An image super-resolution method based on mixed-resolution sparse dictionary learning

A low-resolution image and sparse dictionary technology, applied in the field of digital images, can solve problems such as consuming large computing resources, achieve the effect of enriching image texture information, sharpening image edges, and improving expression ability

CN108335264BActive Publication Date: 2021-08-03WUHAN UNIV
10 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-08-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an image super-resolution method based on mixed-resolution sparse dictionary learning, which includes a dictionary training process and an image super-resolution reconstruction process. In the dictionary learning process, the dictionary is generated by randomly sampling the training sample images, and dictionaries with different resolutions are obtained by repeating similar operations. In the process of image super-resolution reconstruction, based on the mixed resolution dictionary, the multi-resolution sparse expression of the image is carried out. Specifically, the strength of the texture information in the image is judged by the variance, and the image block with rich texture information uses a small resolution The high-resolution dictionary is used for super-resolution reconstruction, and the image blocks with relatively less texture information are reconstructed with a large-resolution dictionary. The invention can sharpen the edge of the object in the image and enhance the texture information of the image, and reduce the smoothing and blurring effect of the super-resolution enlarged image.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of digital images and relates to an image super-resolution method, in particular to an image super-resolution method based on mixed resolution sparse dictionary learning.

[0002] technical background

[0003] The spatial resolution of images is an important factor affecting the performance of image processing tasks. There are many technical means to improve the resolution of images, and image super-resolution reconstruction is one of them. Super-resolution image reconstruction can be seen as the process of reconstructing a high-resolution image from a single or multiple low-resolution images. Image super-resolution technology has been widely used in video surveillance, video format conversion, medical digital imaging, satellite images and other fields. In these fields, how to restore the detail information in the image with loss of detail information becomes the key to image super-resolution reconstruction...

Examples

Embodiment Construction

[0029] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the following in conjunction with the attached figure 1 The present invention will be further described in detail with reference to the implementation examples and implementation examples. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0030] please see figure 1 , a kind of image super-resolution method based on mixed resolution sparse dictionary learning provided by the present invention comprises the following steps:

[0031] Step 1: Take the images in the image library as training samples, train two types of low-resolution dictionaries with resolutions of 3×3 and 5×5, and obtain two pairs of high- and low-resolution dictionaries; among them, 3×3 and 5×5 The resolutions of the high-resolution dictionaries corresponding ...