Content duplicate detection method of network image based on GIST (generalized search tree) global feature and SIFT (scale-invariant feature transform) local feature

A technology of local features and global features, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem that the copyright of pictures cannot be effectively protected, duplicated, etc.

Inactive Publication Date: 2013-09-11
北京明日时尚信息技术有限公司
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, on the one hand, the copyright of pictures cannot be effectively protected;

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
  • Content duplicate detection method of network image based on GIST (generalized search tree) global feature and SIFT (scale-invariant feature transform) local feature
  • Content duplicate detection method of network image based on GIST (generalized search tree) global feature and SIFT (scale-invariant feature transform) local feature
  • Content duplicate detection method of network image based on GIST (generalized search tree) global feature and SIFT (scale-invariant feature transform) local feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0005] The present invention relates to a kind of network picture content duplication detection method based on GIST global feature and SIFT local feature, it is characterized in that, one is to extract GIST feature and SIFT feature to background image set, and adopt LSH (Locality Sensitive Hashing, position sensitive hashing) ) algorithm to establish an index; the second is to extract the GIST feature and SIFT feature for the query image; the third is to match the image feature and perform content duplication detection; the fourth is to update the index; the specific steps are as follows:

[0006] 1. Extract GIST features

[0007] The input image is normalized, and an image pyramid is constructed on each channel of the normalized image, which are R, G, and B color channels respectively. The total number of layers of the image pyramid is , and each layer is an image of a different resolution;

[0008] On a certain layer image of the image pyramid of each channel, the image is ...

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 a content duplicate detection method of a network image based on a GIST global feature and an SIFT local feature. The method comprises the steps as follows: the GIST global feature and the SIFT local feature of an image are extracted respectively; the GIST global feature is used for identifying the image global invariance; the SIFT local feature is used for identifying the image local invariance; and indexing and matching image features are constructed for the two types of the features with an LSH (Locality Sensitive Hashing) algorithm, and content duplicate detection is performed.

Description

technical field [0001] The invention relates to a network picture content repetition detection method based on GIST global features and SIFT local features, and belongs to the field of content-based picture retrieval. Background technique [0002] With the development of network technology and digital imaging technology, people can create pictures in a simple way, and easily share and disseminate them on the Internet, and others can also download, copy and modify pictures without restriction. In this way, on the one hand, the copyright of pictures cannot be effectively protected, and on the other hand, there will be a large number of content duplications in pictures on the Internet. In order to solve these problems, the present invention proposes a method for detecting duplication of network picture content, which can be used not only for the protection of picture copyright, but also for e-commerce websites or picture sharing communities to reduce the storage of duplicate pi...

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 李洋胡楠邹国平
Owner 北京明日时尚信息技术有限公司
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