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

Image processing method for seamless mosaic based on accumulated energy

A technology of seamless splicing and image processing, which is applied in the field of image processing and can solve the problems that the naturalness of image content cannot be well protected and the robustness is weak.

Inactive Publication Date: 2011-12-07
FUDAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the robustness of the existing seamless stitching seam carving technology is relatively weak. Specifically, when the information of the image is very dense, the processed image often cannot protect the naturalness of the image content well.

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 processing method for seamless mosaic based on accumulated energy
  • Image processing method for seamless mosaic based on accumulated energy
  • Image processing method for seamless mosaic based on accumulated energy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Please refer to the accompanying drawings for a further description of the present invention.

[0046] The present invention provides a seamless stitching image processing method based on cumulative energy. For an input image P, the width reduction is realized according to the following steps:

[0047] ① Calculate the intensity table I of the image, and divide all the elements in I by the maximum value of the elements in I (that is, let the largest element return to 1);

[0048] ② Pass I through a Gaussian low-pass filter with a size of 20×20 and a variance of 9 to obtain the blurred image intensity I b ;

[0049] ③; Find the visual saliency table Smap (saliency map) of the input image, and divide all the elements in the Smap by the maximum value of the elements in the Smap (that is, let the largest element return to 1);

[0050] ④ Construct and initialize the minimum energy table A and the maximum energy table B according to the following formula:

[0051] ...

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 present invention provides a seamless stitching image processing method based on cumulative energy, which considers the adverse effect brought by the greedy effect in the traditional seamless stitching seam carving process, and records more energy information in the seamless stitching seam carving process And introduce the energy update step, and integrate the visual saliency information of the image to achieve the purpose of weakening the greedy effect. The advantage of the present invention is that the method of the present invention has better content perception ability than the original seamless splicing technology, and the robustness is improved.

Description

technical field [0001] The present invention relates to an image processing method, in particular to a seamless splicing image processing method based on accumulated energy. Background technique [0002] The purpose of content-aware image scaling is to change the size and aspect ratio of the image arbitrarily, and still maintain a good visual experience of the important content in the original image in the new image. Image scaling is generally divided into two types, one is scaling in which the aspect ratio remains unchanged but the width and height dimensions change; the other is scaling in which the aspect ratio changes. Many display devices today, such as computer monitors, TVs, mp4, etc., have different screen aspect ratios, and often people need to display the same pictures and videos on these different display screens. At this time, it is necessary to use image scaling techniques, especially scaling where the aspect ratio of the image changes. [0003] Seamless stitc...

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): G06T3/40
Inventor 骆思强张军平白云峰
Owner FUDAN UNIV
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