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

Image retrieval method based on style characteristics

An image retrieval and style technology, applied in special data processing applications, instruments, biological neural network models, etc., can solve problems such as poor retrieval results

Active Publication Date: 2017-11-24
ZHONGYUAN WISDOM CITY DESIGN RES INST CO LTD
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This retrieval method focuses on detecting an actual object in a picture, but does not perform well for abstract images without actual objects

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 style characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solutions of the present invention will be described in further detail below through specific implementation methods.

[0022] Such as figure 1 As shown, an image retrieval method based on style features includes the following steps:

[0023] establish plantform

[0024] S1, using the Theano-based framework Keras to build a processing platform:

[0025] (1) Server configuration

[0026] Server with TitanX graphics card, Xeon quad-core processor, 32GB memory;

[0027] (2) Operating system:

[0028] Using Linux operating system;

[0029] (3) Development environment

[0030] Using Python language and PyCharm IDE development environment;

[0031] (4) Framework construction

[0032] The Keras deep learning framework is adopted, and Theano is encapsulated at the bottom layer. Keras is a minimalistic third-party neural network library that can take full advantage of GPU and CPU operations due to its highly modular nature.

[0033] (5) Client tool

[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 provides an image retrieval method based on style characteristics. By adopting a Gram matrix as an operator for describing image style characteristics, style characteristics of all training samples of a given image library are extracted, an image index is constructed, the style characteristics of images to be detected are extracted, an index number of the image with the highest similarity as the image to be detected is found, and a similar image set is returned back according to the index umber. Abstraction image retrieval is achieved through the method, and the method has the advantages of being simple and good in retrieval effect.

Description

technical field [0001] The invention relates to an image retrieval method, in particular to an image retrieval method based on style features. Background technique [0002] There are two types of image retrieval, one is text-based image retrieval TBIR, and the other is content-based image retrieval CBIR. Among them, CBIR retrieves by analyzing the specific objects or scenes contained in the image in detail. The key to its realization lies in the extraction of image features. Common feature extraction methods include extraction based on color, shape, and texture features. The underlying visual features can achieve the purpose of retrieval. This retrieval method focuses on detecting a real object in a picture, but it does not perform well for abstract pictures without real objects. [0003] In order to solve the above existing problems, people have been seeking an ideal technical solution. Contents of the invention [0004] The object of the present invention is to addres...

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): G06F17/30G06N3/04G06N99/00
CPCG06F16/5838G06N20/00G06N3/045
Inventor 陈长宝杜红民侯长生孔晓阳王茹川郭振强郧刚王磊王莹莹肖进胜
Owner ZHONGYUAN WISDOM CITY DESIGN RES INST CO LTD
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