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

Method for enhancing trademark graph similarity judgment accuracy

A graphic similarity and accuracy technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of low accuracy, no further research and development and improvement, etc., to achieve improved accuracy, practical functions, The novel effect of the method

Active Publication Date: 2018-11-06
南昌奇眸科技有限公司
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Now people study how to use computers and other electronic devices to search and match trademarks has become a hot issue in this field. People continue to try various computer algorithms and multimedia technologies to automatically retrieve trademark graphics. In the link of feature extraction and comparison A lot of experiments and improvements have been done, but in the output of the results, it is often simply to judge whether they are similar or to output according to the comparison results, without further research and development and improvement, resulting in low accuracy

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
  • Method for enhancing trademark graph similarity judgment accuracy
  • Method for enhancing trademark graph similarity judgment accuracy
  • Method for enhancing trademark graph similarity judgment accuracy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] as attached figure 1 As shown, a method for improving the accuracy of trademark graphic similarity determination in this embodiment includes:

[0037] S101, sort the result pictures of the trademark similarity search according to the similarity with the trademark to be checked from high to low, and obtain the initial result picture sequence {S 0}=[I 01 , I 02 ,...,I 0k ,...];

[0038] S102, take the first k pictures of the primary result picture sequence in S101 as new trademarks to be checked and perform similarity sorting at least once, wherein k is an integer greater than or equal to 1, and obtain the secondary result picture sequence {S m}=[I m1 , I m2 ,...,I mk ,...], m=1,...,k;

[0039] S103, obtain the comprehensive result picture set S={S through the primary result picture sequence in S101 and the secondary result picture sequence in S102 0 ∪S 1 ∪…∪S m ∪…}={s t};

[0040] S104, taking the same picture in the integrated result picture set S as a unit...

Embodiment 2

[0044]The difference between this embodiment 2 and embodiment 1 is that the obtaining of the first result picture sequence includes the following four steps:

[0045] S201, establishing a trademark graphic database;

[0046] S202, extracting features of the trademarks to be checked and the trademarks in the trademark graph database;

[0047] S203, comparing the similarity between the features extracted in S202 and the features extracted in the trademark graphic database;

[0048] S204. Sort the comparison results in S203 in descending order of similarity.

[0049] In this embodiment, the similarity of feature extraction in the step S202 is based on existing corner detection, LSD (local statistical distribution feature) and GSD (GLobal Statistical Distribution, global statistical distribution feature); the steps The similarity comparison in S203 is also realized by using the existing corner point matching method corresponding to the feature extraction; after the corner point ...

Embodiment 3

[0051] On the basis of Embodiment 2, this embodiment 3 is also provided with a step S301 of preprocessing the graphics of the trademark to be checked and the trademark in the trademark graphics database before the feature extraction in step S202; There are steps such as translation, stretching, compression, enlargement, reduction, segmentation, and rotation; after the feature matching, there is also a step S302 of eliminating incorrectly matched pairs; the step S302 uses a RANSAC algorithm to eliminate incorrectly matched pairs.

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 method for enhancing trademark graph similarity judgment accuracy. Secondary retrieval and even multiple times of retrieval can be performed on the initial sorting result generated by the trademark arbitrary method and then final sorting is performed according to the set generated by final retrieval. According to the method, the sorting results of multiple times of retrieval of the correlation images are fused, the images having high appearance frequency have high weight, and the top sorted images have high weight so that the correlation between the images can be fully mined and the accuracy of trademark graph similarity judgment can be greatly enhanced. Meanwhile, the extraction and comparison mode enabling the initial sorting result to be more stable and accurate is also given for further enhancing the accuracy so as to provide a great foundation for subsequent secondary retrieval and even multiple times of retrieval.

Description

technical field [0001] The invention belongs to the technical field of trademark retrieval, and in particular relates to a method for improving the accuracy of judging the similarity of trademark graphics. Background technique [0002] Trademarks are an indispensable factor in the commercial economy. The annual number of trademark applications reaches one million levels, and the trademark data reaches tens of millions. For such a large number of groups, if people judge or examine whether two trademarks are similar and how similar they are When it comes to judgment, it is all judged by human eyes and subjective consciousness. There is a lot of room for improvement and improvement in terms of the operation cycle and the objective stability of the results. [0003] Now people study how to use computers and other electronic devices to search and match trademarks has become a hot issue in this field. People continue to try various computer algorithms and multimedia technologies 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
IPC IPC(8): G06K9/46G06K9/62
CPCG06V10/507G06V10/754
Inventor 樊晓东李建圃
Owner 南昌奇眸科技有限公司
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