纺织学报 ›› 2011, Vol. 32 ›› Issue (9): 136-141.

• 管理与信息化 • 上一篇    下一篇

基于小波变换的贾卡经编织物多区域自动识别

张丹1,蒋高明2,丛洪莲3,张爱军2   

  1. 1. 江南大学纺织服装学院经编研究中心
    2. 江南大学
    3. 江南大学经编研究中心
  • 收稿日期:2010-10-29 修回日期:2011-03-12 出版日期:2011-09-15 发布日期:2011-09-15
  • 通讯作者: 蒋高明 E-mail:jiang@526.cn

Automatic Identification of Jacquard Warp knitted fabrics' multi-zones based on Wavelet Transformation

  • Received:2010-10-29 Revised:2011-03-12 Online:2011-09-15 Published:2011-09-15

摘要: 为了简化贾卡经编织物贾卡组织区域的设计过程,针对贾卡经编织物多个区域的纹理特点,特别是网孔区域分类困难的情况,提出一种先通过中值滤波去除原图像噪声,再利用小波变换方法提取织物不同区域纹理特征,然后在已知分类数目的情况下,利用K均值聚类方法对所提取特征进行分割的区域自动识别方法。实验结果表明,该方法具有良好的识别效果,可以实现贾卡经编织物2个以上区域的半监督地自动识别,适应于网孔区域的自动分割,识别结果的区域一致性较好,边缘准确度较高。

Abstract: In order to simplify the regional design process of Jacquard regions in warp knitted fabrics, the automatic regional identification method is proposed in connection with the texture characteristics of various regions, particularly the difficult situation in mesh region classification. First median filtering is used for noise elimination in the original image. Second wavelet transform method is adopted to extract different fabrics regional texture features. Then in the case of knowing the Category number, K means clustering method is used to segment these texture features. Experiments show that the method has a good effect, Jacquard warp knitted fabric which with two or more regions can be distinguished in supervised and automatic manner, and the method is adapted to the mesh regions with better regional consistency and edge accuracy.

中图分类号: 

  • TS181.8
[1] 程龙 蒋高明. 经编浮纹贾卡提花原理[J]. 纺织学报, 2014, 35(1): 40-0.
[2] 陈莉 叶介茂. 基于函数Z=axc+byd的图案生成与针织产品设计[J]. 纺织学报, 2013, 34(2): 65-68.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!