User trademark image retrieval-based method and system

An image retrieval and trademark technology, which is applied in digital data information retrieval, special data processing applications, instruments, etc., can solve problems such as inability to guarantee the correctness of trademark classification, lack of consistent measurement standards, and difficulty in describing images, etc., so as to reduce retrieval data, Improved accuracy and reduced management costs

Pending Publication Date: 2020-09-18
南通赛优科技服务有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional trademark retrieval is text-based retrieval, including category-based retrieval and keyword-based retrieval. As the number of registered trademarks increases, traditional trademark retrieval technology has certain defects, for example: 1) The retrieval system is based on manual Classification management, the management cost is too high; 2) When there are relatively abstract trademark images, it is not easy to describe the image in the form of text, and it is not easy to classify; 3) There is no consistent measurement standard for the similarity of images, and it cannot guarantee whether the trademark classification is correct or not. correct

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
  • User trademark image retrieval-based method and system
  • User trademark image retrieval-based method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041] like Figure 1-2 As shown, an embodiment of the present invention provides a method for searching based on a user's trademark image, and the method includes the following steps:

[0042] S1. Obtain the target trademark file, extract the original image of the trademark, and establish an original image database. The specific contents are as follows:

[0043] 1) First, determine the keywords, categories, markers and other attributes that need to be acquired for the target trademark, search for the relevant target trademarks according to each attribute, and obtain the target trademark set;

[0044] 2) Collect the images on each trademark obtained, establish an original image database, and put all the collected trademark images into the database;

[0045] S2. Decompose the original image, construct a fragmented image collection, and extract the feature values ​​in the collection. The specific contents are as follows:

[0046] 1) Obtain the trademark image from the original...

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 a user trademark image retrieval-based method and system and relates to the technical field of trademark image retrieval. The user trademark image retrieval-based method comprises the following steps: S1, obtaining a target trademark file, extracting an original trademark image, and establishing an original image database; s2, decomposing the original image, constructing a fragment image set, and extracting feature values in the set; s3, continuously performing feature fusion on the extracted feature value set to generate key points of the fragment image; and S4, constructing a supervised learning model, and training the key points of the fragment image by using the supervised learning model. According to the invention, the original trademark image is decomposed. According to the trademark image retrieval method and system, the feature values of the fragment images are obtained, then the feature values of the fragment images are utilized to obtain the key pointsof the fragment images, and then the key points of the fragment images are trained, so that the whole retrieval system can quickly retrieve the trademark images, the trademark images are convenientlyclassified, and the retrieval accuracy is greatly improved.

Description

technical field [0001] The invention relates to the technical field of trademark image retrieval, in particular to a method and system for user-based trademark image retrieval. Background technique [0002] Trademarks are used by producers or operators of goods on the goods they produce, manufacture, process, select or distribute, or on the services provided by service providers, to distinguish the source of goods or services, including words and graphics. , letters, numbers, three-dimensional signs, color combinations and sounds, etc., as well as the combination of the above elements, the signs with distinctive features are the products of the modern economy. [0003] The traditional trademark search is based on text, including category-based search and keyword-based search. With the increase in the number of registered trademarks, the traditional trademark search technology has certain defects, such as: 1) The search system is based on manual Classification management, th...

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): G06F16/583
CPCG06F16/583
Inventor 施建建倪海斌
Owner 南通赛优科技服务有限公司
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