欢迎访问《轻工机械》稿件在线采编系统!设为首页 | 加入收藏    
稿件处理系统
期刊信息
  • 中国标准连:ISSN1005-2895
  • 续出版物号: CN 33-1180/TH
  • 主管单位:轻工业杭州机电设计研究院
  • 主办单位:轻工业杭州机电设计研究院、中国轻工机械协会、中国轻工业机械总公司
  • 社  长:刘安江
  • 主  编:黄丽珍
  • 地  址:杭州市余杭区高教路970号西溪联合科技广场4-711
  • 电子邮件:qgjxzz@126.com
理事单位          MORE>>
王泽民, 刘妹琴, 樊臻, 张森林.基于平移相减法的机织物组织识别[J].轻工机械,2018,36(5):53-56
基于平移相减法的机织物组织识别
Recognition Method of Fabric Based on Translational Subtraction Algorithm
  
DOI:10.3969/j.issn.1005 2895.2018.05.010
中文关键词:  织物组织识别  平移相减  亮度累加  相位  组织循环
英文关键词:fabric organization recognition  TSA(translational subtraction algorithm)  grayscale accumulation  phases  texture circulation
基金项目:
作者单位
王泽民, 刘妹琴, 樊臻, 张森林 浙江大学 电气工程学院 浙江 杭州310027 
摘要点击次数: 240
全文下载次数: 188
中文摘要:
      针对现有机织物组织识别方法适用范围窄、鲁棒性差的现状,课题组提出一种计算织物组织循环大小的平移相减算法(translational subtraction algorithm,TSA),并提出了一种基于TSA算法的机织物组织有效识别方法。该方法结合机织物图像不同方向的TSA算法和水平方向的亮度累加法获取织 物组织循环宽度和纬线宽度,然后对机织物图像进行错位TSA算法,分析错位TSA曲线相位的周期性和大小,可以得到织物组织循环的纱线根数和飞数,最终获 得机织物图像的组织意匠图。实验证明该方法对机织物图像光照、纹理和倾斜等干扰因素具有鲁棒性,能有效识别各种类型的机织物组织。
英文摘要:
      In view of the current situation of narrow applicability and poor robustness of existing woven fabric recognition methods, translational subtraction algorithm(TSA) was proposed to calculate the size of fabric texture circulation and a recognition method of woven fabric based on TSA was designed. Through the combination of TSA in different directions of the woven image fabric and horizontal grayscale accumulation, the width of texture circulation and weft was calculated successfully. The number of yarns and the twills in fabric texture circulation can be obtained by using the dislocated TSA to analyze the period and the amplitude of phases of dislocated TSA curves, thus the pattern grid of fabric image was obtained. Experiments show that the proposed method is robust to interferes such as illumination, texture and tilt of the captured fabric image, and can identify various types of fabric images effectively.
查看全文  查看/发表评论  下载PDF阅读器
关闭