Image search method based on soft constraint non-supervision cross-modality hash

An image retrieval and unsupervised technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as no internal connection, no hash code discrete solution, accuracy and efficiency impact, etc., to achieve Effects of improving quality, reducing noise, improving accuracy and efficiency

Inactive Publication Date: 2018-03-06
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the method based on matrix rotation neither gives the discrete solution of the hash code, nor really mines the internal relationship between these sample points, which will affect the accuracy and efficiency of image and text cross-retrieval

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 search method based on soft constraint non-supervision cross-modality hash
  • Image search method based on soft constraint non-supervision cross-modality hash
  • Image search method based on soft constraint non-supervision cross-modality hash

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] like figure 1 As shown, the image retrieval method based on soft-constrained unsupervised cross-modal hashing includes the following steps in sequence: S1, establishing a data set of pictures and their corresponding text data, and extracting each picture and text in the data set Corresponding feature data are processed to obtain image feature data matrix and text feature data matrix; S2, construct image similarity matrix and text similarity matrix, and assign hash codes according to image similarity matrix and text similarity matrix, thus get Guide the hash code; S3, use the guided hash code to optimize the final hash code and the corresponding projection matrix; the specific method is: iteratively update the hash code and the projection matrix until the hash code and the projection matrix no longer change and output Final binary hash code and projection matrix; S4, select the trained hash code corresponding to the preset number of pictures and text data from the traini...

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 search method based on soft constraint non-supervision cross-modality hash. The method sequentially comprises the following steps of building a picture and a dataset of text data corresponding to the picture to obtain an image feature data matrix and a text feature data matrix; configuring an image similarity matrix and a text similarity matrix, distributing hash codes according to the image similarity matrix and the text similarity matrix, and thus obtaining guiding hash codes; adopting the guiding hash codes to optimize final hash codes and a corresponding projection matrix; calculating a Hamming distance between the hash codes and hash codes of a sample in a search base, and then descendingly outputting search results according to the size order of the Hamming distance. When the image search method is utilized, quantification loss of the hash codes can be lowered, semantic gaps can be shortened, discrete solutions can be obtained, and then the accuracy and efficiency of crossed searching of pictures and texts can be improved.

Description

technical field [0001] The invention relates to image retrieval technology, in particular to an image retrieval method based on soft constraint unsupervised cross-modal hashing. Background technique [0002] In recent years, with the rapid increase in the amount of data represented by pictures and texts, the amount of cross-modal data has also increased. Coupled with the fact that the data obtained from a single modality may have errors or inaccuracies, and the emergence of actual needs such as searching for text by image and searching for image by text, cross-modal learning has also been widely used. The main idea of ​​the existing cross-modal learning method is to use matrix mapping and matrix decomposition to obtain a solution to relax the constraints and then perform binarization to obtain the hash code. The hash code generated during its application will inevitably There is quantification loss. In order to solve this problem, a method based on matrix rotation represen...

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
CPCG06F16/583
Inventor 周宇轩郝凌云王书悦刘陆琛孙源良李耀先李倩
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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