A Deep 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: 2022-04-05
JILIN UNIV
View PDF8 Cites 0 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
  • A Deep Image Retrieval Method Fused with Feature Distribution Entropy
  • A Deep Image Retrieval Method Fused with Feature Distribution Entropy
  • A Deep 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 described below in conjunction with the accompanying drawings, but it is not limited thereto. 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 should be covered by the present invention. within the scope of protection.

[0029] The present invention provides a deep image retrieval method that integrates feature distribution entropy, the core of which includes calculating feature distribution entropy and merging feature distribution entropy and R-MAC features through weighted summation. figure 1 The step-by-step flow chart of the deep image retrieval method with fusion feature distribution entropy is given, including convolutional neural network, multi-scale region extraction, calculation of R-MAC features, calculation of feature distribution entropy, fusion of R-MAC feat...

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 deep image retrieval method that integrates feature distribution entropy. In the image retrieval method, the richness of information carried by the feature vector extracted from the image will affect the retrieval effect of the image. The invention proposes A deep image retrieval method that fuses feature distribution entropy is proposed. The core idea of ​​this algorithm is to add feature distribution entropy to the R-MAC feature vector as a supplement to the R-MAC feature, and to fuse the feature distribution entropy and R-MAC feature by weighted summation to obtain the feature vector It has regional distribution information and stronger description capabilities, thereby improving image retrieval performance.

Description

technical field [0001] The invention belongs to the technical field of image retrieval, and relates to a deep 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 the field 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 mainly retrieved one or several visual features such as texture, color, and shape of the image; with the proposal of local invariant descriptors such as scale-invariant feature transformation, a large number of dependent Based on the bag-of-visual-words approach. In recent years, with the rapid development of neural networks, image retrieval alg...

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): 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