基于计算机视觉的铝塑泡罩产品检测方法研究
|
摘要
计算机视觉在实时控制领域的应用是随着计算机硬件技术的发展和对图像处理的深入研究而逐渐发展的。本课题的研究内容是设计一套基于计算机视觉的铝塑泡罩产品包装实时检测的处理方法。以图像处理技术为基础，结合视觉技术、模式识别技术来检测出漏装、碎片、异物等不合格铝塑泡罩包装产品。
分析了利用计算机视觉进行铝塑泡罩包装产品的实时检测的硬件要求。通过现场实验确定了摄像机的要求、光源环境、图像采集卡的性能要求，设计了一套合适的计算机视觉硬件系统，并根据系统要求设计了系统软件。研究了适用于产品包装检测的图像处理算法及方案。
由于铝塑泡罩包装产品反射、折射较强，另外不合格产品中存在裂纹、发丝等异物需要识别，图像检测困难。采用线性灰度变换等方法对图像进行增强，使图像的对比度扩展。采用改进型中值滤波法和多图像平均法，在去除了噪声的基础上尽可能的保护了边缘。边缘提取是图像处理的重点和难点。采用Sobel算法对图像进行处理，使图像边缘部分突出。通过二值化将不同灰度区区分出来，这样有利于图像的特征提取。
在此基础上，利用药片的属性来进行图像分析。分别计算各位置上药片的面积A和周长值P，判断是否和理论值基本一致。然后利用C＝P~2／A来计算C是否接近于4π。通过与标准模板进行对比判断，可以识别药片是否有空泡、漏装、碎片、是否存在异物或破损等情况。根据以上图像分析结果得出产品包装是否合格。
The application of computer vision in real time control develops with the development of computer hardware technology and the profound research on picture processing. The research carried out here is to design a real time detecting program based on computer vision for aluminum-plastic foamed mask packaging products. Based on the picture processing technology, the vision technology, and the pattern recognition technology, this program helps detect unqualified foamed mask packaging products made of aluminum-plastics, like those with omission assemblage, fragments, and foreign bodies.
Analysis is done on the required hardware for the application of computer vision in real time detection over aluminum-plastic foamed mask packaging products. On-the-spot experiments have determined the requirements for the camera, the light source environment, and the properties of the picture collector, designed a computer vision hardware system, and the system software required for the hardware system. A picture processing algorithm and a program are worked out for package detection.
The vision processing is made difficult by the comparatively strong refractiveness, reflectivity, the crazes and foreign bodies like hair existing in unqualified aluminum-plastic foamed mask packaging products. The linear darkness transform method is used to increase the contrastiveness of pictures; the improved mid-value filtering algorithm and local average method are adopted to protect the edge as much as possible on the basis of noise elimination. The edge extraction is the focus and trouble of picture processing. By using the Roberts gradient method, Laplace algorithm, and Sobel algorithm, the picture is processed and the picture edge is highlighted. To suit the characteristic extraction of pictures, the dichotomy is used to differentiate varied darkness regions.
On this basis, the characteristics of tablets are used for picture analysis. The area (A) and the perimeter (P) of the tablets at each position are calculated respectively to see whether they agree with the theoretical values. Then the value of C is calculated by using the function C=P2/A to see whether it approximates 4 . Compare the value with that in the standard mother plate, unusual things like hollow foams, omission assemblage, fragments, foreign bodies or damages in the package of tablets can be detected. Results obtained from this picture analysis determine whether the product package is qualified.
分析了利用计算机视觉进行铝塑泡罩包装产品的实时检测的硬件要求。通过现场实验确定了摄像机的要求、光源环境、图像采集卡的性能要求，设计了一套合适的计算机视觉硬件系统，并根据系统要求设计了系统软件。研究了适用于产品包装检测的图像处理算法及方案。
由于铝塑泡罩包装产品反射、折射较强，另外不合格产品中存在裂纹、发丝等异物需要识别，图像检测困难。采用线性灰度变换等方法对图像进行增强，使图像的对比度扩展。采用改进型中值滤波法和多图像平均法，在去除了噪声的基础上尽可能的保护了边缘。边缘提取是图像处理的重点和难点。采用Sobel算法对图像进行处理，使图像边缘部分突出。通过二值化将不同灰度区区分出来，这样有利于图像的特征提取。
在此基础上，利用药片的属性来进行图像分析。分别计算各位置上药片的面积A和周长值P，判断是否和理论值基本一致。然后利用C＝P~2／A来计算C是否接近于4π。通过与标准模板进行对比判断，可以识别药片是否有空泡、漏装、碎片、是否存在异物或破损等情况。根据以上图像分析结果得出产品包装是否合格。
The application of computer vision in real time control develops with the development of computer hardware technology and the profound research on picture processing. The research carried out here is to design a real time detecting program based on computer vision for aluminum-plastic foamed mask packaging products. Based on the picture processing technology, the vision technology, and the pattern recognition technology, this program helps detect unqualified foamed mask packaging products made of aluminum-plastics, like those with omission assemblage, fragments, and foreign bodies.
Analysis is done on the required hardware for the application of computer vision in real time detection over aluminum-plastic foamed mask packaging products. On-the-spot experiments have determined the requirements for the camera, the light source environment, and the properties of the picture collector, designed a computer vision hardware system, and the system software required for the hardware system. A picture processing algorithm and a program are worked out for package detection.
The vision processing is made difficult by the comparatively strong refractiveness, reflectivity, the crazes and foreign bodies like hair existing in unqualified aluminum-plastic foamed mask packaging products. The linear darkness transform method is used to increase the contrastiveness of pictures; the improved mid-value filtering algorithm and local average method are adopted to protect the edge as much as possible on the basis of noise elimination. The edge extraction is the focus and trouble of picture processing. By using the Roberts gradient method, Laplace algorithm, and Sobel algorithm, the picture is processed and the picture edge is highlighted. To suit the characteristic extraction of pictures, the dichotomy is used to differentiate varied darkness regions.
On this basis, the characteristics of tablets are used for picture analysis. The area (A) and the perimeter (P) of the tablets at each position are calculated respectively to see whether they agree with the theoretical values. Then the value of C is calculated by using the function C=P2/A to see whether it approximates 4 . Compare the value with that in the standard mother plate, unusual things like hollow foams, omission assemblage, fragments, foreign bodies or damages in the package of tablets can be detected. Results obtained from this picture analysis determine whether the product package is qualified.
引文
[1]郑南宁，计算机视觉与模式识别，国防工业出版社，1998
[2]王天珍，计算机视觉研究进展，武汉汽车工业大学学报，VOL．20，NO．1，FEB．1998
[3]Marr D．视觉计算理论。姚国正等译。北京：科学出版社，1988
[4]Rosenfeld A.Computer Vision—Basic Principle.ProC.of.IEEE,1988(8):863-868
[5]Aloimonos Y,Rosenfeld A Response to"Ignorance,Myopia,and Naviete in Computer Vision System"by R.C.Jain and T.O.Binford.CVGIP IMAGE UNDERSTANDING,1991,53(1):120-124
[6]Bajcsy R Active Perception.Proc.of IEEE,1988,76(8):996-1005
[7]Ballade D H,Brown C M.Principles of Animate Vision CVGIP IMAGE UNDERSTANDING,1992.56(1):3-21
[8]Thompson W B.Qalitative Constraints for Structure from Motion.CVGIP IMAGE UNDERSTANDING.1992,56(1):69-77
[9]王润生，图像理解，国防科技大学出版社，1995
[10]韦穗，计算机视觉，机器人，1992(4)
[11]马颂德、张正友，计算机视觉—计算理论与算法基础，科学出版社，1998
[12]戚飞虎等，模式识别与图像处理，上海交通大学出版社，1990
[13]相阿荣、王一鸣，利用色度法识别杂草和土壤背景物，中国农业大学出版社，2000，5(4)：98-100
[14]金伟其，现代城市交通流量的三维图像检测技术，红外与激光工程，Dec．1997
[15]王三武等，CCD电子抄表系统及图像的采集，武汉汽车工业大学学报，Vol．22 No．6 Dec．2000
[16]洪华军等，指纹图像自动识别系统预算法的研究，电子技术应用，2001年第一期
[17]赵红颖等，基于计算机视觉的发动机缺陷检测系统的应用，光学精密工程，Vol．8．No．3 Jun，2000
[18]潘俊民等，基于计算机视觉的自动浇注系统，铸造技术，2/1998
[19]王积分、张新荣，计算机图像识别，中国铁道出版社，1988
[20]屈志毅等，印鉴自动识别系统中图像处理与识别的方法研究，甘肃科学学报，Vol．13 No．1 Mar．2001
[21]胡均安等，实时识别系统技术在片式元件编带机中的应用，武汉汽车工业大学学报，Vol．22．No．6 Dec．200
[22]荆仁杰等，计算机图像处理，浙江大学出版社，1990
[23]蒋加伏等，计算机视觉系统研究中存在的问题及解决思路，长沙交通学院学报，Vol．15 No．1 Mar 1999
[24]CHIU M Y.Is Industry Ready for Machine Vision, Perspective in Computer,Academic Press[C].New York:1989,24:227-230
[25]JAIN R C.Ignorance,Myopia,Naivate in Computer Vision System[R].CVGIP,Image Understanding,1991,53(1):112-117
[26]MCCLAMROCK R.Marr's Three Levels:A Re Evaluation[J].Minds Mach.1991,1(2):185-196
[27]PAVLIDIS T.Why Progress in Machine Vision is So Slow[j] Pattern Recognition Letter,1992,13(4):221-225
[28]ALOIMONOS Y.Robust Computation of Instrisic Images from Multiple Cues[J].Inc.Publisher,1988,1:115-225
[29]NAVON D.Forest before Trees:The Precedence of Global Feature in Visual Perception[J].Cognitive Psychology,1997.9:353-383
[30]CHEN L.Topological Perception A Challenge to Computional Approaches to Vision[M].Elsevier Science Publishers,1989.317-329
[31]GIBSON J J.The Ecological Approach to Visual Perception[M].Houghton Mifflin,1979
[32]BALLARD H D.Computer Vision[M].Prentice Hall,Inc:1982
[33]BAMEA I D.A Class of Algorithms for Fast Image Registration[J].IEEE Trans.on computers,1972(2)
[34]刘效静，汽车牌照自动识别技术研究，南京，南京航空航天大学学报，1998，30(5)
[35]姚庆栋等，图像编码基础，人民邮电出版社，1984
[36]K N Plataniotis,D Androutsos,A N Venetsanopoulos.Content-based color image filters.Electronic Letters,1997;33:212-203
[37]陈永彬等，数字信号处理，南京工学院出版社，1987
[38]KUANG Yu,YOU Zhi-sheng etc,Multi-Targets detection and segmentation of Moving Sperm,Jounal of Image and Graghics,1999,5:405-408(ch)
[39]李树涛、王耀南，图像椒盐噪声的非线性自适应滤除。中国图像图形学报。2000，Vol．15，No．12．2000，999-1001
[40]孙仲康等，数字图像处理及其应用，国防工业出版社，1988
[41](美)W。K。普拉特，数字图像处理学，科学出版社，1984
[42][美]A。罗森菲尔德，数字图像分析，科学出版社，1987
[43]Kenneth.R.Castleman著，朱志刚等译，数字图像处理，电子工业出版社，1998
[44]周新论、柳健等，数字图像处理，国防工业出版社，1986
[45]钟玉琢等，机械人视觉技术，国防工业出版社，1994
[46]Davis R O,New Measures of Sperm Motion.J Andrology,1992,13(2):87-90
[47]lluang T.S.Computer Vision Needs More Experiment and Applications.CVGIP:IU,Jan 1991,53(1)125-126
[48]Canny J.A computational approach to edge detection.IEEE Trans.On PAMI 1986,679-698
[49]Mallat S G,Zhzng S.Charaterization of signals from Multi-scale Edages.IEEE T—PAMI,1992,14(7):710—732
[50]Daubechies I.Orthonormal Bases of Compactly Supported Wavelets Communication on Pure and Applied Mathematics,XLI,1988,909—996
[51]Kapur J N,Sahoo P K,Wrong A.A new method for gray—level picture Thresholding using the entropy of the histogram.Computer Vision Graphics Image Process,1985,29(3):273—285
[52]Sahoo P K,Soltani,Wrong A,Chen Y C,A Survey of Thresholding Techniques.Computer Vision Graphics Process,1988,41(2):233—260
[53]Cinque L,Levialdi S,Rosenfield A,Fast pyramidal algorithum for image thresholding,Pattern Recognition,1995,28(5):901—906
[54]孙洪波等，实时动态图像检测系统研究，测控技术，1997年第八个五年计划6卷第2期
[55]魏武等，车牌识别的分布式结构处理方法研究，长沙交通学院学报，Vol．16 No．2 June 2000
[56]冯月霞等，一种基于视频图像处理的识别系统，电子技术，2001年第4期
[57]李玉山等，彩色图像的边缘检测研究，模式识别与人工智能，Vol．5 No．2 June 1992
[58]刘勇等，图像差异的分析与识别，复旦学报(自然科学版)，Vol．39 No．5 Oct，2000
[59]程文娟等，工业物料自动识别中主色调特征的提取，沈阳师范学院学报，Vol．19 No．3 Jul 2001
[60]罗西平，田捷等，图像分割方法综述，模式识别与人工智能，1999，9(3)：300-312
[61]付忠良，基于图像差距度量的阈值选取方法，计算机研究与发展，Vol．38 No．5 May 2001
[62]王思贤等，低对比度图像目标分割的研究，武汉大学学报(自然科学版)，Vol．46 No．5 Oct 2000
[63]冯丽爽，CCD传感器在人体运动图像检测系统中的应用，仪表技术与传感器，2001年第5期
[64]付忠良，图像阈值选取方法---Otsu方法的推广，计算机应用，2000，5(5)：37—39
[65]胡玉僖等，具有数字图像处理功能的运动分析系统，光学技术，No．1 Jan．1998
[66]杨平先等，基于分形的图像边缘检测研究，电讯技术，Vol．38 No．4 Aug．1998
[67]张文淘，高速运动可视多目标精确检测研究，电子与信息学报，Vol．23 No．4 Apr．2001
[68]Otsu.A threshold selection method from gray-level histogram.IEEE Trans on SMC-9,1979,9(3):62-66
[69]李玉山，物体表面缺陷模型及检测方法的研究，西安电子科技大学学报，1988，15(4)：82-91
[70]陈斌等，车牌号码颜色提取搜索方法，计算机应用，Vol．21 No．4 Apr．2001
[71]黄信新等，实时图像轮廓抽取算法研究，计算机应用，Vol．21 No．3 Mar．2001
[72]陈松灿等，图像的模糊识别方法研究与实现，电子学报，2000年第11期
[73]曾召华等，基于Gabor滤波器的边缘检测方法，无线电工程，2000年第3期
[74]D.C Wang,Vagnucci AH,Licc,Gradient inverse Weighted Something Scheme and evaluation of its Performance CGGIP 6,167-187
[75]K N Plataniotis,D Androutsos,A N Venetsanopoulos.content-based color image filters.Electronics Letter,1997:33:212-203
[2]王天珍，计算机视觉研究进展，武汉汽车工业大学学报，VOL．20，NO．1，FEB．1998
[3]Marr D．视觉计算理论。姚国正等译。北京：科学出版社，1988
[4]Rosenfeld A.Computer Vision—Basic Principle.ProC.of.IEEE,1988(8):863-868
[5]Aloimonos Y,Rosenfeld A Response to"Ignorance,Myopia,and Naviete in Computer Vision System"by R.C.Jain and T.O.Binford.CVGIP IMAGE UNDERSTANDING,1991,53(1):120-124
[6]Bajcsy R Active Perception.Proc.of IEEE,1988,76(8):996-1005
[7]Ballade D H,Brown C M.Principles of Animate Vision CVGIP IMAGE UNDERSTANDING,1992.56(1):3-21
[8]Thompson W B.Qalitative Constraints for Structure from Motion.CVGIP IMAGE UNDERSTANDING.1992,56(1):69-77
[9]王润生，图像理解，国防科技大学出版社，1995
[10]韦穗，计算机视觉，机器人，1992(4)
[11]马颂德、张正友，计算机视觉—计算理论与算法基础，科学出版社，1998
[12]戚飞虎等，模式识别与图像处理，上海交通大学出版社，1990
[13]相阿荣、王一鸣，利用色度法识别杂草和土壤背景物，中国农业大学出版社，2000，5(4)：98-100
[14]金伟其，现代城市交通流量的三维图像检测技术，红外与激光工程，Dec．1997
[15]王三武等，CCD电子抄表系统及图像的采集，武汉汽车工业大学学报，Vol．22 No．6 Dec．2000
[16]洪华军等，指纹图像自动识别系统预算法的研究，电子技术应用，2001年第一期
[17]赵红颖等，基于计算机视觉的发动机缺陷检测系统的应用，光学精密工程，Vol．8．No．3 Jun，2000
[18]潘俊民等，基于计算机视觉的自动浇注系统，铸造技术，2/1998
[19]王积分、张新荣，计算机图像识别，中国铁道出版社，1988
[20]屈志毅等，印鉴自动识别系统中图像处理与识别的方法研究，甘肃科学学报，Vol．13 No．1 Mar．2001
[21]胡均安等，实时识别系统技术在片式元件编带机中的应用，武汉汽车工业大学学报，Vol．22．No．6 Dec．200
[22]荆仁杰等，计算机图像处理，浙江大学出版社，1990
[23]蒋加伏等，计算机视觉系统研究中存在的问题及解决思路，长沙交通学院学报，Vol．15 No．1 Mar 1999
[24]CHIU M Y.Is Industry Ready for Machine Vision, Perspective in Computer,Academic Press[C].New York:1989,24:227-230
[25]JAIN R C.Ignorance,Myopia,Naivate in Computer Vision System[R].CVGIP,Image Understanding,1991,53(1):112-117
[26]MCCLAMROCK R.Marr's Three Levels:A Re Evaluation[J].Minds Mach.1991,1(2):185-196
[27]PAVLIDIS T.Why Progress in Machine Vision is So Slow[j] Pattern Recognition Letter,1992,13(4):221-225
[28]ALOIMONOS Y.Robust Computation of Instrisic Images from Multiple Cues[J].Inc.Publisher,1988,1:115-225
[29]NAVON D.Forest before Trees:The Precedence of Global Feature in Visual Perception[J].Cognitive Psychology,1997.9:353-383
[30]CHEN L.Topological Perception A Challenge to Computional Approaches to Vision[M].Elsevier Science Publishers,1989.317-329
[31]GIBSON J J.The Ecological Approach to Visual Perception[M].Houghton Mifflin,1979
[32]BALLARD H D.Computer Vision[M].Prentice Hall,Inc:1982
[33]BAMEA I D.A Class of Algorithms for Fast Image Registration[J].IEEE Trans.on computers,1972(2)
[34]刘效静，汽车牌照自动识别技术研究，南京，南京航空航天大学学报，1998，30(5)
[35]姚庆栋等，图像编码基础，人民邮电出版社，1984
[36]K N Plataniotis,D Androutsos,A N Venetsanopoulos.Content-based color image filters.Electronic Letters,1997;33:212-203
[37]陈永彬等，数字信号处理，南京工学院出版社，1987
[38]KUANG Yu,YOU Zhi-sheng etc,Multi-Targets detection and segmentation of Moving Sperm,Jounal of Image and Graghics,1999,5:405-408(ch)
[39]李树涛、王耀南，图像椒盐噪声的非线性自适应滤除。中国图像图形学报。2000，Vol．15，No．12．2000，999-1001
[40]孙仲康等，数字图像处理及其应用，国防工业出版社，1988
[41](美)W。K。普拉特，数字图像处理学，科学出版社，1984
[42][美]A。罗森菲尔德，数字图像分析，科学出版社，1987
[43]Kenneth.R.Castleman著，朱志刚等译，数字图像处理，电子工业出版社，1998
[44]周新论、柳健等，数字图像处理，国防工业出版社，1986
[45]钟玉琢等，机械人视觉技术，国防工业出版社，1994
[46]Davis R O,New Measures of Sperm Motion.J Andrology,1992,13(2):87-90
[47]lluang T.S.Computer Vision Needs More Experiment and Applications.CVGIP:IU,Jan 1991,53(1)125-126
[48]Canny J.A computational approach to edge detection.IEEE Trans.On PAMI 1986,679-698
[49]Mallat S G,Zhzng S.Charaterization of signals from Multi-scale Edages.IEEE T—PAMI,1992,14(7):710—732
[50]Daubechies I.Orthonormal Bases of Compactly Supported Wavelets Communication on Pure and Applied Mathematics,XLI,1988,909—996
[51]Kapur J N,Sahoo P K,Wrong A.A new method for gray—level picture Thresholding using the entropy of the histogram.Computer Vision Graphics Image Process,1985,29(3):273—285
[52]Sahoo P K,Soltani,Wrong A,Chen Y C,A Survey of Thresholding Techniques.Computer Vision Graphics Process,1988,41(2):233—260
[53]Cinque L,Levialdi S,Rosenfield A,Fast pyramidal algorithum for image thresholding,Pattern Recognition,1995,28(5):901—906
[54]孙洪波等，实时动态图像检测系统研究，测控技术，1997年第八个五年计划6卷第2期
[55]魏武等，车牌识别的分布式结构处理方法研究，长沙交通学院学报，Vol．16 No．2 June 2000
[56]冯月霞等，一种基于视频图像处理的识别系统，电子技术，2001年第4期
[57]李玉山等，彩色图像的边缘检测研究，模式识别与人工智能，Vol．5 No．2 June 1992
[58]刘勇等，图像差异的分析与识别，复旦学报(自然科学版)，Vol．39 No．5 Oct，2000
[59]程文娟等，工业物料自动识别中主色调特征的提取，沈阳师范学院学报，Vol．19 No．3 Jul 2001
[60]罗西平，田捷等，图像分割方法综述，模式识别与人工智能，1999，9(3)：300-312
[61]付忠良，基于图像差距度量的阈值选取方法，计算机研究与发展，Vol．38 No．5 May 2001
[62]王思贤等，低对比度图像目标分割的研究，武汉大学学报(自然科学版)，Vol．46 No．5 Oct 2000
[63]冯丽爽，CCD传感器在人体运动图像检测系统中的应用，仪表技术与传感器，2001年第5期
[64]付忠良，图像阈值选取方法---Otsu方法的推广，计算机应用，2000，5(5)：37—39
[65]胡玉僖等，具有数字图像处理功能的运动分析系统，光学技术，No．1 Jan．1998
[66]杨平先等，基于分形的图像边缘检测研究，电讯技术，Vol．38 No．4 Aug．1998
[67]张文淘，高速运动可视多目标精确检测研究，电子与信息学报，Vol．23 No．4 Apr．2001
[68]Otsu.A threshold selection method from gray-level histogram.IEEE Trans on SMC-9,1979,9(3):62-66
[69]李玉山，物体表面缺陷模型及检测方法的研究，西安电子科技大学学报，1988，15(4)：82-91
[70]陈斌等，车牌号码颜色提取搜索方法，计算机应用，Vol．21 No．4 Apr．2001
[71]黄信新等，实时图像轮廓抽取算法研究，计算机应用，Vol．21 No．3 Mar．2001
[72]陈松灿等，图像的模糊识别方法研究与实现，电子学报，2000年第11期
[73]曾召华等，基于Gabor滤波器的边缘检测方法，无线电工程，2000年第3期
[74]D.C Wang,Vagnucci AH,Licc,Gradient inverse Weighted Something Scheme and evaluation of its Performance CGGIP 6,167-187
[75]K N Plataniotis,D Androutsos,A N Venetsanopoulos.content-based color image filters.Electronics Letter,1997:33:212-203