Complex-background image saliency detection method based on low-rank representation

A complex background, low-rank representation technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as chaotic colors, complex surface textures, and the influence of changing backgrounds, so as to improve resolution and enlarge The effect of the gap

Inactive Publication Date: 2018-11-02
DALIAN MARITIME UNIVERSITY
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Saliency detection methods based on low-rank representations can be successful in application, but there are still shortcomings, especially when the salient objects in the image are inconsistent in size and affected by complex backgrounds, existing detection methods are vulnerable to chaotic colors. , complex surface texture and the influence of changing background

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
  • Complex-background image saliency detection method based on low-rank representation
  • Complex-background image saliency detection method based on low-rank representation
  • Complex-background image saliency detection method based on low-rank representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific embodiment of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0048]It should be noted that, in the following specific embodiments, when describing the embodiments of the present invention in detail, in order to clearly show the structure of the present invention for the convenience of description, the structures in the drawings are not drawn according to the general scale, and are drawn Partial magnification, deformation and simplification are included, therefore, it should be avoided to be interpreted as a limitation of the present invention.

[0049] In the following specific embodiments of the present invention, please refer to figure 1 . as the picture shows,

[0050] A complex background image saliency detection method based on low-rank representation, characterized in that it comprises the following steps:

[0051] Step S1: Use the superpixel segmentation method to segment the input ...

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 complex-background image saliency detection method based on low-rank representation. A distance constraint among sparse subgraphs is added in a low-rank saliency model, gapsbetween a saliency target and background targets are increased, prior knowledge weights are fused in the sparse subgraphs, and thus saliency target information is enhanced in matrix decomposition. Themethod can improve discerning capability of the saliency target and the background targets, and can be used for image detection of large-area saliency targets and complex backgrounds.

Description

technical field [0001] The invention relates to the field of image saliency detection, in particular to a low-rank representation-based saliency detection method for complex background images. Background technique [0002] The standard of image saliency detection is to be able to highlight the most salient object, to highlight the entire salient object consistently, to accurately conform to the boundary of the object, and to have high noise immunity. [0003] Low-rank representation is a method that can capture the low-dimensional structure of image data. It is assumed that the background features of the image belong to the same low-dimensional subspace, and the salient objects of smaller size are regarded as sparse noise, so the low-rank matrix recovery algorithm is used The feature matrix of an image can be decomposed into a low-rank matrix and a sparse matrix. [0004] Recently, some saliency detection algorithms based on low-rank matrix recovery have emerged. Saliency ...

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): G06K9/46
CPCG06V10/56G06V10/462
Inventor 于纯妍宋梅萍岑鹍王春阳张建祎
Owner DALIAN MARITIME UNIVERSITY
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