Bird feather color feature extraction method

A color feature and extraction method technology, applied in digital image processing and color fields, can solve the problems of different color feature extraction and representative colors not being extracted, so as to expand the design field, increase added value, and broaden the market prospect Effect

Inactive Publication Date: 2018-07-20
ZHEJIANG SCI-TECH UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the K-means algorithm has the problem that each color feature extraction is different and some representative colors have not been extracted.

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
  • Bird feather color feature extraction method
  • Bird feather color feature extraction method
  • Bird feather color feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] A kind of bird feather color feature extraction method of the present embodiment, comprises the steps:

[0031] a) pick a photo of a bird;

[0032] b) Use Matlab software to open one or two bird photos that require color feature extraction;

[0033] c) Use Matlab software to extract the RGB values ​​of all pixels in the opened bird photo,

[0034] d) color-separate the bird photos according to the improved K-means clustering algorithm;

[0035] d1) The selection of the first initial cluster center is fixed as big red (R=255, G=0, B=0), and the second initial cluster center is green (R=0, G=255, B=0 ), the third initial point is blue (R=0, G=0, B=255);

[0036] d2) Calculate the next initial cluster center in turn by distance measurement method until all categories of initial cluster centers are selected, then calculate the distance between the remaining data and the first, second, and third initial cluster centers, and the maximum distance is the fourth cluster cent...

Embodiment 2

[0049] A kind of bird feather color feature extraction method of the present embodiment, comprises the steps:

[0050] a) Select a peacock feather photo to extract its color features;

[0051] b) Use Matlab software to open one or two bird photos that require color feature extraction;

[0052] c) using Matlab software to extract the RGB values ​​of all pixels in the opened bird photos;

[0053] d) color-separate the bird photos according to the improved K-Means clustering algorithm;

[0054] d1) The selection of the first initial cluster center is fixed as big red (R=255, G=0, B=0), and the second initial cluster center is green (R=0, G=255, B=0 ), the third initial point is blue (R=0, G=0, B=255);

[0055] d2) Calculate the next initial cluster center in turn by distance measurement method until all categories of initial cluster centers are selected, then calculate the distance between the remaining data and the first, second, and third initial cluster centers, and the max...

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 bird feather color feature extraction method. The method comprises the following steps: step a, collecting and selecting a plurality of high-resolution bird photos; step b, opening a bird photo needing color feature extraction by using Matlab software; step c, extracting RGB values of all the pixels in the opened bird photo by using Matlab software and setting the number of feature colors needing to be extracted and a convergence error value; step d, carrying out color separation on the bird photo based on a K-Means clustering algorithm; step e, carrying out color dataextraction on the photo after color separation by using Matlab software; and step f, extracting color data to make a color card. With the bird feather color feature extraction method, problems of feature color system changing and color missing during the traditional color feature extraction process can be solved, so that the high accuracy and stability of the extracted color features are ensured.The bird feather color feature extraction method can be applied to the silk field to increase the additional value of silk products.

Description

【Technical field】 [0001] The invention relates to the technical field of digital image processing and color, in particular to a method for extracting bird feather color features. 【Background technique】 [0002] Color bionics is an innovative color design method produced by the combination of bionic color research results and color design methods. It takes the excellent color function and form of natural organisms as the research object, explores its color principle, and uses it for design innovation to provide human beings with a higher level of color design results. Birds are one of the most colorful and beautiful terrestrial vertebrates. Every kind of bird has its own unique feather color. These rich and gorgeous biological colors are preserved by natural selection after hundreds of millions of years of evolution. During the long evolution, the color organization and color organization that conform to the law of formal beauty have gradually formed. structure. To perform...

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): G06K9/46G06K9/62
CPCG06V10/56G06F18/23213
Inventor 祝成炎朱炜婧金肖克吕智宁张旻爽张红霞
Owner ZHEJIANG SCI-TECH UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap