Attention mechanism and hash-based image retrieval method and device and storage medium

An image retrieval and attention technology, applied in still image data retrieval, metadata still image retrieval, still image data indexing, etc., can solve problems such as limiting accuracy, interfering with image embedding learning, etc., to achieve rapid retrieval and improve learning ability , improve the effect of expression

Active Publication Date: 2020-09-29
CENT SOUTH UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides an image retrieval method, device and storage medium based on attention mechanism and hash, in order to solve the problem in the prior art that images may contain some Visual information that has nothing to do with semantic expression interferes with image embedding learning to a certain extent, and for hash codes with limited expressive capabilities, it limits the accuracy 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
  • Attention mechanism and hash-based image retrieval method and device and storage medium
  • Attention mechanism and hash-based image retrieval method and device and storage medium
  • Attention mechanism and hash-based image retrieval method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] like figure 1 As shown, the present embodiment provides an image retrieval method based on attention mechanism and hash, including:

[0058] S01: For each image in the original data set, the discrete hash code of each image is obtained based on the pre-trained hash feature extraction model based on the attention mechanism, and then the image feature library corresponding to the original data set is established;

[0059] S02: Obtain the discrete hash code of the image to be detected based on the pre-trained hash feature extraction model based on the attention mechanism;

[0060] S03: Query the data in the image feature library that has the closest discrete hash coding Hamming distance to the image to be detected, and the image corresponding to the data in the original data set is the retrieval result;

[0061] Wherein, the hash feature extraction model based on the attention mechanism is obtained by training the attention hash network model based on a labeled data set, ...

Embodiment 2

[0101] like figure 2 As shown, the present embodiment provides an image retrieval device based on attention mechanism, including:

[0102] The image feature library building module 1 is used to obtain the discrete hash code of each image based on the pre-trained hash feature extraction model based on the attention mechanism for each image in the original data set, and then establish a The image feature library corresponding to the set;

[0103] The discrete hash code generation module 2 of the image to be detected is used to obtain the discrete hash code of the image to be detected based on the pre-trained hash feature extraction model based on the attention mechanism;

[0104] Retrieval module 3, querying the data with the nearest discrete hash coding Hamming distance of the image to be detected in the image feature database, and the image corresponding to the data in the original data set is the retrieval result;

[0105] Wherein, the hash feature extraction model based o...

Embodiment 3

[0108]This embodiment provides a computer-readable storage medium, which stores a computer program, and when the computer program is loaded by a processor, it executes an image retrieval method based on attention mechanism and hash provided in Embodiment 1.

[0109] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

[0110] The present application is described with reference to flowcharts and / or block diagrams of methods, apparat...

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 an attention mechanism and hash-based image retrieval method and device and a storage medium, and the method comprises the steps: obtaining the discrete hash code of each imagebased on a pre-trained attention mechanism-based hash feature extraction model for each image in an original data set, and building an image feature library; obtaining a discrete hash code of a to-be-detected image based on a pre-trained hash feature extraction model based on the attention mechanism; and querying data closest to the discrete hash code Hamming distance of the to-be-detected imagein an image feature library, wherein the image corresponding to the data is a retrieval result. The Hash feature extraction model based on the attention mechanism gives full play to the ability of thedeep convolutional neural network to extract the abstract semantic features of the image; and by embedding the attention module, the network can focus on the visual content capable of expressing semantic information of the whole image as much as possible in the image, the expression effect of hash coding is improved, and image retrieval is more accurate and faster.

Description

technical field [0001] The invention relates to the technical field of image retrieval, in particular to an image retrieval method, device and storage medium based on attention mechanism and hash. Background technique [0002] With the development of the Internet, cloud computing, Internet of Things, social media and digital devices, multimedia data such as images, audio and video are growing at an unprecedented rate. As the visual basis of human perception of the world, image data can help people understand information, express information and transmit information. How to accurately and quickly retrieve images related to user queries from massive image data is a problem that researchers in the field of multimedia retrieval are extremely concerned about. . Due to its advantages in solving the curse of dimensionality, search efficiency, and storage overhead, hashing methods are widely used in approximate nearest neighbor queries for large-scale multimedia data. [0003] In ...

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): G06F16/51G06F16/53G06F16/58G06N3/04G06N3/08
CPCG06F16/51G06F16/58G06F16/53G06N3/084G06N3/045Y02D10/00
Inventor 龙军魏翔翔朱磊
Owner CENT SOUTH 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