基于图像处理的蚕丝被工艺质量中填充物均匀度检测研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着计算机技术的飞速发展和图像处理技术的日益成熟,图像检测技术已经成功应用于工业检测,人工智能,生物医学,空间探测以及遥感等许多领域,不仅取得了很多研究成果,并促使这些学科产生了新的发展。
     蚕丝被工艺质量中填充物均匀度的检测是蚕丝被质量检测中最重要的检验项目之一,目前基本上依靠人工检测,传统的检测方法劳动强度大,耗费时间长,且容易受检验人员主观因素影响,重复一致性偏差大,而且是破坏性测试。因此,寻找一种能有效地代替人工检测的方法具有重要的理论与现实意义。本文正是在这种背景下,提出了基于图像处理的蚕丝被工艺质量中填充物均匀度的检测研究这一课题。
     本文对传统的蚕丝被填充物均匀度检测方法和图像检测相关技术进行了详细的分析和研究,在分析了蚕丝被国家标准(GB/T24252-2009)中关于蚕丝被填充物均匀度检测的相关检测方法,以及蚕丝被厚薄差异率和角质量差异率的计算方法的基础上,从图像处理的角度建立了厚薄差异率和角质量差异率的计算公式,具体研究工作:
     1.搭建合适的光照环境利用数码相机近距离大幅度的采集蚕丝被图像,然后进行图像的预处理,消除噪声和畸变。主要研究了图像几何畸变的校正算法。本课题利用双线性内插算法校正图像采集过程中造成的几何畸变,首先通过坐标变换对图像像素位置进行校正,然后利用双线性内插法进行像素灰度值的估算。
     2.研究了图像光照不均匀的校正算法。针对图像采集过程中背景光照的不均匀对图像灰度值提取所造成的影响;提出了基于小波的光照不均匀校正算法。首先通过基于小波的非线性回归方法来估计光照分布,然后从原图中减去光照分布图,实现消除不均匀背景光照的目的。
     3.研究了蚕丝被透光率(亮度)偏差与厚度均匀性,厚薄差异率的关系,结合光学知识建立了图像灰度,光密度及重量或体积的线性关系,然后利用蚕丝被图像积分光密度代替蚕丝被的重量求得厚薄差异率和角质量差异率。具体推导过程见附录。根据蚕丝被国家标准进行等级分类。实现蚕丝被均匀度检测的非破坏性测试。
     本文从图像处理的角度建立蚕丝被图像灰度值与蚕丝被厚度或者重量的关系,结合光学知识提取蚕丝被填充物含量的测量参数,然后由填充物含量测量参数代替蚕丝被的重量计算厚薄差异率H和角质量差异率J。实现蚕丝被工艺质量中填充物均匀度的非破坏性检测。本文的研究促进图像处理技术的在工业检测方面的应用更加广泛,同时也为蚕丝被工艺质量中厚薄均匀度的检测开辟新思路。
With the development of modern computer technology especially the development ofimage manipulation technology; computer technology has become the research hotspot in manyfields. Is applied widely on many fields such as automatic target recognition, intelligenttechnology, biomedicine, medical image analysis, remote sensing and space exploration. And alot of researching results produced, these studies have pushed the new development in everysubject.
     The wadding cover evenness detection is one of the most important areas in the detection ofthe quality of silk quilts. At present, the detection of the quality of silk quits mainly rely onhuman experience. And this traditional approach has become the bottleneck of textiles’ rapiddesign and production. Therefore, in order to replace artificially detection, it is boththeoretically and practically significant to develop an effective system which can detect silkquilts automatically. Based on this background, this paper presented a study regarding to thenondestructive examination of the homogeneous degree of the fill for silk quilts based on imageprocessing technique.
     This paper analyses and studies the existing evenness detection methods of silk quits andthe existing image processing methods. According to the computational methods of the weightof silk(H) and the homogeneous degree of the fill for silk quilt(J) in the state principal of thesilk quilts(GB/T24252-2009), evenness detection of wadding cover from the view of imageprocessing was discussed. The calculating formula of Thick and thin was given and algorithmmodel was established. The research points and achievements are listed as follows:
     (1) In the system. It utilizes CCD for gathering digital image of silk quilts, and thenprocesses those images by computer image processing technology; this method can reducenoises and the correction of the geometrical distortion and imaging non-uniformity of theprojected image; then the gray scale of pixels are acquired in terms of gray distribution.
     (2) Research on Digitalize Imaging non-uniformity Correction Methods, The limitation of imaging condition in actual environment causes sometimes the non-uniform background lighton the images when capturing. To resolve this problem, a new method for the correction ofunevenness elimination technique based on wavelet transference is proposed. Using nonlinearwavelet transform for obtaining distribution characteristic of background light. Experimentresults demonstrated that the method achieved a satisfactory effect of removing the unevenillumination.
     (3) In order to improve the efficiency and veracity of silk quilt evenness detection based onimage processing. A new method that is based on optical theory and image processing has beenproposed for analyzing the relationship between pixel gray values, the optical density in animage and weight of silk(H). The homogeneous degree of the fill for silk quilt (J) can bedetermined by using pixel gray values replace weight to calculate deviation. After that, thesedata are classified based on the Chinese National Standards (GB) by H and J. To compare withtraditional method, it can build the Non Destructive Testing (NDT), which has been proved tobe a practical method
     This paper presented a study regarding to the nondestructive examination of thehomogeneous degree of the fill for silk quilts based on image processing technique. A methodthat is based on optical theory has been proposed for analyzing the weight of the fillingparameter measurement. The homogeneous degree of the fill for silk quilt can be determined byusing pixel gray values replace weight to calculate deviation. This study has an importantpractical significance for image processing technology and the development of thenondestructive examination of the homogeneous degree of the fill for silk quilts.
引文
[1]牛艳红.《蚕丝被》新国标正式实施跟踪报道[J].纺织服装周刊2010,4.
    [2]中华人民共和国国家质量监督检验检疫总局,GB/T24252-2009蚕丝被[S],中华人民共和国国家标准,中国标准出版社,2009-06-19.
    [3]曹渭芳,徐俊荣.浅谈标准GB/T24252—2009《蚕丝被》[J].中国纤检,2010,5.
    [4]冈萨雷斯(美)等著.数字图像处理(英文版)[M].北京:电子工业出版社.2011.
    [5]邹丽君.基于图像处理的电缆绝缘层厚度测量的研究[D].青岛:青岛科技大学,2009,6.
    [6]曾奇波.基于图像处理技术的大米质量实时检测系统研究[D].湖南:湖南科技大学,2009,5
    [7]郑苹.基于数字图像处理的颗粒细度检测系统的改进[D].武汉:武汉科技大学,2005,4
    [8]周平生.基于图像处理的精密测量关键技术研究[D].西安:西安电子科技大学,2010
    [9]刘文耀.数字图像采集与处理[M].北京:电子工业出版社,2007
    [10]李俊.机器视觉照明光源关键技术研究[D].天津理工大学,2007
    [11]张道勇.基于线阵CCD的大幅面扫描技术研究[D].广东工业大学,2005
    [12]沈庭芝,方子文.数字图像处理及模式识别[M].北京理工大学出版社,1998
    [13]刘兴,刘庆祥.一种彩色图像转换为灰度图像的算法[J].现代电子技术,2007,6:134-136
    [14]王益艳.图像去噪算法的研究[D].西安:陕西师范大学,2008,1-5.
    [15]雷浩鹏.数字图像去噪算法研究及应用[D].长沙:长沙理工大学,2010,3
    [16]Clarke T A. The development of camera calibration methods and models. Photogram metric Record,1998,16(91):51-66
    [17] Rocchini D,Rita A D. Relief effects on aerial photos geometric correction [J].Applied Geography,2005,25:159-168.
    [18]廖士中.一种光学镜头摄像机几何畸变的校正方法[J].中国图像与图形学报,2000(7):593–596.
    [19]万峰,杜明辉.数码相机设计中图像几何畸变校正的实现[J].计算机工程,2005,31(17):191-192
    [20]马广彬,章文毅,陈甫.图像几何畸变精校正研究[J].计算机工程与应用,2007,43(9):45-48
    [21] Sakamoto T. Software Pixel Interpolation for Digital Still Cameras Suitable for a32-bit MCU. IEEETrans. Consumer Electronics,1998,44(4):1342-1352
    [22] D Zmura M,Iverson G.Color Constancy. Basic Theory of Two-Stage Linear Recovery of SpectralDescription for Lights and Surfaces[J]. J Opt Soc Am,1993,A10(10):2148-2165
    [23]梁琳,何卫平,雷蕾等,光照不均匀图像增强方法综述[J].计算机应用研究,2010,27(5).6-9
    [24] J.Kim.J.Fessler,Intensity-based image registration using robust correlation coefficients[J].IEEE Trans.On Medical Imaging,2004,23(11):1430—1444.
    [25]V.Vigneron,T.Q.Syed,G.Barlovatz-Meimon,Adaptive filtering and hypothesis testing: Application tocancerous cells detection.V.Vigneron et al./Pattern Recognition Letters,2010,31:2217-2219
    [26]孙忠贵.数字图像光照不均匀校正及Mat lab实现[J].微计算机信息,2008,24(4-3):313-314
    [27] Soille P. Morphological image analysis: principle and applications.Springer Press,1999.
    [28]阮秋琦,阮语智.数字图像处理[M].北京:电子工业出版社,2006.
    [29]罗海霞,刘斌,龙永红等,同态滤波在光照补偿中的应用[J].湖南大学学报,2008,22(5):24-27
    [30]王宇,龙兴武.基于小波的不均匀光照的校正[J].光学技术,2005,31(5):726-728
    [31]赵素娜,艾矫燕,李世晓.小波变换在图像照度不均校正中的应用[J].计算机技术与自动化,2010,29(1):99-101
    [32]杨欢.应用于工业检测的光照不均匀图像的校正[J].微计算机信息.2009,25(7-3):244-245.
    [33]杨杰,付忠良,阮波.照度不均匀图像的快速自适应灰度修正[J].计算机应用,2005,25(3):23-26
    [34]Wei Zhou,Chandra Kambhamettu. A unified framework for scene illuminant estimation[J]. Image andVision Computing,2008,26:415-429
    [35]郑军,徐春广,肖定国等.数字图像中照度不均匀校正技术研究[J].北京理工大学学报,2003,23(3):3-4
    [36]视觉检测系统中亮度不均匀背景的一种去除方法[J].机床与液压,2003,2:228-229.
    [37]程培英,沈会良.一种光照不均匀图像的恢复增强方法[J].计算机应用与软件,2008,25(10).
    [38]孙燮华.数字图像处理原理与算法[M].机械工业出版社,2010,8
    [39] Kenneth R. Castellan著;朱志刚,石定机,林学阎等译.数字图像处理[M].电子工业出版社,2011.58-66
    [40] Banghaln J.A,Marshall S. Image and signal processing with mathematical morphology [J]. Electronics&Communication Engineering Journal,1998,6:117-128.
    [41]王义国,医学图像自动特征提取的研究[D].吉林:长春理工大学,2008,4
    [42]程远,基于小波纹理分析的彩色车牌定位算法研究[D].西安:西安科技大学,2010,6
    [43]秦和平,邢宝妹,周佩琴等.“光密度”标准名称、量符号及其使用规范探讨[J].科技与出版,2006,1.
    [44]章毓晋.图像处理和分析[M].北京:清华大学出版社,1999,187-191.
    [45]Cuesta N,Martinez A,Cuttitta F,et al Identification of adrenomedullin in avian type II pneumocytes:increased expression after exposure to air pollutant s [J].J Histochem Cytochem,2005,53(6):7732780.
    [46]胡学龙,许开宇.数字图像处理[M].北京:电子工业出版社,2006,152-165.
    [47]李枫.图像分析中光密度参数物理意义的正确理解和使用[J].解剖学杂志,2009,32(2):271-274
    [48]王树党.图像分析系统中光度学参数-灰度与光密度的应用[J].山西医科大学学报,2003,34(5):462
    [49]汤耀法,胡江元,李宽俨.光密度和积分光密度[J].上海医科大学学报,1997,24(2).
    [50] Mat kowskyj KA,Cox R,Jensen R. T,et al. V Quantitative immunophistochmeistry by measuringcumulative signal strength accurately measures receptor number[J]. J Histochem Cytochem,2003,51(2):205-214
    [51]吕宏生,朱庆生,王军.全自动显微镜及图像分析系统处理免疫组化图像[J].中国体视学与图像分析,2004,9(1):37-40
    [52]黄锐,PCR凝胶成像分析算法研究[D].天津:河北工业大学,2009.
    [53]李海燕,数字图像处理技术在骨髓成分识别中的应用[D].南京:南京航空航天大学,2006.
    [54]李涛,范妤,刘芳.免疫组织化学图像光密度分析的标准化方法[J].解剖学杂志,2008,31(5):727-728
    [55]求是科技. Visual C++数字图像处理典型算法及实现[M].北京:人民邮电出版社,2006,6.
    [56]冯伟兴,唐墨,贺波. Visual C++数字图像模式识别技术详解[M].北京:机械工业出版社,2010,

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700