纺织学报 ›› 2011, Vol. 32 ›› Issue (10): 141-0.

• 管理与信息化 • 上一篇    下一篇

经编贾卡织物纹理分割与轮廓提取技术

张扬1,蒋高明2,姚君洲3,童有成4   

  1. 1. 浙江理工大学;江南大学
    2. 江南大学
    3. 江南大学 经编技术教育部工程研究中心
    4. 浙江大学 宁波理工学院
  • 收稿日期:2010-11-19 修回日期:2011-05-25 出版日期:2011-10-15 发布日期:2011-10-24
  • 通讯作者: 蒋高明 E-mail:jiang@526.cn

Texture segmentation and contour extraction of jacquard fabric

  • Received:2010-11-19 Revised:2011-05-25 Online:2011-10-15 Published:2011-10-24

摘要: 为了进一步提高经编贾卡织物智能分析与设计技术,提出一种基于小波变换和Canny算子的贾卡织物纹理分割和轮廓提取算法。该算法首先采用具有局部定域能力和多分辨率能力的小波变换作为分析工具,将织物图像的织物图像中的低频部分作递归金字塔结构分解;其次从分解后的最大尺度水平开始,逐层图像聚类,并融入下一尺度水平上的高频信息实现纹理的重构和自动分割;最后采用canny算子对分割后的图像纹理进行轮廓跟踪提取。实验结果表明:该算法对于贾卡织物具有较好地适用性,并为后续的深入研究提供一个理论平台。

Abstract: To improve the intelligent analysis and design technology of warp knitting jacquard fabric, a new way of texture segmentation and contour extraction based on wavelet-transform and canny operator is proposed in this paper. Firstly making use of the wavelet-transform which has the ability of orientation and multiresolution, the algorithm decomposes the low frequency part of the fabric image in a way of pyramid-structure. Secondly from the biggest level after decomposition, the image is automatic clustered and segmented with the information at the next level. Lastly the texture’s contour of image is traced and extracted through the method of canny operator. The results show that this algorithm is a feasible way for jacquard fabric, and it supplies a theoretical platform for subsequent research.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!