Depth image retrieval method fused with feature distribution entropy

A technology for fusing features and depth images, applied in still image data retrieval, still image data query, still image data clustering/classification, etc., can solve problems affecting retrieval performance, inconsistency, etc., to improve image retrieval performance and improve discrimination performance and improve retrieval performance

Active Publication Date: 2019-10-15
JILIN UNIV
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the pooling method ignores the difference in the distribution of eigenvalues ​​in different regions. The MAC eigenvalues ​​calculated in different regions may be the same, but the distribution of eigenvalues ​​​​in the region is generally inconsistent. Such differences cannot be reflected in the regional MAC characteristics. reflected, and these differences can affect the performance of retrieval

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
  • Depth image retrieval method fused with feature distribution entropy
  • Depth image retrieval method fused with feature distribution entropy
  • Depth image retrieval method fused with feature distribution entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The technical solution of the present invention will be further explained below in conjunction with the drawings, but it is not limited to this. Any modification or equivalent replacement of the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention shall be covered by the present invention. In the scope of protection.

[0029] The present invention provides a depth image retrieval method for fusing feature distribution entropy, the core of which includes calculating feature distribution entropy and fusing the feature distribution entropy and R-MAC feature through weighted summation. figure 1 The flow chart of the depth image retrieval method based on fusion feature distribution entropy is given, including convolutional neural network, multi-scale region extraction, calculation of R-MAC feature, calculation of feature distribution entropy, fusion of R-MAC feature and feature distribution entr...

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 depth image retrieval method fused with feature distribution entropy, and provides a depth image retrieval method fused with feature distribution entropy for solving the problem that in image retrieval, the rich degree of information carried by feature vectors extracted from an image can influence the retrieval effect of the image. According to the core idea of the algorithm, a feature distribution entropy is added into an R-MAC feature vector to serve as a supplement of the R-MAC feature, the feature distribution entropy and the R-MAC feature are fused together in aweighted summation mode, the obtained feature vector has regional distribution information and higher description capacity, and therefore the image retrieval performance is improved.

Description

Technical field [0001] The invention belongs to the technical field of image retrieval, and relates to a depth image retrieval method that integrates feature distribution entropy. Background technique [0002] In recent years, with the rapid development of Internet technology and multimedia technology, as well as the vigorous development of computer vision, the number of images on the Internet has exploded. For all kinds of rich image visual information, how to use this information to retrieve images accurately and efficiently has become a research hotspot at home and abroad. [0003] Early content-based image retrieval was mainly based on one or several visual features such as texture, color, and shape of the image; with the introduction of local invariant descriptors such as scale-invariant feature transformation, a large number of dependencies Method based on visual bag of words. In recent years, with the rapid development of neural networks, image retrieval algorithms based o...

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): G06F16/53G06F16/55G06N3/04
CPCG06F16/53G06F16/55G06N3/045
Inventor 刘萍萍郭慧俐勾贵霞苗壮石立达金百鑫王振王慧
Owner JILIN UNIV
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