摘要
传统的浆纱截面图像分析主要依靠人工检测分析,效率较低。将数字图像处理技术应用于浆纱切片图像的自动分析,改进了纺织行业中传统的手工操作流程,提高了工作效率,对实现纺织产品检测的自动化、智能化具有现实意义。目前常用的浆纱截面图像分析方法主要是基于投影仪的人工分析和基于图像分析软件的半自动分析。
课题设计中引入数学形态学运算,考虑通过不同型号的视频显微镜采集的不同种类浆纱截面图像的特点,提出了一种基于数学形态学的浆纱切片自动分割算法,包括浆纱截面的分割,浆纱被覆与浸透部分的分割等。该方法在对浆纱切片图像进行预处理后,利用灰度填充算法获得浆纱截面在图像中的位置,并用闭合、面积滤波、孔洞填充等一系列处理分割出完整的浆纱截面以及浆纱截面的被覆与浸透部分。之后提出了一种基于特征点连接的算法来确定纱线的边缘,实现了浆纱截面被覆与浸透部分的分割,计算出了浆膜完整率。最后通过对浆纱截面总面积以及被覆与浸透部分面积的计算得到了浆纱的被覆率和浸透率。在设计中充分考虑了浆纱截面图像的特点,严格按照人工分割浆纱截面被覆与浸透部分的标准来分割图像,获得了比较理想的处理结果。
本文对多幅浆纱截面图像进行了实验,结果表明算法可以有效地进行浆纱截面参数的分析,处理速度快且准确率较高。
In the textile industry, the analysis of sizing section images is usually done by workers, so the analysis procedure is very time consuming and inefficiency. In order to improve work efficiency, Digital Image Processing is utilized to achieve automatic analysis of sizing section images. It plays an important role to improve automatization and artificial intelligence in textile production. Nowadays the realization of analysising sizing section images commonly based on projection equipments and image analysis software.
This thesis proposes a new automatic segmentation algorithm for sizing section images to segment the entire sizing section, the coating part and penetration part of them, the mathematics morphology approach was used and the characteristics of different sizing section images got through distinct video microscopes was carefully considered. This approach is based on locating the sizing section in the image which has been preprocessed, and the entire sizing section, coating part and penetration part are segmented after the processing of close, area filtering and filling holes algorithms. Further, an approach based on mark points' connection is proposed to get the edge of the yarn and separates the coating and penetration part of the sizing section and gets the integrity rate of it. At last, the coating rate and penetration rate are got through computing the areas of entire sizing section, coating part and penetration part of the microscopic images. The characteristics of the sizing section microscopic images are carefully considered and the standards of segmentation methods are strictly abided, the results are satisfiable.
Experiments are done through many sizing section microscopic images and the results show that the algorithm can be used to process these images in short time and at a high accurate rate.
引文
[1]朱德震,张依鸿编著.浆纱与调浆.北京:纺织工业出版社,1990.6
[2]李亚滨,杨弘等著.简明纺织材料学.北京:中国纺织出版社,1999.1
[3]沈兰萍著.织物组织与纺织品快速设计.西安:西北工业大学出版社,2002.8
[4]杨元.浆纱浆液渗透及被覆测试方法的比较.上海纺织科技,2005.33(7):60-64
[5]M.Grimaud.A new measure of contrast:Dynamics.Image Algebra and Morphological Image Processing Ⅲ,1992.1769:292-305
[6]Thomas W,Quigley JR,Karen E,Kyllo.Useful techniques in textile microscopy.Analytical Technique,1992.(8):19-22
[7]丁喻洋.纺织纤维显微图像的自动聚焦以及多焦面问题的研究.东华大学硕学位论文,2006.2
[8]吴潜,居太亮,姚伯威.应用种子填充算法提取图像的形状特征.电讯技术,2001.4:88-90
[9]张恩杰.长丝上浆效果快速检测评定系统的研制.东华大学硕士学位论文,2004.2
[10]卢官明,毕厚杰.形态重构算法及应用.信号处理,2000.16(2):137-144
[11]姚桂芬.基于浆纱质量的经纱可织性预测研究.东华大学博士学位文,2004.6
[12]蔡晋辉.实时自动视觉检测系统相关算法及应用研究.浙江大学博士学位论文,2005.6
[13]王跃宗,刘冲,王立鼎等.显微图象中目标对象的边缘提取研究.小型微型计算机系统,2003.24(12):2177-2180
[14]LucVincent.Morphological Grayscale Reconstruction in Image Analysis:Application and Efficient Algorithms.Image Processing,1993.2(2):176-201
[15]赵其明.高质量浆纱切片的制作方法.上海纺织科技,2005.33(9):68-69
[16]文浩,马金盛,王玉慧等.基于形态学灰度重构的乳腺微钙化点提取.CT理论与应用研究,2006.15(2):33-37
[17]徐东燕,付忠良,阮波.一种基于多结构元的弱对比度图像边缘检测方法.计算机应用,2004.24(6):108-110
[18]吴丹,刘修国,尚建嘎.数学形态学在图像处理与分析中的应用及展望.工程图学学报,2003(2):120-125
[19]王丰元,高松,孙壮志.数学形态学原理及其在图像处理中的应用.山东工程学院学报,1999.13(2):5-8
[20]张光新,蔡晋辉,周泽魁,施丽莲.面积重构算子的理论和应用.浙江大学学报,2005.39(9):1358-1362
[21]孙即祥著.图像分析.北京:科学出版社,2004
[22]高松.浆液渗透与被覆的定量测定.棉纺织技术,1992.(8):44-45
[23]张怀珠.浆纱横截面的显微定量观测及其应用.纺织技术,1964.(10):22-25
[24]夏德深,傅德胜著,计算机图像处理及应用.南京:东南大学出版社,2004.2
[25]边肇祺,张学工著,模式识别.北京:清华大学出版社,2000.1
[26]Maria Petrou,Panagiota Bosdogianni著.赖剑煌,冯国灿等译.数字图像处理疑难解析.北京:机械工业出版社,2005.4
[27]董立,于戈.一种有效的图像二值化方法.东北大学报.2004.25(12):1149-1152
[28]N.Otsu.A threshold selection method from gray-level histogram.IEEE Trans.SMC,1979:62-66,
[29]龙钧字,金连文.一种基于全局均值和局部方差的图像二值化方法.计算机工程,2004.30(2)
[30]刘冲,王跃宗,王立鼎,宋展.显微图象中目标对象的识别.计算机工程与应用,2003.9:98-100
[31]郭桂蓉主编.模糊模式识别.长沙:国防科技大学出版社,1992.4
[32]Zenzo S D.A note on the gradient of a multi image.Computer Graphics and Image Processing,1986.33:116-125
[33]Shiozaki A.Edge extraction using entropy operator.Computer Vision Graphics and Image Processing,1986.36:1-9
[34]Tetsuya Sano,Hidekazu Nagahata,Hiroshi Endo etal.A visual feedback System for micromanipulation whit stereoscopic microscope.IEEE Instrumentation and Measurement Technology Conference,1998.2:1127-1132.
[35]L.Vincent and B.Masters.Morphological image processing and network analysis of corneal endothelial cell images.Image Algebra and Morphological Image ProcessingⅢ,1992.1769:212-226
[37]Ma Bao-li,Zong Guang2hua,Hao Wei.Path planning of nonholonomic chained systems:a polynomial fitting approach.Acta Auto matica Sinsea,1999.25(5):662-666
[38]杨高波等编著.MATLAB 7.0混合编程.北京:电子工业出版社,2006.1
[39]郑阿奇著.matlab实用教程.北京:电子工业出版社,2004.5
[40]罗军辉,冯平.matlab7.0在图像处理中的应用.北京:机械工业出版社,2005.6
[41]Patricia A,Annis,Kam E,Kyllo.Hand techniques for cross sectioning fiber and yarns.Analytical Technique,1992.(9):78-82
[42]刘燕平.浆纱切片实验方法的研究.棉纺织技术,1984.(1):28-31
[43]周永元.浆纱合理质量指标的探索.纺织学报,1990.(4):14-17
[44]薛继伟,张问银,陈冬芳,王桂华.基于数学形态学的图像滤波方法.大庆石油学院学报,2003.27(4):48-50
[45]陈虎,周朝辉,王守尊.基于数学形态学的图像去噪方法研究.工程图学学报,2004(2):116一119
[46]David Simon,周瑜萍等著.Visual C++6编程宝典.北京:电子工业出社,2005.1
[47]DavidM,Hall,Robert P.Seanning electron microscopy for problem solving in textiles.Textile Chemist and colorist,1992.(6):15-18
[48]Behera B K,Had P K.Meehanism of yarn break for high-pressure squeezed sized yam.Indian Journal of Fiber & Textile Research,1993,(12):165-169
[49]丁雪荣.基于MATLAB图像处理技术的针织物结构参数测量的研究.天津工业大学硕士学位论文,2005.12
[50]周长发.精通Visual C++图像处理编程.北京:电子工业出版社,2004.10
[51]S.K.Pal,R.A.King.Histogram Egualization With S and π Functions in Detecting X-Ray Edge.Electron Letter,1981.17:302-304
[52]Hari P K,Behera B K.High pressure squeezing in sizing:performance of cotton yarn.Textile research journal.1989,(10):597-600
[53]李学佳.图像处理技术应用于纺织工业的最新动态.毛纺科技,2005.7:58-61
[54]章毓晋著.图像处理和分析.北京:清华大学出版社,1999.3
[55]Eileen K,Boylston.Microscopical Evaluation of Yarns.Textile Chemist and colorist,1999.(2):20-22