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

Learning to predict color harmony from user preferences

A color and user technology, applied in the field of image processing, can solve problems such as inaccurate prediction models and failure to consider the influence of color harmony, and achieve high accuracy

Active Publication Date: 2021-11-05
ZHEJIANG GONGSHANG UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although such a data set can be quickly trained as a label for a supervised model, it does not consider the influence of different users' preferences on the degree of color harmony, so their prediction models are not accurate.

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
  • Learning to predict color harmony from user preferences
  • Learning to predict color harmony from user preferences
  • Learning to predict color harmony from user preferences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention quantifies the color aesthetics of different users through the model, and finally reflects each user's preference for color through the aesthetic ability value. The user can input five different color themes with the same area, and the method in this paper can generate the color themes. The degree of harmony of the color theme, expressed in numerical values.

[0033] Part 1: Data Acquisition and Preprocessing

[0034] Step 1: Perform an online crawler on the online website COLOURLOvers to obtain all color theme ids with more than 5 comments on the website, as well as user comment ids and specific comments.

[0035] Step 2: Semantic classification of the obtained comment information. Retrieve whether there are keywords of selected positive words or negative words in user comments, and judge the harmony degree of the comments according to the keywords. For comments that do not contain keywords, list their harmony value as 4. Table 1 shows the deta...

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 learning and predicting the degree of color harmony according to user preference. The present invention is based on user comments of a large-scale website data set, first semantically classifies user comments on color themes in the data set, and divides comments into multiple different harmony values ​​according to specific keywords. Multiple color themes are then extracted from the color themes and trained in a three-layer backpropagation neural network. The results output from the hidden layer generate aesthetic ability values ​​that conform to user aesthetics through a probability density model based on Kernel distribution. Finally, the final color harmony value is obtained through linear calculation. The harmony value estimated by the present invention has high accuracy because it takes into account the aesthetics of different users on colors, and the present invention can be used in practical applications such as color suggestions with palettes, recoloring of images, and color style conversions scene.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for learning and predicting the degree of color harmony according to user preference. Background technique [0002] Color matching can be used in various fields such as graphics, posters, clothing and interior home design. Among them, harmonious color matching is the decisive factor for the popularity of the design. Designers often adopt harmonious color matching that everyone can accept in their designs, some of which are proven to be effective in color harmony theory, for example, the color matching at a specific position in the color wheel is harmonious, and people build on this basis Harmonious color matching such as similar colors, contrasting colors, and three roles. But in most people's eyes, they lack the artist's eye and theoretical knowledge, so creating and evaluating a harmonious set of color themes becomes very difficult. [0003] Wit...

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 Patents(China)
IPC IPC(8): G06F16/951G06N3/04G06N3/08
CPCG06F16/951G06N3/084G06N3/047G06N3/048G06N3/045
Inventor 杨柏林魏天祥
Owner ZHEJIANG GONGSHANG UNIVERSITY
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