Image retrieval method based on deep learning and hash coding

A hash coding and deep learning technology, applied in the field of computer vision, can solve the problems of binary hash coding single retrieval task, limited application range, slow model convergence, etc., achieve good retrieval effect, reduce calculation amount, and fast model training Effect

Active Publication Date: 2017-11-07
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that, on the one hand, only one similarity measure can be used during training, so the final binary hash code can only be used for a single retrieval task, which limits the scope of application of this method; on the other hand, , this method uses image triplets during training, which leads to slow model convergence during training and takes a long time to train

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
  • Image retrieval method based on deep learning and hash coding
  • Image retrieval method based on deep learning and hash coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following describes the image retrieval method based on deep learning and hash coding provided in the embodiments of the present invention with reference to the accompanying drawings.

[0029] Deep learning is derived from artificial neural networks. In the field of image retrieval, deep learning can combine the underlying features of the image to form higher-level representations, such as attribute categories, to discover the distributed feature representation of image data; hash coding is a fast Algorithms with query capability and low memory overhead. In the field of image retrieval, the image content can be expressed as a binary hash sequence using hash coding, and the sequence is used to represent the characteristics of the image.

[0030] After careful study, the inventor proposed an image retrieval method using a deep neural network, which can learn binary hash co...

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 relates to a model training method based on deep learning and hash coding. The method comprises the steps of regarding partially labeled image data as training data of a network model, and representing the training data as an analog-two-value hash code through a deep network, wherein the analogy-two-value hash code refers to a simulation two-value hash code of which the value is a continuous value; regarding the obtained analog-two-value hash code as input, connecting the analog-two-value hash code to one or more task layers, and using one or more tasks to conduct training at the same time; obtaining a two-value hash code which is used for representing the training data and carries feature information capable of being retrieved based on the analog-two-value hash code.

Description

Technical field [0001] The present invention relates to the technical field of computer vision, in particular to an image retrieval method based on deep learning and hash coding. Background technique [0002] With the development of science and technology, today's world has entered the era of big data, especially the rapid growth of image data resources. Therefore, the retrieval of large-scale image data to meet user needs has brought new challenges to the field of image retrieval technology. Compared with the traditional text-based image retrieval technology (Text-Based Image Retrieval, TBIR), content-based image retrieval (Content-Based Image Retrieval, CBIR) has attracted more and more attention. [0003] In the CBIR technology, how to effectively describe the characteristics of the image and what method to use for rapid similarity retrieval is a research hotspot in recent years. Due to the superiority of deep neural networks in feature learning and the computing speed and stor...

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): G06F17/30G06K9/62
CPCG06F16/583G06F16/5866G06F18/24
Inventor 陈熙霖刘昊淼王瑞平
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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