Unlock instant, AI-driven research and patent intelligence for your innovation.

Theme color extraction method based on human eye vision

A technology of human vision and extraction methods, applied in instruments, character and pattern recognition, computer parts, etc., can solve problems such as inability to extract theme colors, poor theme colors, and theme colors that cannot cover the image color space.

Active Publication Date: 2019-10-01
BINHAI IND TECH RES INST OF ZHEJIANG UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

O'Donovan et al. proposed a method based on measuring the harmony of color sets, but this method is aimed at the application of graphic design, so when this method deals with natural images, it usually extracts poor theme colors. The method needs to extract the theme color from multiple pictures and is not suitable for extracting the theme color from a single picture
Lin et al. also extracted a method for learning the subject color of the human eye, but the subject color extracted by this color extraction method cannot cover the color space of the entire image, and cannot extract a fixed number of subject colors. For some image editing related In the field of processing, the number of adjustable theme colors will be more suitable for the scene

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
  • Theme color extraction method based on human eye vision
  • Theme color extraction method based on human eye vision
  • Theme color extraction method based on human eye vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

[0041] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0042] Such as figure 1 As shown, a subject color extraction method based on human vision includes the following steps:

[0043] A. Construct a color map model in the RGB color space;

[0044] B. Establish the connection relationship between pixel colors in the color map model;

[0045] C. Use the Louvain community discovery algorithm to obtain the initial theme color;

[0046] D. Use the data-driven method to learn the way the human eye extracts the theme color, and obtain the sorting theme color result similar to the human eye vision.

[0047] The steps for setting up the color map model in the step A are:

[0048] A1. Select the picture that needs to extract the theme color;

[00...

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 theme color extraction method based on human eye vision. The theme color extraction method comprises the following steps: constructing a color map model in an RGB color space;establishing a connection relationship between pixel point colors in the color map model; obtaining an initial theme color by using a Louvain community discovery algorithm; and obtaining the sorted theme color similar to the human eye vision in a data driving manner. The method has the advantages that the main problems that in an existing theme color extraction method, vision is inconsistent withthat of human eyes, and extracted theme colors have no importance sorting are solved; in order to obtain a color consistent with a human eye vision extraction theme color, an improved community discovery algorithm is utilized to obtain an initial theme color on the basis of constructing a color map model, then three important attribute values, namely significance, distance and number, in color extraction are selected, a linear equation is constructed to fit a theme color extraction rule of human eyes, and a theme color extraction effect similar to the human eyes is obtained.

Description

technical field [0001] The invention belongs to the field of subject color extraction, and in particular relates to a subject color extraction method based on human vision. Background technique [0002] Pictures of natural scenes generally have a harmonious and consistent color distribution, and in many image design applications, it is difficult for non-professional designers to extract appropriate theme colors to create color visual effects that are consistent with natural scenes. Therefore, being able to automatically and accurately extract the theme color in the picture plays a great role in the above-mentioned applications. In addition, accurate extraction of theme colors has many applications in image classification, image retrieval, image recoloring and other fields. It is still difficult to extract a satisfactory theme color from a picture. At present, the existing theme color extraction algorithms mainly fall into two categories: the theme color extraction method ba...

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): G06K9/46
CPCG06V10/56
Inventor 盛楠陈刚叶静雯宋杰
Owner BINHAI IND TECH RES INST OF ZHEJIANG UNIV