捆扎线材图像处理的识别方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
目前,国内大多数钢材生产厂家都采用人工方法来计量捆扎线材的根数,效率低下,劳动强度高,计数误差大,而引进全自动生产线,成本较高,因此,他们迫切需要低廉的自动计数仪。从上世纪90年代初,国内开始从事应用计算机视觉的方法进行线材的在线自动计数研究,取得了一定的成果,但还处于理论研究阶段,没有出现成熟的产品。本课题是北方工业大学承担的北京市教育委员会科学基金的捆扎线材图像测量计数仪的子课题。该计数仪的研制不仅具有一定的理论意义,同时还有良好的市场前景。
     课题仍然采用计算机视觉的方法来尝试线材的在线计数,主要研究内容是系统的软件部分,包括图像的采集、预处理、物体的分割和识别并且计数。根据所处理图像的实际特点,文中提出了一种新的基于类圆的粘连体分割方法和基于统计模式识别的类圆识别方法,由于该算法主要的运算为加法、减法和逻辑运算,从而保证了算法的实时性。对一幅大小为640~*480的图像,整个处理耗时小于1秒,完全能满足实际生产要求。该算法对图像的二值化效果要求较高,当物体间的缝隙在二值化后能部分或全部判定为背景,即粘连的物体在二值化后能有明显的凹陷时,识别率很高,误差几乎可以为零。反之,则误差会上升,一种可行的改进方案是利用物体的边缘信息,文中也进行了这方面的尝试,受时间限制,只进行了简单的试验。虽然引入边缘信息能减少可能的误差,但是如果物体内部灰度不均匀,则要考虑由此而造成的伪边缘信息对分割的影响,同时,结合边缘信息后,处理速度也将会有所降低。
     文中的研究大部分时间是针对用数码相机在施工现场采集的图像设计的,仅在末期用了较少的几根钢筋进行在线测试,因此,仅就算法而言,还有许多具体的研究、工作去调试、完善和改进,如果再进一步结合嵌入式硬件和生产管理的需要,形成一个较成型的产品,则需要做更多、更深入的研究。
     文中除对算法进行了描述外,也给出了算法的应用效果,并且简要地讨论了引起误差的几个因素。
     本文在查阅大量的文献基础上(限于作者查找的资料范围,没有见到国外有关这方面的文献),提出了一种适合线材计数的分割和识别方法,并就进一步的改进进行了一些有益的探索,为日后的计数仪研制打下了坚实的基础。
At present, almost all steel factories count bundled bar one by one by workers, it is laborious, low effective, and may cause high error. If these factories would import foreign automatic product lines, they will pay much and improve the cost of steel bar dramatically. So, these manufactories desire a cheap, applied counter. From the first of 1990s, by using computer vision, studies of this area had been begun. Although a bit progress had been got since then, there is much to do if it is used at spot in factory. This study is sub study of counter of bundle bar by image processing, taken on by North China University of Technology, sponsored by education committee of Peking city. This study may do some research on theory and the product will be a good future.
    In this paper, the author tries to count steel bars of each bundle by making use of computer vision. The main research includes the following area: image acquisition, image pre-processing, image segmentation, object recognition. An new segmentation method based on quasi-circular assumption and an new object recognition method based on scanning are present. Owing to the simple addition, subtraction and logic operation, these two methods have real time property. The total CPU time is less than 1 second for an 640*480 pixels image, this can meet on line counting. Both two methods require a good binary image, if there exist concave, the aggregated objects will be segmented and recognized correctly and the error is lower, otherwise, it may give err result. Considering the edge information will give robust segmentation, but the information may contain noise when the object is strongly non-uniformity and the speed decreases.
    The author pay much time to test the arithmetic on the image photographed by digital camera, so there are much works to do to apply this software in practice.
    In this paper, not only do we explain our new algorithm, but also we test them by real digital photo, man-made image, video image. Furthermore, we compute and discuss the error and its factors. After consulting many references, this paper presents a fast method to count the steel bar of one bundle.
引文
[1] 杨枝灵,王开,等.Visual C++数字图像获取处理及实践应用.北京:人民邮电出版社,2003.73~82 504~573
    [2] 张益贞,刘滔.Visual C++实现MPEG/JPEG编解码技术.北京:人民邮电出版社,2002.10~168
    [3] 周长发.精通Visual C++.net图像处理编程.北京:电子工业出版社,2002.1~153
    [4] 何斌,马天予,王运坚,等.Visual C++数字图像处理.北京:人民邮电出版社,2001
    [5] 夏良正.数字图像处理.南京:东南大学出版社,1999.1~37
    [6] Kenneth R.Castleman.数字图像处理.朱志刚等译.北京:电子工业出版社,2002.1~28
    [7] Rafael C.Gonzalez,Richard E.Woods.Digital Image Processing(Second Edition).北京:电子工业出版社,2003
    [8] 马颂德,张正友.计算机视觉——计算理论与算法基础.北京:科学出版社,1997.1~9
    [9] 贾云得.机器视觉.北京:科学出版社,2000
    [10] 章毓晋.图象理解与计算机视觉.北京:清华大学出版社,2000
    [11] 章毓晋.图象处理与分析.北京:清华大学出版社,1999
    [12] 章毓晋.图象分割.北京:科学出版社,2001
    [13] 崔屹.图象处理与分析——数学形态学方法及应用.北京:科学出版社,2000
    [14] 沈福元.计算机图像处理在线钢筋计数新技术通过鉴定.上海金属24卷:24
    [15] 朱常青,冯筱林,杨建国.螺纹钢筋(棒材类)的精确计数方法.上海大学学报(自然科学版)1998,Vol4,No 5
    [16] 王培珍,杨维翰,沈玉梁.基于融合技术的棒材定支数图像识别.合肥工业大学学报(自然科学版),2003,Vol26,No 2
    [17] 张琳,芩豫皖,杜培明.基于VC的棒材自动计数方法的研究与应用.工业控制计算机,2003,16卷,第3期
    [18] 王爱民,沈兰荪.图像分割研究综述.测控技术 2000,19卷第5期:p1-6
    [19] 应勤.Photoshop7.0入门与提高.北京:清华大学出版社,2002
    
    
    [20] 谷口庆治.数字图象处理(应用篇).北京:科学出版社,2002
    [21] 栾新,朱铁一.不规则类圆形目标图象识别新策略.中国图象图形学报,1999,4(3),A:202~206
    [22] 赵立初,施鹏飞.基于动态阈值选择和细化算法的角膜细胞轮廓抽取.上海交通大学学报,1998,32(9)67~69
    [23] 王浩军,郑崇勋.彩色血液细胞图像的自动分割方法研究.生物医学工程学杂志 2002,19(2):251—255
    [24] 王金涛,刘文耀.流域分割算法在细胞图像分割中的应用.西南交通大学学报,2002,37(3):290~294
    [25] 王浩军,郑崇勋.基干自适应多尺度的血液细胞图像阈值分割方法研究.西安交通大学学报,2001,35(4):390~397
    [26] 苑纬琦,等 血细胞计算机自动计数仪.医疗装备,1997,10(2):8~10
    [27] 苑纬琦,等 血细胞数的图象检测方法研究,仪器仪表学报,1999,20(3):305~307
    [28] 易东,李辉智.细胞图像的斑点缝隙噪声消除方法研究.ACTA ACADEMIAE MEDICINAE MILITARIS TERTIAE ,1999:285~287
    [29] 陆建峰,杨静宇.重叠细胞图像分离算法的设计.计算机研究与发展,2000,37(2):228~232
    [30] 刘相滨,邹北骥.一个微生物细胞图像自动判读系统的实现.计算机工程与应用,2002,(7):125~127
    [31] 王昕,曲波.一种不规则封闭形状的轮廓跟踪算法.南京航空航天大学学报,1996,28(4) :580~583
    [32] 苑纬琦,张田文.一种新的堆积颗粒图像边缘检测方法.哈尔滨工业大学学报,2001,33(4) :454~458
    [33] 赵雪春,戚飞虎.基于可变形模型及像素相似性统计的自动图像分割.红外与毫米波学报,2000,19(1):33~37
    [34] 黄敬雄,谢维信.基于模糊神经网络的目标识别.西安电于科技大学学报,1997,24(1):72~77
    [35] 张新明,沈兰荪.基于特征距离的阈值法及其在眼科图象分割中的应用.中国图象图形学报,2001,6(2A):159~163
    [36] 金立左,夏良正.图象分割的自适应模糊阈值法,中国图象图形学报,2000,5(5A):390~395
    
    
    [37] 刘宏兵,杨万海.图像小波边缘提取中阈值选取的一种自适应方法.西安电了科技大学学报(自然科学版),2000,27(3):294~296
    [38] 许东,袁晓辉.一种基于可变形模型的图像分割算法.红外与毫米波学报,2002,21(1):49~53
    [39] 章毓晋.中国图像工程及当前的几个研究热点.计算机辅助设计与图形学学报,2002,14(6):489~500
    [40] 韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术,2002,24(6):91-94
    [41] 赵荣椿,等.图象分割技术进展.中国体视学与图象分析,1998,3(2):121-127
    [42] 唐慧明.二值图像颗粒分割及其应用.计算机工程与科学,1994,3:1~3
    [43] 齐国生,叶丹,洪强宁,等.基于圆形假设和多边形近似的细胞图像分解.计算机工程与应用,2003.16:75~85
    [44] 王磊,莫玉龙,戚飞虎.基于Canny理论的边缘提取改善方法.中国图象图形学报,1996,Vol1,No3:191!~193
    [45] 刘文萍,吴立德.图象分割中阙值选取方法比较研究.模式识别与人工智能.1997,9:271~277
    [46] 周群,胡光锐.基于模板覆盖法的钢筋在线计数方法.上海交通大学学报,1999,Vol 33,No11:1462~1464
    [47] 王培珍,杜培明,周雷.基于融合技术的螺纹钢打捆端面图像分割方案探讨.安徽工业大学学报,2003,Vol 20,No 1:62~65
    [48] 章毓晋.图象分割评价技术分类和评价.中国图象图形学报,1996,Vol 1,No 2:151~158
    [49] 吴一全,朱兆达.图像处理中阈值选取方法30年(1969~1992)的进展(一).数据采集与处理,1993,8(3):193~201
    [50] 吴一全,朱兆达.图像处理中阈值选取方法30年(1969~1992)的进展(二).数据采集与处理,1993,8(4):261~281
    [51] 侯格贤,毕笃彦,吴成柯.图象分割质量评价方法研究.中国图象图形学报,2000,Vol 5(A),No 1:39~43
    [52] 罗希平,田捷,诸葛婴,等.图像分割方法综述.模式识别与人工智能,1999,Vol 12,No3:300~312
    [53] Zhang Y J.A survey on evaluation methods for image segmentation. Pattern Recognition,1996, 29(8): 1335~1346
    
    
    [54] J.Canny. A Computational Approach to Edge Detection. IEEE Trans.PAMI-8,1996,Vol PAMI-8,No 6,679~698
    [55] Wang W X.. Binary Image Segmentation and Classification of Aggregates Based on Polygonal Approximation and Classification of Concavities[J].Pattern Recognition ,1998:31(10)1503~1524
    [56] Guimaraes L V, Suizm A A, Maeda J. A New Automatic Circular Decomposition Algorithm Applied to Blood Cell Images[C].In: Proceedings of IEEE International Symposium on Bio-Informatics and Biomedical Engineering, Arlington, VA, USA, New York: IEEE 2000:277~280
    [57] RACHID.D. Regnlarization, Scale-Space, and Edge Detection Filters. Journal of Mathematical Imaging and Vision ,1997,7:291~307
    [58] A. Amin. A Document Skew Detection Method Using the Hough Transform. Pattern Analysis & Applications (2000)3:243-253
    [59] H. Utkui, H. Koksel. Classification of wheat grains by digital image analysis using statistical filters. Euphytica, 1998(100): 171~178.
    [60] Kittler J, Illingworth J. Mininum error thresholding [J] Pattern Recognition 1986, 19:41~47
    [61] GUANG DENG. Differentiation-Based Edge Detection Using the Logarithmic Image Processing Model. Journal of Mathematical Imaging and Vision ,1998(8):161~180
    [62] Theera-Umpon, Nipon, Gader, Paul D.Automated white blood cell counting via classification-free granulometric methods. Proceedings of SPIE-The International Society for Optical Engineering.,1999,3646.-260-269
    [63] Zikuan Chen, Yang Tao, Xin Chen, and Carl Griffis. Wavelet-based adaptive thresholding method for image segmentation Optical engineering.,2001,40(5):-868~874
    [64] Wu, H.-S.; Gil, J.; Barba, J .Optimal segmentation of cell images .lEE Proceedings: Vision, Image and Signal Processing.,1998,145(1).-50~56
    [65] Tabb, Mark; Ahuja, Narendra .Multiscale image segmentation by integrated edge and region detection. IEEE Transactions on Image Processing.,1997,6(5).-642~654
    [66] TehChuan Chen, KuoLiang Chung. An Efficient Randomized Algorithm for Detecting Circles Computer Vision and Image Understanding,2001,83(2).-172~191
    [67] Nipon T, Counting white blood cells using morphological granulometries Journal of Electronic Imaging,2001,9(2).-170~177
    [68] P J.H. Bronkorsta M.J.T. Reinders, E.A. Hendriks. On-line detection of red blood cell shape using deformable templates. Pattern recognition letters ,2001,21(5).-413~424
    
    
    [69] Illingworth J,Kittler.A Survey of the Hough Transform. Computer Vision,Graphics,and Image Processing,1988,44:87~116
    [70] Sahoo P K, et al. A Survey of thresholding techniques.CVGIP,1998,41:233~260
    [71] Pal N R,Pal S k.. A Review on image segmentation techniques. Pattern Recognition,1993,26:1277~1294
    [72] Weszka J S. A survey of threshold selection techniques. CGIP,1978,7:259~265
    [73] Davis L S. A survey of edge detection techniques.CGIP,1975,4:248~270
    [74] Fu K S,Mui J K. A survey on image segmentation. Pattern Recognition,1981,13:3~16
    [75] Zhang Y J.Segmentation evaluation and comparsion:a study of various algorithms.SPIE, 1993,2094:801~812
    [76] Chalana V,Kim Y. A Methodology for Evaluation of Boundary Detection on Medical Images. IEEE Trans on Medical Imaging,1997,16(5):642~652
    [77] 栾新.原木材积计算机视觉检测系统的研究:[博士学位论文].哈尔滨:哈尔滨工业大学,1997
    [78] 陆志敏.玻璃瓶罐外形尺寸的计算机视觉检测:[硕士学位论文].广西:广西师范大学,2000
    [79] 魏晓燕.基于数字图像处理的椭圆型孔径自动检测系统:[硕士学位论文].南京:南京师范大学,2002
    [80] 刘立波.数学形态学在二值图象处理与分析中的研究及应用:[硕士学位论文].西安:西北大学,2002
    [81] 边肇祺,张学工,等.模式识别(第二版).北京:清华大学出版社,2000

© 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