Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Large-scale image high-speed retrieval method based on multi-view enhanced depth hash

A multi-view, large-scale technique for new theoretical domains

Active Publication Date: 2020-01-10
HANGZHOU DIANZI UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method utilizes an effective view stability evaluation method to actively explore the relationship between views, which will affect the optimization direction of the entire network.

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
  • Large-scale image high-speed retrieval method based on multi-view enhanced depth hash
  • Large-scale image high-speed retrieval method based on multi-view enhanced depth hash
  • Large-scale image high-speed retrieval method based on multi-view enhanced depth hash

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with drawings and embodiments.

[0062] The present invention combines deep hash learning with multi-view methods for the first time through deep multi-view enhanced hashing. The submodule multi-view hashing finds view relations and quantifies them under non-deep learning conditions. Deep multi-view enhanced hashing preserves the inherent advantages of multi-view methods and can be applied to any single-view hashing retrieval model.

[0063] The present invention comprises the steps:

[0064] Step 1, problem definition and multi-view hash (MV-Hash) detailed explanation

[0065] suppose is a set of objects, and the corresponding features:

[0066]

[0067] Among them, d m is the dimension of the mth view, where M is the number of views and N is the number of objects. We also denote an integrated binary code matrix where b i yes with o i associated binary code, and q is the code length. ...

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 large-scale image high-speed retrieval method based on multi-view enhanced deep hash. The method comprises the following steps: step 1, acquiring image multi-view feature representation; step 2, calculating a view relation matrix; step 3, designing a loss function of the model; step 4, performing fusion and enhancement; step 5, training the built model on a large-scale image training data set; step 6, testing the trained model to generate a hash code, and then performing hash retrieval; step 7, carrying out an experiment to evaluate the index. According to the method,the influence of Hamming radius extension on the result is small; and along with the increase of the code length, the precision is kept stable.

Description

technical field [0001] The invention belongs to the technical field of computer images and artificial intelligence, and specifically solves the problem of high-speed retrieval of large-scale image data sets. The method involves new theories such as multi-view, deep learning and hash learning. Background technique [0002] With the explosive growth of image data, efficient large-scale image retrieval algorithms are urgently needed for many tasks. Approximate nearest neighbor search, which balances time-consuming and efficient retrieval on large-scale datasets, has attracted increasing attention. Hashing is an efficient method for nearest neighbor search in large-scale data spaces by embedding high-dimensional feature descriptors in similarity-preserving Hamming spaces with low dimensions. However, compared with traditional retrieval methods, large-scale high-speed retrieval through binary codes has a certain degree of reduction in retrieval accuracy. [0003] Hashing learni...

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
IPC IPC(8): G06F16/583G06N3/04G06N3/08
CPCG06F16/532G06F16/583G06N3/084G06N3/045
Inventor 颜成钢龚镖白俊杰孙垚棋张继勇张勇东沈韬
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com