Fast Image Retrieval Method Based on Asymmetric Depth Discrete Hash, Retrieval Model and Model Construction Method

A technology for image retrieval and construction methods, which is applied in special data processing applications, instruments, and electrical digital data processing, etc., and can solve the problem of encouraging hash code class compactness, separation between classes, and unrobustness, etc. question

Active Publication Date: 2018-12-21
成都快眼科技有限公司
View PDF9 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Despite simplicity and very good performance, ADSH does not explicitly encourage compactness within classes of hash codes and separation between classes
In addition, the mean square loss adopted by ADSH is not robust to abnormal cases

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
  • Fast Image Retrieval Method Based on Asymmetric Depth Discrete Hash, Retrieval Model and Model Construction Method
  • Fast Image Retrieval Method Based on Asymmetric Depth Discrete Hash, Retrieval Model and Model Construction Method
  • Fast Image Retrieval Method Based on Asymmetric Depth Discrete Hash, Retrieval Model and Model Construction Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0054] Any feature disclosed in this specification (including the abstract and drawings), unless specifically stated, can be replaced by other equivalent or similar purpose alternative features. That is, unless expressly stated otherwise, each feature is one example only of a series of equivalent or similar features.

[0055] A fast image retrieval model construction method based on asymmetric deep discrete hashing, the specific method includes,

[0056] S1, collect a large number of training pictures, and mark the picture category; adjust the size of all pictures to a fixed size; randomly divide ...

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 provides a fast image retrieval method based on asymmetric depth discrete hash, a method for constructing a retrieval model and a retrieval model, wherein that scheme of the invention considers the compactness within a class and the separability between the hash codes of a query image and a database image, constructs a measure learning model, and simultaneously learn an approximate binary code of the query image and a discrete hash code of the database image through depth learning and discrete optimization; By constructing an asymmetric hash code learning framework, combining measure learning, depth learning and discrete optimization, a depth convolutional neural network is trained to learn discrete discriminant hash codes for database images and query images. So that the minimum Hamming distance between classes of hash codes is greater than the maximum Hamming distance within the class.

Description

technical field [0001] The invention relates to a fast image retrieval method based on asymmetric deep discrete hash, a retrieval model and a model construction method, and relates to the field of image retrieval. Background technique [0002] The proliferation of social networks and digital devices has led to an explosion of multimedia data. In order to achieve fast and accurate retrieval from large-scale multimedia data, it is very necessary to design effective indexing and retrieval methods. For large-scale image retrieval, Approximate Nearest Neighbor (ANN) search techniques have received increasing attention. Because of the efficiency of storage and computation, hashing has become a very popular and effective technique among existing ANN search techniques. The purpose of the hash method is to map the picture to a compact binary code so that the data structure or semantic similarity in the original space can be approximately preserved in the Hamming space. [0003] Ha...

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): G06F17/30
Inventor 李宏亮马雷
Owner 成都快眼科技有限公司
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