彩色分割在多刻度线的指针仪表中的研究及应用
|
摘要
图像分割是图像分析和模式识别需要解决的首要问题和基本问题,也是图像处理的经典难题。彩色图像比灰度图像具有更多的视觉信息,因而受到了越来越多的重视。本论文的主要研究目的和任务就是力求将彩色图像分割的方法运用到多刻度线指针表的识别系统中,将传统的仪表识别系统中加入彩色图像分割的新方法,改善以往的仪表识别系统。
本文主要论述了利用颜色提取及图像分割技术对多刻度线的指针式仪表的进行识别处理的原理、步骤以及具体的实现过程。详细介绍了彩色图像处理的基本理论基础,将图像颜色特征比较明显的指针式表盘作为研究重点,应用基于颜色提取的彩色图像分割技术完成对指针表盘图像中彩色刻度区域的分割提取,提出了一种新的应用在多刻度线的指针式仪表中的彩色分割算法。经过实验分析证明,该算法充分利用了指针刻度区域的彩色信息,取得了较好的分割效果,并且简化了指针刻度值的识别算法,为后续识别奠定了基础。
此外,本文还通过模板匹配的方法利用刻度线旁的字符标识识别出相应刻度线测量值的物理意义,对后续指针刻度值的识别具有决定性的意义。大量的实验结果数据表明,这种方法具有比较满意的识别效果。
The image segmentation, which is the first essential and fundamental issue in the image analysis and pattern recognition, is a classical difficult problem in the image processing. The color images, which possess more visual information than the gray images do, have aroused more and more attentions. The research object of this paper is using color image segmentation into the system which identifies the multi-scale pointer meters. By adding a new color image segmentation method to the traditional instrument recognition system, we can improve the previous instrument identification system.
This thesis mostly discusses the image processing and recognition means of the multi-scale pointer meters, by using the technology of color extracting and image segmentation. This paper introduces the theory of colorized image processing, makes the multi-scale pointer meters that have obvious character of color be the emphases of research, uses the technology of color extracting and image segmentation to extract the colorful part of the scale line which should be identified and uses many image processing technology to bring forward a new color image segmentation method for using into the system which identifies the multi-scale pointer meters. Through a great deal of experiments, this method fully uses the color information, and has good processing result, and this method establishes the basic for identifying the scale value.
Besides, in order to know the physical means of the scale value, this paper uses the template matching method to identify the characters which beside scale lines, it establishes the basic for identifying the scale value. Through a great deal of experiments, this method has satisfying processing result.
本文主要论述了利用颜色提取及图像分割技术对多刻度线的指针式仪表的进行识别处理的原理、步骤以及具体的实现过程。详细介绍了彩色图像处理的基本理论基础,将图像颜色特征比较明显的指针式表盘作为研究重点,应用基于颜色提取的彩色图像分割技术完成对指针表盘图像中彩色刻度区域的分割提取,提出了一种新的应用在多刻度线的指针式仪表中的彩色分割算法。经过实验分析证明,该算法充分利用了指针刻度区域的彩色信息,取得了较好的分割效果,并且简化了指针刻度值的识别算法,为后续识别奠定了基础。
此外,本文还通过模板匹配的方法利用刻度线旁的字符标识识别出相应刻度线测量值的物理意义,对后续指针刻度值的识别具有决定性的意义。大量的实验结果数据表明,这种方法具有比较满意的识别效果。
The image segmentation, which is the first essential and fundamental issue in the image analysis and pattern recognition, is a classical difficult problem in the image processing. The color images, which possess more visual information than the gray images do, have aroused more and more attentions. The research object of this paper is using color image segmentation into the system which identifies the multi-scale pointer meters. By adding a new color image segmentation method to the traditional instrument recognition system, we can improve the previous instrument identification system.
This thesis mostly discusses the image processing and recognition means of the multi-scale pointer meters, by using the technology of color extracting and image segmentation. This paper introduces the theory of colorized image processing, makes the multi-scale pointer meters that have obvious character of color be the emphases of research, uses the technology of color extracting and image segmentation to extract the colorful part of the scale line which should be identified and uses many image processing technology to bring forward a new color image segmentation method for using into the system which identifies the multi-scale pointer meters. Through a great deal of experiments, this method fully uses the color information, and has good processing result, and this method establishes the basic for identifying the scale value.
Besides, in order to know the physical means of the scale value, this paper uses the template matching method to identify the characters which beside scale lines, it establishes the basic for identifying the scale value. Through a great deal of experiments, this method has satisfying processing result.
引文
[1]黄飞,吴敏渊,曹开田.基于HSI空间的彩色图像分割[J].小型微型机算机系统,2004,(3):471-474.
[2]汪鼎文,李元香.基于HSI颜色空问的x射线彩色图像分割[J].计算机工程与设计,2006,(1):139-141.
[3]高天芳,孔凡让,余涛等.非电子仪表的一种计算机判读和处理系统.中国科学技术大学学报,1999,(12).
[4]王三武,戴亚文,景仁坤.复杂仪表的图像自动读数识别方法.武汉理工大学报·信息与管理工程版,2003,(12).
[5]周洪,钟明慧.工业过程显示仪表的数字处理与视频传输.仪器仪表学报,29,(4).
[6]孟宪尧,李实.机舱监测报警新结构的探索.大连海事大学学报.1999,(11).
[7]杨耀权,赵艳琴,何晓燕等.基于计算机视觉技术的指针式仪表自动检定方法.仪器仪表学报,22,(3).
[8]王东文,刘明远,史昊.汽车仪表板总成智能检测方法.仪器仪表学报,1996,(10).
[9]霍宏、沈长妹、李樱.一种快速识别飞机仪表参数的算法.吉林工业大学学报,1998,(1).
[10]严义、包健.一种实用视觉识别的仪表自动检定系统.仪表技术与传感器,2002,(2).
[11]马丽红,张宇,邓健平.基于形态开闭滤波二值标记和纹理特征合并的分水岭算法[J].中国图像图形学报,2003,8(1):77-83.
[12]Luo J B,Guo C E.Perceptual grouping of segmentated regions in color images[J].Pattern Recognition,2003,36(12):2781-2792.
[13]Serra J.Image segmentation[A].Proceedings of the IEEE International Conference on Image Processing[C].2003,Vol.1.345-348.
[14] Littmann E,Ritter H. Adaptive color segmentation-a comparison of neural and statistical methods[J]. IEEE Transactions on Neural Net-work, 1997, 8(1) : 175-184.
[15] Pham D L, Prince J L. An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities[J]. PatternRecognition, 1999,32(1):57-68.
[16] Obadia B L,Gee A. Adaptive segmentation of ultrasound images [J]. Image and Computing, 1999,17(10): 583-588.
[17] ZhaoMS, Yang Y B, Yan H. An adaptive thresholding method for bi-narization of blueprint images[J]. Pattern Recognitions, 2000, 33(6) :927-943.
[18] Tian L F,Slaughter D C. Enviromentally adaptive segmentation algo-rithm for outdoor image segmentation [J]. Computers and Electronics in Agriculture, 1998,21(3): 153-168.
[19] Lee K M, Meer P, Park R H. Robust adaptive segmentation of range images[J]. IEEE Transactions on Pattern Analysis andMachine Intelli-gence, 1998, 20(2):200-20
[20] Yujin Zhan, Yun He, Yurong Yao. Color image segmentation based on HSI model[J]. High Technology LeRers,1998, (7):28-31
[21] Ashraf Elnagar,Saad Harous. Recognition of Handu Numerals Using Structural Descriptors. Taylor&Francis, 2003, 3(15) :299-314.
[22] Theo Pavlidis. 36 years on the pattern recognition front lecture given ICPR' 2000 in Barcelona, Spain on the occasion of receiving the K. S. Fu prize. Pattern Recognition Letters 24(2003)1-7.
[23] Byung-Gyu Kim, Jac-Ick shim, Dong-Jo park. Fast image segmentation based on muti-resolution analysis and wavelets[J]. Pattern RecognitionLetters, 2003(24) :2995—3006.
[24] Sclarofs, Liu L. Deformable Shape Detector and Description vi8 Model-Based Grouping [J]. IEEE Tran, on Pattern Analysis and Machine Intelligence, 2001 (23) :475—488.
[28]Kumgollu F,Sankur B,Harmanei A E.Color image segmentation using histo-~am muhithresholding and fusion[J].Image and Vision Computing,2001,19(13):918-928.
[26]ALEGRIA F C,SERRAA C.Automatic calibration of analog and digital measuring instruments using computer vision[J].IEEE Transactions on Instrumentation and Measure-ment,2000,49(1):94-99
[27]ILLINGWORTH J,KITTLER J,A survey of the trans-form[J].Computer Vision,Graphics,and Image Processing,1988,44(3):87-116.
[28]潘晨,顾峰.基于3直方图的彩色图像分割方法[J].中国图像图形学报,2002,7(8):800-805.
[29]林开颜,徐立鸿,吴军辉.快速模糊均值聚类彩色图像分割方法[J].中国图像图形学报,2004,9A(2):159-164.
[30]赵雪春、戚飞虎.基于彩色分割的车牌自动识别技术[J].上海交通大学学报,1998,32(10):4-9.
[31]张引、潘云鹤.彩色汽车图象牌照定位新方法.中国图象图形学报2001,(4).
[32]鲁宗骐,梁诚.用Sobel算子细化边缘[J].中国图像图形学报,2000,6(5):516-520.
[33]崔屹.数字图像处理技术与应用[M].北京:电子工业出版社,1997.
[34]徐毅,杨耀权.计算机视觉及其在电力工业中的应用[J].电力情报,2000,(1):1-5.
[35]李盛阳,叶梧,冯穗利.基于Hough变换的视觉识别方法在仪表自动检测中的应用研究.科学技术与工程,2005,(1):82-85.
[36]陈彬,金连文.一种仪表指针位置检测的中心投影法.计算机应用研究,2005,(1):246-248.
[37]赵书涛,李宝树,贾秀芳.基于计算机视觉的电测仪表自动识别方法的研究.仪器仪表学报,2004,(8):606-607.
[38]王博,秦岭松.基于计算机视觉的指针式仪表白动检测系统.计算机工程,2005,6):19-21.
[39]任光龙.指针式仪表图像的快速分割法研究,计算机工程与设计, 2005,(3):790-792.
[40]章毓晋,图像工程图象处理和分析.清华大学出版社,1999,(3).
[2]汪鼎文,李元香.基于HSI颜色空问的x射线彩色图像分割[J].计算机工程与设计,2006,(1):139-141.
[3]高天芳,孔凡让,余涛等.非电子仪表的一种计算机判读和处理系统.中国科学技术大学学报,1999,(12).
[4]王三武,戴亚文,景仁坤.复杂仪表的图像自动读数识别方法.武汉理工大学报·信息与管理工程版,2003,(12).
[5]周洪,钟明慧.工业过程显示仪表的数字处理与视频传输.仪器仪表学报,29,(4).
[6]孟宪尧,李实.机舱监测报警新结构的探索.大连海事大学学报.1999,(11).
[7]杨耀权,赵艳琴,何晓燕等.基于计算机视觉技术的指针式仪表自动检定方法.仪器仪表学报,22,(3).
[8]王东文,刘明远,史昊.汽车仪表板总成智能检测方法.仪器仪表学报,1996,(10).
[9]霍宏、沈长妹、李樱.一种快速识别飞机仪表参数的算法.吉林工业大学学报,1998,(1).
[10]严义、包健.一种实用视觉识别的仪表自动检定系统.仪表技术与传感器,2002,(2).
[11]马丽红,张宇,邓健平.基于形态开闭滤波二值标记和纹理特征合并的分水岭算法[J].中国图像图形学报,2003,8(1):77-83.
[12]Luo J B,Guo C E.Perceptual grouping of segmentated regions in color images[J].Pattern Recognition,2003,36(12):2781-2792.
[13]Serra J.Image segmentation[A].Proceedings of the IEEE International Conference on Image Processing[C].2003,Vol.1.345-348.
[14] Littmann E,Ritter H. Adaptive color segmentation-a comparison of neural and statistical methods[J]. IEEE Transactions on Neural Net-work, 1997, 8(1) : 175-184.
[15] Pham D L, Prince J L. An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities[J]. PatternRecognition, 1999,32(1):57-68.
[16] Obadia B L,Gee A. Adaptive segmentation of ultrasound images [J]. Image and Computing, 1999,17(10): 583-588.
[17] ZhaoMS, Yang Y B, Yan H. An adaptive thresholding method for bi-narization of blueprint images[J]. Pattern Recognitions, 2000, 33(6) :927-943.
[18] Tian L F,Slaughter D C. Enviromentally adaptive segmentation algo-rithm for outdoor image segmentation [J]. Computers and Electronics in Agriculture, 1998,21(3): 153-168.
[19] Lee K M, Meer P, Park R H. Robust adaptive segmentation of range images[J]. IEEE Transactions on Pattern Analysis andMachine Intelli-gence, 1998, 20(2):200-20
[20] Yujin Zhan, Yun He, Yurong Yao. Color image segmentation based on HSI model[J]. High Technology LeRers,1998, (7):28-31
[21] Ashraf Elnagar,Saad Harous. Recognition of Handu Numerals Using Structural Descriptors. Taylor&Francis, 2003, 3(15) :299-314.
[22] Theo Pavlidis. 36 years on the pattern recognition front lecture given ICPR' 2000 in Barcelona, Spain on the occasion of receiving the K. S. Fu prize. Pattern Recognition Letters 24(2003)1-7.
[23] Byung-Gyu Kim, Jac-Ick shim, Dong-Jo park. Fast image segmentation based on muti-resolution analysis and wavelets[J]. Pattern RecognitionLetters, 2003(24) :2995—3006.
[24] Sclarofs, Liu L. Deformable Shape Detector and Description vi8 Model-Based Grouping [J]. IEEE Tran, on Pattern Analysis and Machine Intelligence, 2001 (23) :475—488.
[28]Kumgollu F,Sankur B,Harmanei A E.Color image segmentation using histo-~am muhithresholding and fusion[J].Image and Vision Computing,2001,19(13):918-928.
[26]ALEGRIA F C,SERRAA C.Automatic calibration of analog and digital measuring instruments using computer vision[J].IEEE Transactions on Instrumentation and Measure-ment,2000,49(1):94-99
[27]ILLINGWORTH J,KITTLER J,A survey of the trans-form[J].Computer Vision,Graphics,and Image Processing,1988,44(3):87-116.
[28]潘晨,顾峰.基于3直方图的彩色图像分割方法[J].中国图像图形学报,2002,7(8):800-805.
[29]林开颜,徐立鸿,吴军辉.快速模糊均值聚类彩色图像分割方法[J].中国图像图形学报,2004,9A(2):159-164.
[30]赵雪春、戚飞虎.基于彩色分割的车牌自动识别技术[J].上海交通大学学报,1998,32(10):4-9.
[31]张引、潘云鹤.彩色汽车图象牌照定位新方法.中国图象图形学报2001,(4).
[32]鲁宗骐,梁诚.用Sobel算子细化边缘[J].中国图像图形学报,2000,6(5):516-520.
[33]崔屹.数字图像处理技术与应用[M].北京:电子工业出版社,1997.
[34]徐毅,杨耀权.计算机视觉及其在电力工业中的应用[J].电力情报,2000,(1):1-5.
[35]李盛阳,叶梧,冯穗利.基于Hough变换的视觉识别方法在仪表自动检测中的应用研究.科学技术与工程,2005,(1):82-85.
[36]陈彬,金连文.一种仪表指针位置检测的中心投影法.计算机应用研究,2005,(1):246-248.
[37]赵书涛,李宝树,贾秀芳.基于计算机视觉的电测仪表自动识别方法的研究.仪器仪表学报,2004,(8):606-607.
[38]王博,秦岭松.基于计算机视觉的指针式仪表白动检测系统.计算机工程,2005,6):19-21.
[39]任光龙.指针式仪表图像的快速分割法研究,计算机工程与设计, 2005,(3):790-792.
[40]章毓晋,图像工程图象处理和分析.清华大学出版社,1999,(3).