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

Intelligent LOGO generation method based on StyleGAN

An intelligent and slogan technology, applied in the field of computer vision, can solve the problems of low efficiency of logo icons, and achieve the effect of various styles and high efficiency

Pending Publication Date: 2022-03-22
北京艺源酷科技有限公司
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Under the existing technology, the design of logo icons relies on manual designers, limited by the efficiency of labor, the efficiency of manual designers to design logo icons will be relatively low

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
  • Intelligent LOGO generation method based on StyleGAN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] as attached figure 1 As shown, a kind of intelligent LOGO generation method based on STYLEGAN of the present embodiment comprises the following process:

[0039] 1. The user enters the name of the logo, the slogan of the logo, and selects the industry to which the logo belongs;

[0040] 2. Generation steps

[0041] 2.1. Prepare a batch of logo icon datasets;

[0042] 2.2. Divide 2.1 into different sub-datasets according to the industry;

[0043] 2.3. On the sub-dataset of 2.2, use StyleGAN to train generative models of different industries;

[0044] 2.4. When the user selects an industry, the corresponding logo icon can be generated according to the generation model in 2.3.

[0045] 3. Logo font collocation rules

[0046] The logo font matching rules of this embodiment are as follows:

[0047] 3.1. Prepare a batch of logo data

[0048] 3.2. Divide the logo data in 3.1 into different sub-datasets according to the industry

[0049] 3.3. Manually mark the font of t...

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 relates to the technical field of computer vision and the technical field of graphic processing methods, in particular to an intelligent LOGO generation method based on a StyleGAN. According to the method, the StyleGAN algorithm is adopted, the logo icon generation model is obtained based on massive logo data set training, and the efficiency of generating the logo icon through the generation model is higher than that of completely manual or semi-manual operation; compared with the logo generated by manual rules, the effect is more in line with aesthetics, and the styles are more diverse.

Description

technical field [0001] The invention relates to the technical field of computer vision and the technical field of graphics processing methods, in particular to an intelligent LOGO generation method based on StyleGAN. Background technique [0002] A complete logo graphic consists of logo icon + logo name + logo slogan + logo font matching rules + logo layout rules + logo color matching rules. For logo icons, the current common technologies in the industry are as follows: one is completely designed by the designer; the other is to summarize some steps of the manual design of the designer into rules, and then realize the semi-manual design of manual + rules, For example, "Logo Generation Method Based on Natural Patterns, Intelligent Logo Generator", which has been patented, application publication number CN 108549530 A, application number: 202110966926.6. [0003] Generative Adversarial Networks (GANs) are one of the most promising approaches for unsupervised learning on compl...

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): G06T11/60G06T11/00G06F30/27G06N3/04G06N3/08
CPCG06T11/60G06T11/001G06F30/27G06N3/088G06N3/047G06N3/045
Inventor 张国昌王宝臣李晋松殷允恒
Owner 北京艺源酷科技有限公司
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