A Method of Pattern Feature Extraction for Clothing Texture

Ying Wu
{"title":"A Method of Pattern Feature Extraction for Clothing Texture","authors":"Ying Wu","doi":"10.1109/ICRIS.2017.10","DOIUrl":null,"url":null,"abstract":"In order to improve the information elements in fashion design display ability, feature extraction and pattern information for modeling clothing texture, a clothing texture pattern texture segmentation method the dynamic characteristics and speed up robust feature matching based on sparse interference on clothing texture acquisition case scattered point segmentation and denoising, color the introduction of Hessian component RGB scale clothing texture pattern decomposition method to decompose, clothing texture pattern feature extraction by the interference of texture segmentation, using Taubin smoothing operator clothing texture map in case of three-dimensional reconstruction of image pixel space, linear texture pattern reorganization of the clothing RGB component by Radon transform, to achieve the extraction of pattern features for clothing texture. The simulation results show that the extracted pattern features by using this method to achieve the texture of the clothing, clothing color information fusion of shape vision information can improve the information expression ability of dress texture, and the feature extraction of output pattern is better.","PeriodicalId":443064,"journal":{"name":"2017 International Conference on Robots & Intelligent System (ICRIS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Robots & Intelligent System (ICRIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRIS.2017.10","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In order to improve the information elements in fashion design display ability, feature extraction and pattern information for modeling clothing texture, a clothing texture pattern texture segmentation method the dynamic characteristics and speed up robust feature matching based on sparse interference on clothing texture acquisition case scattered point segmentation and denoising, color the introduction of Hessian component RGB scale clothing texture pattern decomposition method to decompose, clothing texture pattern feature extraction by the interference of texture segmentation, using Taubin smoothing operator clothing texture map in case of three-dimensional reconstruction of image pixel space, linear texture pattern reorganization of the clothing RGB component by Radon transform, to achieve the extraction of pattern features for clothing texture. The simulation results show that the extracted pattern features by using this method to achieve the texture of the clothing, clothing color information fusion of shape vision information can improve the information expression ability of dress texture, and the feature extraction of output pattern is better.
一种服装纹理图案特征提取方法
为了提高服装设计中信息元素的展示能力,提取服装纹理的特征并对图案信息进行建模,提出了一种服装纹理图案纹理分割的动态特征和加快鲁棒特征匹配的方法,基于稀疏干扰对服装纹理采集案例进行散点分割和去噪,彩色引入Hessian分量RGB尺度服装纹理图案分解方法进行分解;服装纹理图案特征提取通过纹理分割的干涉,利用Taubin平滑算子对服装纹理图进行三维图像像素空间重构,对服装的RGB分量进行线性纹理图案重组,通过Radon变换,实现服装纹理图案特征的提取。仿真结果表明,利用该方法提取的图案特征实现了服装纹理、服装颜色信息与形状视觉信息的融合,提高了服装纹理的信息表达能力,并且输出图案的特征提取效果较好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信