Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Quick super-resolution processing method for mobile phone photographing

A processing method and super-resolution technology, applied in the field of image processing, can solve the problems of difficult mobile terminal use, poor portability, etc., and achieve the effect of reducing parameters and operands, improving practicability, and improving practical significance.

Active Publication Date: 2020-07-17
ANHUI UNIVERSITY OF TECHNOLOGY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009]The purpose of the present invention is to overcome the shortcomings of traditional deep learning models, which are relatively poor in portability and difficult to use on mobile terminals, and provide a fast super-resolution processing for mobile phone photography method

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
  • Quick super-resolution processing method for mobile phone photographing
  • Quick super-resolution processing method for mobile phone photographing
  • Quick super-resolution processing method for mobile phone photographing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] combine figure 1 , a kind of fast super-resolution processing method of mobile phone photographing of the present embodiment, its steps are:

[0063] Step 1. Using commonly used image processing data sets, make high-resolution image blocks and low-resolution image block training sets; the specific process is:

[0064] First, using the conventional existing DIV2K data set, each original color image in the commonly used image processing data set is first cropped with a step size of 27, and finally a high-resolution image block with a size of 100*100 is obtained, and then the high-resolution The image is down-sampled by 4 times to obtain a low-resolution image of 25*25 size corresponding to the high-resolution image; thus a collection of high-resolution image blocks and low-resolution image blocks for deep network training is obtained.

[0065] Step 2. Construct a fast and lightweight image super-resolution model;

[0066] 2-1. The fast and lightweight super-resolution n...

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 quick super-resolution processing method for mobile phone photographing, and belongs to the technical field of image processing. The invention provides a novel quick light-weight image super-resolution model. A Tensorflow lite general technology is adopted to apply the model to a mobile phone terminal; according to the method, the unclear part of the shot picture is cut,the required part is selected and subjected to image super-resolution processing, so that the effect of local magnification and sharpness is achieved, the running speed of the model is about 3-5 s, and therefore wide application prospects are provided for application of the deep learning model to Android and other mobile terminals.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically relates to a fast super-resolution processing method for taking pictures with a mobile phone. Background technique [0002] There are relatively common methods for clearing pictures after taking pictures, such as using ps to sharpen the pictures, etc., the real processing effect is average. With the deepening of the application of deep learning in image processing, the continuous improvement of image super-resolution algorithms The development has made a qualitative leap in image clarity processing. As a classic problem in the field of computer vision, image super-resolution (SR) technology refers to the process of restoring a higher-resolution image from one or more low-resolution images or image sequences. This technology is mainly used to enhance the spatial resolution of the image, which can break through the limitations of the original system imaging hardware ...

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): G06T3/40G06N3/04G06N3/08
CPCG06T3/4053G06T3/4046G06N3/084G06N3/045
Inventor 刘恒吴文雪
Owner ANHUI UNIVERSITY OF TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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