Image significance detection method based on fusion type geodesic curve and boundary comparison

A detection method, a geodesic technique, applied in the field of image analysis

Active Publication Date: 2017-02-01
HEBEI UNIV OF TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to provide an image saliency detection method based on fusion-type geodesic and boundary comparison, adopting the idea of ​​background priority, taking the prior knowledge that most of the image boundary areas are backgrounds, and combining each area with The boundary comparison map is obtained by comparing the background area, and then the boundary comparison map and the geodesic map with color contrast are linearly fused, and multiplied by the geodesic map without color contrast containing spatial features to obtain a saliency map, which overcomes the existing technology Bug that does not consistently highlight salient objects

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 significance detection method based on fusion type geodesic curve and boundary comparison
  • Image significance detection method based on fusion type geodesic curve and boundary comparison
  • Image significance detection method based on fusion type geodesic curve and boundary comparison

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] The specific steps of the image saliency detection method based on fusion-type geodesic and boundary comparison in this embodiment are as follows:

[0069] In the first step, input a color image:

[0070] Input RGB image to computer through USB interface I 0 , with a size of M×N pixels;

[0071] The second step, superpixel segmentation:

[0072] For the image I input in the first step above 0 Perform regular superpixel segmentation and irregular superpixel segmentation, the specific steps are as follows:

[0073] (2.1) Regular superpixel segmentation:

[0074] For the image I input in the first step above 0 , taking a square pixel block of s×s pixels as the segmentation unit to segment it. In this embodiment, s is set to 10 to obtain M′×N′ regular superpixels, where M’= ，N’＝ , is rounded, the segmented image is converted from RGB space to LAB space, and in LAB space, the average value of the gray features of each channel of the regular superpixe...

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 relates to an image significance detection method based on fusion type geodesic curve and boundary comparison and relates to common image analysis in an image data processing process. The method comprises steps that color images are inputted; superpixel segmentation including regular superpixel segmentation and irregular superpixel segmentation is carried out; a boundary comparison chart Sc is calculated; a geodesic curve chart Gc with color comparison and a geodesic curve chart Gn without color comparison are calculated, including pre-processing, calculating adjacent matrixes and calculating the geodesic curve chart Gc with color comparison and the geodesic curve chart Gn without color comparison; a significant chart is acquired through fusing three types of characteristic charts. The method is advantaged in that a problem that significant targets can not be consistently highlighted in the prior art is solved.

Description

technical field [0001] The technical solution of the invention relates to image analysis in general image data processing, specifically an image saliency detection method based on fused geodesics and boundary comparison. Background technique [0002] The saliency of an image reflects how much human eyes are interested in different regions in the image. Now image saliency detection has been widely used in image compression, image scaling, object recognition and image segmentation and other fields. However, with the intelligent development of computers and the continuous popularization of saliency detection applications, people's performance requirements for image saliency detection are also constantly improving. It is hoped that computers can imitate the human visual system more intelligently, and obtain saliency information in images. Higher quality saliency maps. How to accurately and quickly locate the salient areas in the image from a large number of images and extract ...

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): G06T7/11
CPCG06T2207/10004
Inventor 刘依郭迎春阎刚于洋师硕翟艳东马润欣
Owner HEBEI UNIV OF TECH
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap