Supercharge Your Innovation With Domain-Expert AI Agents!

Blocking, weighting and matching retrieval method based on commodity image saliency map

A product image and remarkable technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as inability to reflect, retrieve users, poor detection results, etc., to achieve the goal of improving similarity and enhancing robustness Effect

Inactive Publication Date: 2013-04-17
HANGZHOU TAOTAOSOU TECH
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] When using global features such as color, texture, shape, etc. for image retrieval, the foreground and background of the image are not distinguished, resulting in the inability to reflect what the user really cares about in the image. Only the global statistical similarity of the image can be compared, resulting in poor detection results.
[0007] In order to overcome the insufficiency of global features in describing image content, a region-based image retrieval method is now proposed, but it does not highlight the image parts that the user cares about, which may lead to the retrieval of images that the user is not satisfied with.

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
  • Blocking, weighting and matching retrieval method based on commodity image saliency map
  • Blocking, weighting and matching retrieval method based on commodity image saliency map
  • Blocking, weighting and matching retrieval method based on commodity image saliency map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The purpose and effects of the present invention will become more apparent by describing the present invention in detail below in conjunction with the accompanying drawings.

[0018] Such as figure 1 As shown, the present invention is based on the sub-block weighted matching retrieval method of commodity image saliency map and comprises the following steps:

[0019] Step 1: Extraction of product image features to provide feature data for subsequent image retrieval and matching.

[0020] Firstly, adopt the strategy of actively dividing the product query image uploaded by the user, and extract it as the original image respectively. figure 1 Visual features of 5 sub-image blocks of size / 2 including upper, lower, left, right, and center and 6 original images.

[0021] Visual features mainly include shape features and layout features. The image shape feature extraction method adopted in this patent is as follows: firstly, the color image is converted into a grayscale imag...

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 blocking, weighting and matching retrieval method based on a commodity image saliency map. The characteristics of block images are calculated by actively blocking a commodity inquiring image inputted by a user, the saliency map of a commodity body of the inquiring image is extracted, and weight coefficients of the characteristics of the block images in matching measurement are calculated according to the saliency map. The function of the commodity body in matching is highlighted, recall ratio and precision ratio are increased, and the method is fine in robustness in application.

Description

technical field [0001] The invention relates to the technical field of image search and the field of image processing for pattern recognition, in particular to a retrieval method and system based on block weighted matching of commodity salient images. Background technique [0002] With the development of multimedia information technology and Internet technology, especially the emergence of large-scale digital image database, image information has been paid more and more attention. How to manage the rapidly growing image information and quickly and effectively find out the images that people are interested in from the massive image collection has become a work with extensive practical significance. [0003] Early image retrieval was text-based image retrieval (Text_Based Image Retrival). However, this retrieval method has great limitations. The visual features contained in rich images often cannot be described objectively by text. [0004] The content-based image retrieval t...

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 吕晟珉孙凯
Owner HANGZHOU TAOTAOSOU TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com