Image co-saliency detection method based on energy optimization

A technology of energy optimization and detection method, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., and can solve problems such as missing targets, complex manual marking, and excessive background noise

Active Publication Date: 2021-03-26
HEBEI UNIV OF TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is: to provide an image collaborative saliency detection method based on energy optimization, which fuses three important saliency clues, optimizes the energy equation after fusion, and overcomes the complexity of manual marking in the prior art. Excessive background noise and lack of targets

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 co-saliency detection method based on energy optimization
  • Image co-saliency detection method based on energy optimization
  • Image co-saliency detection method based on energy optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0139] In this embodiment, the salient object is an airplane, and the input image group contains 22 images in total, and each image contains the salient object airplane. The image collaborative saliency detection method based on energy optimization described in this embodiment, specifically The steps are as follows: the first step, the input image group {I 1 , I 2 ,...,I n}, for preprocessing:

[0140] Input a set of image groups {I 1 , I 2 ,...,I n}, using the SLIC superpixel region segmentation algorithm to perform superpixel region segmentation on all the images in the image group, where image I i pre-divided into regions for image I i Extract the average CIE-Lab color space color feature from each superpixel region in and spatial location features Calculate image I with known method RBD algorithm i The sth superpixel region in and image I i The s′th superpixel region in The color distance and spatial position distance between, for all images in the above ...

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 is based on the energy optimized image collaborative saliency detection method, relates to the field of image data processing, fuses three important saliency clues, optimizes the energy equation after fusion, and the steps are: input image group {I 1 ,I 2 ,...,I n}, perform preprocessing; determine the initial candidate simple saliency map calculate the initial co-saliency map set simple image I sim ; Separately extract the color features of the foreground area and the background area of ​​a simple image; complete image co-saliency detection. The invention overcomes the defects of complex manual marking, excessive background noise and lack of targets in the prior art.

Description

technical field [0001] The invention relates to the field of image data processing, in particular to an image collaborative saliency detection method based on energy optimization. Background technique [0002] Image co-saliency detection is an emerging research field of computer vision, its purpose is to detect the same object or the same category of objects from two or more images, it has been widely used in image retrieval, image co-segmentation and weakly supervised localization, etc. [0003] Compared with the traditional single-image saliency detection, image co-saliency detection is an extension of visual saliency analysis on multiple images, aiming to detect the same object or the same category of objects in multiple images, therefore, the image co-saliency is significant Sex detection methods are not only affected by the contrast in a single image, but also by the correlation in multiple related images. [0004] In the prior art, image co-saliency detection methods ...

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): G06K9/32G06K9/34G06K9/46
CPCG06V10/25G06V10/267G06V10/462
Inventor 于明王红义刘依朱叶郝小可师硕于洋郭迎春阎刚
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