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

A Multi-table Hash Image Retrieval Method with Double Compensation

A multi-table hashing and image retrieval technology, which is applied to still image data retrieval, still image data indexing, digital data information retrieval, etc., can solve the problem that multi-table hashing requires more overhead, and achieve fast query speed and auxiliary The effect of small memory and speed-up

Active Publication Date: 2020-11-24
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the existing hash image retrieval method in multi-table retrieval, and propose a multi-table hash image retrieval method with double compensation. This method mainly reflects relatively good performance and can solve the problem of Disadvantages of multi-table hashing requiring more overhead under the same performance

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 Multi-table Hash Image Retrieval Method with Double Compensation
  • A Multi-table Hash Image Retrieval Method with Double Compensation
  • A Multi-table Hash Image Retrieval Method with Double Compensation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be further described below in conjunction with specific examples.

[0063] Such as figure 1 As shown, it is the operation flowchart of the double-compensated multi-table hash image retrieval method of the present invention, which is divided into two parts: offline training and online query, wherein feature extraction in offline training and hash table training all need to spend It takes a lot of time, but it is within an acceptable range because it is offline and does not affect query performance. exist Figure 2 to Figure 4 It is an evaluation of query performance, which is described below.

[0064] In this example, this method is implemented on the CIFAR10 dataset to establish retrieval and evaluate performance. Hardware includes, 128G memory server. Software includes MATLAB. The CIFAR10 dataset is a dataset with 60,000 images grouped into 10 categories. Among them, 1,000 images are randomly selected as queries, and the remaining 59,00...

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 double compensation based multi-table Hash image retrieval method. The method comprises the steps of image characteristics extraction and category information processing, Hash table training, mapping of image characteristics to hamming space according to Hash tables and category weight calculation, hamming distance calculation based on query and query result returning and re-sorting operation. The method has the advantages of being quick in query response, small in internal storage expenditure and high query performance on the aspect of image retrieval, is greatly improved on the aspect of multi-table Hash image retrieval and overcomes the shortcoming of additional expenditure of multi-table Hash.

Description

technical field [0001] The invention relates to the technical field of image retrieval, in particular to a double-compensation multi-table hash image retrieval method. Background technique [0002] With the development of the Internet, the number of multimedia files has grown rapidly, and the images uploaded by people have also become a very large scale. This poses a very big challenge to the image retrieval problem. Traditional retrieval methods based on tree structure generally require a lot of additional auxiliary space, which even exceeds the size of the original image data; and once the feature dimension of the image is large, the performance of the method based on tree structure will decrease. Degenerated, even to the complexity of linear retrieval. In contrast, hash-based image retrieval methods consistently have superlinear time complexity and require a satisfactory auxiliary space. [0003] For a hash-based image retrieval method with F hash bits, the image is fi...

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): G06F16/51G06F16/583G06F16/532
CPCG06F16/50
Inventor 吴永贤周先成田星
Owner SOUTH CHINA UNIV OF TECH
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