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

Image similarity calculation system, image search system, image similarity calculation method, and image similarity calculation program

A technology of image similarity and computing system, applied in computing, computing model, image analysis, etc.

Inactive Publication Date: 2007-03-07
NEC CORP
View PDF4 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Inability to obtain sufficient throughput to determine or retrieve original images from edited images

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 similarity calculation system, image search system, image similarity calculation method, and image similarity calculation program
  • Image similarity calculation system, image search system, image similarity calculation method, and image similarity calculation program
  • Image similarity calculation system, image search system, image similarity calculation method, and image similarity calculation program

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0100] A first embodiment of the present invention will be described with reference to the drawings. As shown in the block diagram of Figure 1, the first embodiment of the image similarity calculation system according to the present invention functionally includes: feature quantity extraction part 11, image similarity calculation part 12, editing probability model estimation device (editing probability calculation device An example of ) 13, and local area weight calculation means 14.

[0101] The feature amount extraction section 11 functionally includes image segmentation means 111 and small area feature amount extraction means 112 .

[0102] When an edited query image is input, the image segmentation means 111 segments the query image into small regions. The image segmentation unit 111 outputs the query image divided into small regions to the small region feature quantity extraction unit 112 . Editing processing means partially changing the image pattern. Editing examples...

no. 2 example

[0140] A second embodiment of the present invention will be described in further detail with reference to the accompanying drawings. As shown in the block diagram of FIG. 7, the second embodiment differs from the first embodiment as follows. The second embodiment of the image similarity calculation system according to the present invention replaces the image similarity calculation section 12 shown in FIG. 1 according to the first embodiment with an image similarity calculation section 22 . The second embodiment includes a reference image group small area feature amount storage section 25 and retrieval result output means 26 . The second embodiment provides an image similarity calculation system having a reference image group small region feature amount storage section 25 and retrieval result output means 26 . Such a system implements an image retrieval system.

[0141] The reference image group small area feature amount storage section 25 stores small area feature amounts fo...

no. 3 example

[0159] A third embodiment of the present invention will be described in further detail with reference to the drawings. As shown in the block diagram of FIG. 9, a third embodiment of the image similarity calculation system according to the present invention includes a feature quantity extraction section 11, an image similarity calculation section 32, an edited region detection device (an example of an edit probability calculation device) 33, and Local area weight calculation means 34 . The feature amount extraction section 11 is the same as that provided for the first embodiment.

[0160] The edited area detection means 33 uses a method of automatically detecting an edited area, such as a paper tape detection method for an edited query image provided as an input. Using this method, the edited area detection means 33 calculates a local edit probability, that is, the probability that an edit process is applied to each partial area in the query image. The edited area detection m...

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

There is provided an image similarity calculation system for calculating an image similarity between an image which has been subjected to processing and an original image. Local area weight value calculation means (14) calculates as a local area weight value a weight value for each image local area according to the probability of being subjected to processing for each image local area and outputs the calculated local area weight value to image similarity calculation means (122). A small area similarity calculation means (121) compares the characteristic amount of each small area obtained by dividing a query image to the characteristic amount of each small area obtained by dividing a reference image and calculates the similarity of characteristic amounts of each small area. The image similarity calculation means (122) calculates the image similarity between the query image and the reference image by using the weight value for each small area obtained from the local area weight value inputted from the local area weight value calculation means (14) on the calculated similarity of the characteristic amounts for each small area.

Description

technical field [0001] The present invention relates to an image similarity calculation system, an image similarity calculation method, and an image similarity calculation program for calculating the similarity of multiple images, and also relates to an image retrieval system for retrieving images similar to a query image . More specifically, the present invention relates to an image similarity calculation system, an image similarity calculation method, and an image similarity calculation program for detecting the similarity between an original image and an edited image, and also relates to a method for retrieving and An image retrieval system for images similar to the edited query image. Background technique [0002] There is an image similarity calculation method to calculate the similarity between two images to be compared with each other. Generally, such an image similarity calculation method is used to calculate the similarity between a query image and a retrieved ima...

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): G06T7/00G06F17/30G06N3/00G06V10/50
CPCG06K9/4642G06K9/6212G06V10/50G06V10/758G06T7/00G06N3/00
Inventor 岩元浩太
Owner NEC CORP
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