An image retrieval method based on deep semantic sorting hash encoding

A technology of hash coding and image retrieval, used in still image data retrieval, special data processing applications, instruments, etc.

Active Publication Date: 2018-08-03
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Meanwhile, an algorithm based on a surrogate ranking loss function is used to solve the multivariate non-smooth ranking metric optimization problem during learning

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
  • An image retrieval method based on deep semantic sorting hash encoding
  • An image retrieval method based on deep semantic sorting hash encoding
  • An image retrieval method based on deep semantic sorting hash encoding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0019] The invention proposes a hash coding based on deep semantic sorting and applies it to image retrieval. This method uses a deep convolutional neural network to construct a multi-layer deep hash function, and derives the semantic similarity ranking between images according to the multi-label information of the image, which is used for the supervised learning of the deep hash function. Based on this, a strategy based on a proxy ranking loss function is used to solve the non-smooth multivariate ranking metric optimization problem during model learning. The key steps involved in the method of the present invention are described in detail below.

[0020] see figure 1 The illustrated invention utilizes a method of image...

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 image retrieval method based on deep semantic sorting hash coding. The method comprises the following steps: using part of the images in a multi-label image data set as a training set, and the remaining images as an image test set; using depth volume Construct a deep hash function using a product neural network; construct a semantic similarity ranking between images according to the multi-label information of the image; use the triplet-based proxy ranking loss function as the actual model objective function, and use stochastic gradient descent The method is used to optimize the deep hash function; use the learned deep hash function to calculate the hash code of the image, and retrieve the image by calculating the Hamming distance between the hash code of the test image and the hash code of each image in the training set . The method of the invention can preserve the multi-level similarity of the multi-label image in the semantic space, and jointly learn the deep feature expression and hash coding of the image, thereby avoiding the loss of semantic information.

Description

technical field [0001] The invention relates to the field of pattern recognition and machine learning, in particular to image hash coding and retrieval. Background technique [0002] The explosive growth of network images makes content-based image retrieval more and more important. Hash coding has been widely used in large-scale image retrieval due to its high efficiency and easy storage. Nevertheless, most of the hash coding methods based on semantic tags only solve the problem of binary similarity measure (i.e. similar or dissimilar), but they cannot handle the multi-level semantic similarity measure in multi-label images well. . In addition, the process of most hash coding methods is generally to first extract the hand-designed feature expression, and then learn a deep hash function on this basis. These hand-designed features tend to describe appearance rather than semantic information, and are not suitable for tasks involving complex semantic structures. Contents of...

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): G06F17/30G06K9/62
CPCG06F16/50G06F18/2111
Inventor 王亮谭铁牛黄永祯赵放
Owner INST OF AUTOMATION 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