of detail of the information that the image can provide. The higher the image resolution, the richer the detailed information can be provided, and the more accurate and detailed description of the objective scene. Due to the bottleneck of sensor manufacturing technology, the traditional method of improving image resolution by improving hardware structure is no longer applicable. In this context, image super-resolution reconstruction using software technology, as an important research direction in the field of image processing, has received extensive attentio...

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 Patents(China)
IPC IPC(8): G06T5/00
Inventor 张爱新徐光耀李建华金波李生红
Owner SHANGHAI JIAO TONG 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
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