机织物组织结构的识别-控制理论与控制工程专业论文.docxVIP

中文摘要中文摘要 中文摘要 中文摘要 本文以华茂纺织股份有限公司的机织物组织结构识别的生产需求为应用背景，针对平 纹、斜纹、缎纹的单层机织物，通过采集图像，对其进行数字图像处理，探寻出识别机织物 的组织结构和经纬线密度的方法。 首先，为了适应机织物图像采集和识别的要求，要选择台适的图像采集装置。本实验在 图像采集装置上组合采片j了尼康微距数码照相机4500和体视显微镜，并且配备了侧照明光 源。这样选择图像采集装置的目的是使采集的图像在放大倍数上适中，能够清晰地观察到织 物的纹理，又不保留太多的细节而影响了主要信息的提取。 然后．本文根据机织物在光照下表面凸凹这一特性反映在二维图像上的灰度的差异，尝 试从织物灰应图像中识别出经纬密度和织物的组织结构。在经纬线密度的识别上，采用谱估 计的周期图法求经纬线根数和经纬线密度：在机织物的组织结构识别上，利用数字图像处理 的基本方法，根据织物图像的特点，本文提出了如卜的识别组织结构的三种处理方案：基于 图像分割和数学形态学处理的方法、基于区域分块处理的方法和基于小波分解特征提取的方 法来求取组织结构。实验结果表明，这些方案对单层的基本机织物组织结构的识别是有效的。 最后，本文叙述了对机织物识别的总结和展望。 关键词：数字图像处理组织结构机织物纹理分析小波分解 东南大学硕士学位论文Abstract 东南大学硕士学位论文 Abstract Researches ofautomatic recognition ofwoven textile were motivated by the demands offabric industry Humans have surprising capability to easily comprehend image，but studies of automatic recognition of woven textile have always been difficult mainly because the physical irregularity of fibers and textures under illumination，and also lack of prior knowledge in recognition． The principal purpose of this dissertation is to find out some practical methods for industrial recognition for some certain types ofwoven texture with aRempts．Some general prerequisites required． Some techniques are proposed in this dissertation based the integration of certain fundamental image process methods．The numerical experiments ofcase study in this dissertation support the methods．The work described here has not yet provided completely solution，but it suggests that the of these methods combined with the human manipulations interactively makes it possible to recognition ofwoven textures ifthe textures not too complex． Experimental results show that this technique produces satisfied results than traditional techniques based unitary specific method．And industrial application will be expected in not400-long future． Future work wilI be focus甜on the development ofindustrial software． Key words：digital image processing，texture analysis，woven textile，textural feature，wavelet analysis lI 学位论文独创·陛声明本人声明所呈交的学位论文是我