Unlock instant, AI-driven research and patent intelligence for your innovation.

Image super-resolution method and system based on transfer learning

A technology of transfer learning and super-resolution, applied in graphics and image conversion, image data processing, instruments, etc., can solve the problems of affecting the reconstruction effect and small training database, and achieve the effect of enriching the training database

Inactive Publication Date: 2017-01-11
SHENZHEN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image super-resolution method and system based on transfer learning, which aims to solve the problem in the prior art that the reconstruction effect is affected due to the small training database

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 super-resolution method and system based on transfer learning
  • Image super-resolution method and system based on transfer learning
  • Image super-resolution method and system based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It shows the implementation flowchart of the image super-resolution method based on transfer learning provided by Embodiment 1 of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0026] In step S101, a low-resolution image is obtained by down-sampling the high-resolution image, and the high-resolution image includes: an original image and a transition image.

[0027] In the embodiment of the present invention, image super-resolution needs to establish a training database, which contains the original image T 0 On the basis of it, transfer images are also obtained from other fields. The method based on transfer learning is to use the knowledge learned from one environment to help the learning tasks in the new environment, which can transfer information from different fields to a specific field. Therefore, the present invention randomly selects...

Embodiment 2

[0075] Image 6 A structural diagram of the image super-resolution system based on transfer learning provided by Embodiment 2 of the present invention is shown. For convenience of description, only parts related to the embodiment of the present invention are shown. The image super-resolution system based on migration learning includes: a low-resolution image acquisition unit 61, a feature pair extraction unit 62, a projection matrix acquisition unit 63, and a high-resolution image reconstruction unit 64, wherein:

[0076] The low-resolution image acquisition unit 61 is configured to obtain a low-resolution image by down-sampling the high-resolution image, and the high-resolution image includes: an original image and a migrated image.

[0077] In the embodiment of the present invention, image super-resolution needs to establish a training database, which contains the original image T 0 On the basis of it, transfer images are also obtained from other fields. The method based on...

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 is applicable to the technical field of computers, and provides an image super-resolution method and system based on transfer learning. The method includes: obtaining a low-resolution image by down-sampling of a high-resolution image, wherein the high-resolution image comprises an original image and a transfer image; extracting a feature pair of the high-resolution image and the low-resolution image according to the high-resolution image and the low-resolution image; for the feature of each low-resolution image, obtaining a projection matrix through calculation of a low-resolution neighborhood and a corresponding high-resolution neighborhood; and during reconstruction, forming a reconstructed high-resolution image according to the feature of the low-resolution image and the projection matrix. According to the method and system, a training database is more abundant through increase of the transfer image, and a favorable condition is provided for subsequent reconstruction of the image.

Description

technical field [0001] The invention belongs to the field of computer technology, in particular to an image super-resolution method and system based on transfer learning. Background technique [0002] In the field of imaging applications, people often expect high-resolution (HR) images, which means that the pixel density in the image is high, which can provide more details, which are indispensable in many practical applications. Image super-resolution (SR) is the process of generating a high-resolution (HR) image from an input low-resolution (LR) image. Image super-resolution is widely used in many fields, including computer vision, video surveillance and In fields such as remote sensing images, image super-resolution technology can break through the limitations of image equipment and the environment, and produce a high-resolution image that cannot be obtained by traditional digital cameras. For these reasons, many image super-resolution methods have been developed and achi...

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 Applications(China)
IPC IPC(8): G06T3/40
CPCG06T3/4053
Inventor 苏美钟圣华江健民
Owner SHENZHEN UNIV