纺织学报 ›› 2015, Vol. 36 ›› Issue (05): 123-126.

• 管理与信息化 • 上一篇    下一篇

基于图像边缘特征的领带花型检索方法

  

  • 收稿日期:2014-03-05 修回日期:2014-06-10 出版日期:2015-05-15 发布日期:2015-05-12
  • 通讯作者: 张华熊 E-mail:zhxhz@zstu.edu.cn

Necktie pattern retrieval method based on image edge characteristics

  • Received:2014-03-05 Revised:2014-06-10 Online:2015-05-15 Published:2015-05-12

摘要:

为了提高领带花型检索的速度和准确度,提出了一种基于图像边缘特征的检索方法。首先,对图案进行边缘检测,提取领带花型的轮廓,量化为边缘特征值;然后,分析边缘特征值分布的数理统计特性,将花型分为条纹、多边形和复杂图案 3 个大类;最后,将待检索花型与数据库内同类花型进行匹配,选取最相似的花型图案。结果表明,基于图像边缘特征的检索方法能够精确地检索相似的领带花型,并且计算量小,检测速度快,可以满足实际应用的需求。

关键词: 领带花型, 图像检索, 边缘特征, 特征匹配

Abstract:

In order to increase the accuracy and speed of necktie pattern retrieval, an image retrieval method based on the edge characteristics is introduced. Firstly, the edge of necktie pattern is extracted by edge detection, and the result is quantitated as edge characteristic. After that, the statistic of the edge characteristic distribution is analyzed. Based on analyses, the necktie pattern is divided into stripe, polygon and complex pattern. Finally, the pattern to be retrieved is matching with the patterns in the database, and the most-similar patterns are chosen as a result. The experiment result shows that the proposed method could retrieve similar patterns precisely with low computation, which is greatly practicable.

Key words: necktie pattern, image retrieval, edge characteristic, feature matching

中图分类号: 

  • TP 399
[1] 汪珊娜 张华熊 康锋. 基于卷积神经网络的领带花型情感分类[J]. 纺织学报, 2018, 39(08): 117-123.
[2] 向忠 何旋 钱淼 胡旭东. 基于边缘和颜色特征的织物印花花型检索[J]. 纺织学报, 2018, 39(05): 137-143.
[3] 曹霞 李岳阳 罗海驰 蒋高明 丛洪莲. 蕾丝花边的改进型纹理特征检索方法[J]. 纺织学报, 2016, 37(06): 142-154.
[4] 康锋 胡洁 张华熊 周慧. 基于最大稳定极值区域的织物图案检索[J]. 纺织学报, 2015, 36(10): 156-0.
[5] 项明 姚雪存 崔振东 华铨平. 利用相关反馈技术和形状特征的服装图像检索算法[J]. 纺织学报, 2014, 35(2): 94-0.
[6] 刘军;李重;胡觉亮. 基于特征匹配的三维试衣效果[J]. 纺织学报, 2009, 30(01): 122-126.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!