高噪声目标图像的轮胎规格号识别技术研究
|
摘要
轮胎规格号是指生产厂家在轮胎胎侧印制的代表轮胎规格的特定意义的字符,对于厂家来说,这些参数在轮胎工厂管理中对于轮胎类型的识别分类非常重要,可用来作为生产管理、质量追查的一个重要参量。
目前OCR技术被广泛用于字符识别,但在国内还没有轮胎规格号识别的相关研究及报导,国外针对DOT(US Department of Transportation缩写)码和轮胎规格号识别的一个比较成熟的技术是线激光扫描CCD成像识别,这套识别系统采用三角法测量技术,优点是识别轮胎模压成型字符可靠,强健,缺点是成本高,处理时间长,需要线激光发射设备、CCD成像系统和机械运动结构,并且对印刷字符无法识别。
本文在分析国内外研究现状的基础上,围绕轮胎规格号识别开展研究,针对目标图像的特点,提出LED阵列照明、CMOS成像以及BP神经网络算法识别系统,该系统成本低,速度快,能有效识别不同字体、大噪声背景下的轮胎规格号字符。其中,在图像预处理方面,采用最小二乘法迭代拟合圆法对圆心进行精确定位,并且提出利用积分加窗统计法提取规格号字符区域,用边缘自适应定位算法对单个字符进行分割,有效排除了大噪声干扰。在规格号识别上,提取了多种特征分析,利用BP神经网络算法的字符分类器和基于规格号关系特征的二次分类器识别,使得规格号识别达到了较高的识别率,并且该识别系统耗费时间少,能够满足快速检测要求,本课题的研究工作取得了预期效果。
本文工作的主要创新点如下:
1、轮胎图像采集的照明技术研究。由于轮胎图像背景和前景字符是同种橡胶材质,表面色差很小,因此通常采集得到的图像有噪声大、对比度低的特点,本文采用特定设计的环形阵列LED结构照明,有效降低了图像噪声,提高图像对比度。
2、高噪声背景下的识别目标提取算法。算法利用积分窗口来降低图像边缘图维数,由二维变成一维,并提出利用一维信号的极值点来形成锯齿波,依据锯齿波的波形参数和其规则性来提取规格号字符区域;针对字符个体分割的复杂性问题,提出边缘自适应定位算法,该算法利用边缘强度、连接强度和字符宽度,采用阈值由小到大、区域分割由大到小多次迭代来定位字符。算法抗噪能力强,适合复杂环境下的字符精确定位。
3、结合关系特征的轮胎规格号综合识别算法。针对规格号字符特点,深入研究了轮胎规格号字符识别特征,提出了基于BP神经网络的规格号字符识别;并提出基于规格号关系特征的二次分类器识别算法;针对噪声混淆字符信息的情况,提出字符截断方法以获得不完全可区分字符特征算法,提高字符识别率。实验结果表明,结合关系特征的轮胎规格号综合识别算法适合于轮胎规格号识别。
Tire Specifications is character printed in sidewall of the body by manufacturers on behalf of specific significance. These parameters is very important to identify the type of classification for tire factory management, used as a important parameters for production management、quality of tracing.
At present, OCR technology is widely used in character recognition, but tire specifications have not yet identified its research and related reporting in the domestic. A more mature technology abroad for the DOT Code and Tire Specifications identification is the CCD imaging with scanning of line laser, this identification system using triangulation measurement technology, the advantage of identification of tire molding character are reliable and robust, the disadvantage are high cost、long processing time and needing line laser equipment、CCD imaging systems and mechanical structure, moreover, it does not recognize the printed characters.
Based on the analysis of the history and recent developments around tire Specifications identification, study was carried out. The article analysed characteristics of the target image, a system was presented that included LED lighting arrays, CMOS imaging, as well as identification of BP neural network, which low-cost, fast and effective identification of different fonts of tire specifications with big background noise. Among them, in image pre-processing, the use of iterative least square method used to fit accurate positioning of the circle center , and proposed integral windowed statistics to extract specifications character region, a edge adaptive localization algorithm for segmentation of individual characters,which effectively ruled out big noises. In specifications recognition, research was developed by using a variety of characteristics extracted, and combined methods were used to identify tire specifications with classifier of BP neural network algorithm-based classifier and secondary classifier recognition algorithm of specifications, which have high recognition rate and the less time-consuming. The identification system meeted the rapid testing requirements and came up to the desired effect.
The following are the main innovations.
1. Lighting technology research for Tire image capture.As tire image background and character prospects is the same kinds of rubber material, the surface color difference is very small, therefore the image acquisition are with noise and low contrast, this paper adopts specific design structure of a ring array of LED lighting, effectively reducing the image noise, increase image contrast.
2. Extraction algorithms for recognition object of high noise background. Algorithm using integral window to reduce the dimensions of the image edge map, from two-dimensional to one-dimensional, and to make use of one-dimensional signals to form the sawtooth extreme points, based on sawtooth waveform parameters and specifications of its rules to extract the number of characters in the region ; for the segmentation of individual characters in the complexity of the issue and put forward edge adaptive localization algorithm, the algorithm uses edge-connection strength、edge strength and character length and using threshold from small to large, regional division multiple iterations to locate the characters in descending . Algorithm for anti-noise capability, suitable for a complex environment, precise positioning of characters.
3.Combining with the relation features of an integrated recognition algorithm of tire specifications. According to the characteristics of specification characters, in-depth study of the tire specification character recognition features, recognition algorithm of specifications was presented based on BP neural network character recognition; and secondary classifier recognition algorithm of specifications was proposed based on the relationship features . For the noise, confusion of character information proposed method to obtain the truncated characters are not fully distinguish between characters feature algorithm to improve character recognition rate. Experimental results show that the comprehensive specifications recognition algorithm combined with relationship features is adaptive of tire specifications recognition..
目前OCR技术被广泛用于字符识别,但在国内还没有轮胎规格号识别的相关研究及报导,国外针对DOT(US Department of Transportation缩写)码和轮胎规格号识别的一个比较成熟的技术是线激光扫描CCD成像识别,这套识别系统采用三角法测量技术,优点是识别轮胎模压成型字符可靠,强健,缺点是成本高,处理时间长,需要线激光发射设备、CCD成像系统和机械运动结构,并且对印刷字符无法识别。
本文在分析国内外研究现状的基础上,围绕轮胎规格号识别开展研究,针对目标图像的特点,提出LED阵列照明、CMOS成像以及BP神经网络算法识别系统,该系统成本低,速度快,能有效识别不同字体、大噪声背景下的轮胎规格号字符。其中,在图像预处理方面,采用最小二乘法迭代拟合圆法对圆心进行精确定位,并且提出利用积分加窗统计法提取规格号字符区域,用边缘自适应定位算法对单个字符进行分割,有效排除了大噪声干扰。在规格号识别上,提取了多种特征分析,利用BP神经网络算法的字符分类器和基于规格号关系特征的二次分类器识别,使得规格号识别达到了较高的识别率,并且该识别系统耗费时间少,能够满足快速检测要求,本课题的研究工作取得了预期效果。
本文工作的主要创新点如下:
1、轮胎图像采集的照明技术研究。由于轮胎图像背景和前景字符是同种橡胶材质,表面色差很小,因此通常采集得到的图像有噪声大、对比度低的特点,本文采用特定设计的环形阵列LED结构照明,有效降低了图像噪声,提高图像对比度。
2、高噪声背景下的识别目标提取算法。算法利用积分窗口来降低图像边缘图维数,由二维变成一维,并提出利用一维信号的极值点来形成锯齿波,依据锯齿波的波形参数和其规则性来提取规格号字符区域;针对字符个体分割的复杂性问题,提出边缘自适应定位算法,该算法利用边缘强度、连接强度和字符宽度,采用阈值由小到大、区域分割由大到小多次迭代来定位字符。算法抗噪能力强,适合复杂环境下的字符精确定位。
3、结合关系特征的轮胎规格号综合识别算法。针对规格号字符特点,深入研究了轮胎规格号字符识别特征,提出了基于BP神经网络的规格号字符识别;并提出基于规格号关系特征的二次分类器识别算法;针对噪声混淆字符信息的情况,提出字符截断方法以获得不完全可区分字符特征算法,提高字符识别率。实验结果表明,结合关系特征的轮胎规格号综合识别算法适合于轮胎规格号识别。
Tire Specifications is character printed in sidewall of the body by manufacturers on behalf of specific significance. These parameters is very important to identify the type of classification for tire factory management, used as a important parameters for production management、quality of tracing.
At present, OCR technology is widely used in character recognition, but tire specifications have not yet identified its research and related reporting in the domestic. A more mature technology abroad for the DOT Code and Tire Specifications identification is the CCD imaging with scanning of line laser, this identification system using triangulation measurement technology, the advantage of identification of tire molding character are reliable and robust, the disadvantage are high cost、long processing time and needing line laser equipment、CCD imaging systems and mechanical structure, moreover, it does not recognize the printed characters.
Based on the analysis of the history and recent developments around tire Specifications identification, study was carried out. The article analysed characteristics of the target image, a system was presented that included LED lighting arrays, CMOS imaging, as well as identification of BP neural network, which low-cost, fast and effective identification of different fonts of tire specifications with big background noise. Among them, in image pre-processing, the use of iterative least square method used to fit accurate positioning of the circle center , and proposed integral windowed statistics to extract specifications character region, a edge adaptive localization algorithm for segmentation of individual characters,which effectively ruled out big noises. In specifications recognition, research was developed by using a variety of characteristics extracted, and combined methods were used to identify tire specifications with classifier of BP neural network algorithm-based classifier and secondary classifier recognition algorithm of specifications, which have high recognition rate and the less time-consuming. The identification system meeted the rapid testing requirements and came up to the desired effect.
The following are the main innovations.
1. Lighting technology research for Tire image capture.As tire image background and character prospects is the same kinds of rubber material, the surface color difference is very small, therefore the image acquisition are with noise and low contrast, this paper adopts specific design structure of a ring array of LED lighting, effectively reducing the image noise, increase image contrast.
2. Extraction algorithms for recognition object of high noise background. Algorithm using integral window to reduce the dimensions of the image edge map, from two-dimensional to one-dimensional, and to make use of one-dimensional signals to form the sawtooth extreme points, based on sawtooth waveform parameters and specifications of its rules to extract the number of characters in the region ; for the segmentation of individual characters in the complexity of the issue and put forward edge adaptive localization algorithm, the algorithm uses edge-connection strength、edge strength and character length and using threshold from small to large, regional division multiple iterations to locate the characters in descending . Algorithm for anti-noise capability, suitable for a complex environment, precise positioning of characters.
3.Combining with the relation features of an integrated recognition algorithm of tire specifications. According to the characteristics of specification characters, in-depth study of the tire specification character recognition features, recognition algorithm of specifications was presented based on BP neural network character recognition; and secondary classifier recognition algorithm of specifications was proposed based on the relationship features . For the noise, confusion of character information proposed method to obtain the truncated characters are not fully distinguish between characters feature algorithm to improve character recognition rate. Experimental results show that the comprehensive specifications recognition algorithm combined with relationship features is adaptive of tire specifications recognition..
引文
[1]吴忠,自动识别技术在现代轮胎工业中的应用,轮胎工业,2002(12):760– 763。
[2]刘连云,以胎号为中心的轮胎管理系统,轮胎工业,2003,23:392-396。
[3]孙俊,李正明,杨继昌,汽车轮胎信息识别与管理系统的设计,江苏大学学报(自然科学版),2004,25(5):397– 400。
[4]朱金陆,黄有平等,激光轮胎打码机的开发及应用,2007年第27卷第1期,p61-62。
[5] Jianhai Cao:A Study on Recognizing and Checking of the Pressed Protuberant Character on a Metal Label, Jinan:Shangdong University,2004(In Chinses).
[6] GunSeo koo,HaeSeok Oh , MCBP Neural Network Formation for Efficient Recognition of Tire Sorting Code by Image Processing,1996 IEEE,T6-PC6.1 - T6-PC6.4,P524-527.
[7]王方智,条码在轮胎工业中的应用,轮胎工业,1999, 19: 176-177。
[8]陈礼宾,朱金陆,陈绍文,条码技术在轮胎生产管理中的应用,轮胎工业,2005年第25卷第10期,p623-625。
[9] BYTEWISE,“Automatic Tire Identification and DOT Code Recognition Using Very-High-Speed Laser Profile Sensors”http://www.bytewise.com/files/DOT_Code_Recognition_IntroV4.pdf.
[10]王先波,轮胎胎号自动识别录入装置的设计与软件实现,华南理工大学硕士学位论文,2002年。
[11]于清溪,工程轮胎生产现状与发展前景,橡塑技术与装备,2007年第33卷,p1-15。
[12]蔡为民,国内外轮胎发展分析,2007年第27卷第12期,p707-711。
[13]邓海燕,轮胎产品DOT认证概述,2002年第22卷第7期,p394-397。
[14]卢晋人,黄元庆,激光三角法测量表面形貌,厦门大学学报(自然科学版),2004年第43卷第l期。
[15]周祥,轮胎胎号自动识别系统的研究与设计,江苏大学硕士学位论文,2005年。
[16]冯慧平,蔡习训等,LED阵列光源之照明设计,中国机械工程学会第二十四届全国学术研讨会论文集,论文编号:E05-0002。
[17]胡海蕾,LED照明光学系统的设计及其阵列光照度分布研究,福建师范大学硕士学位论文,2005年。
[18] J.R.Coaton,A.M.Marsden,光源与照明,第四版,上海复旦大学出版社,2000。
[19]刘潮东,史忠科,各向异性扩散-中值滤波在红外图像处理中的应用[J]弹箭与制导学报,2006,(03)。
[20]张文攀,吴军辉,朱震,李华,王强,基于准十字窗口的中值滤波法在红外图像处理中的应用,电光与控制,2006,(01)。
[21]仲兆满,韩其睿,王电化,一种基于方向梯度的图像滤波算法,淮阴师范学院学报(自然科学版),2005,(03)。
[22]李冰,王艳,耿则勋,一种改进的遥感图像自适应加权滤波算法,测绘学院学报,2005,(02)。
[23]张霞,葛芦生,自适应中值滤波算法的研究与应用,微计算机信息,2007,(06)。
[24]薛小强,使用迭代重加权最小二乘法求解平面度误差,中国农机化,2005,(03)。
[25]陈良泽,用矩阵运算实现曲线拟合中的最小二乘法,传感器技术,2001,(02)。
[26]刘海香,张彩明,梁秀霞,平面上散乱数据点的二次曲线拟合,计算机辅助设计与图形学学报,2004,(11)。
[27]徐国旺,廖明潮,拟合圆的几种方法,武汉工业学院学报,2002,(04)。
[28]田社平,张守愚,李定学,俞朴,平面圆圆心及半径的最小二乘拟合,实用测试技术,1995,(05)。
[29]曾清红,卢德唐,基于移动最小二乘法的曲线曲面拟合,工程图学学报, 2004,(01)。
[30]李全信,圆曲线的拟合方法与精度分析,北京测绘,2001,(03)。
[31]孔兵,王昭,谭玉山,基于圆拟合的激光光斑中心检测算法,红外与激光工程,2002,(03)。
[32]冯慧君,陶素娟,李隆,基于双线性插值算法的图像放缩技术与实现,计算机应用与软件,2004,(07)。
[33]孙成叶,桑农,张天序,王新赛,图像双线性插值无级放大及其运算量分析,计算机工程,2005,(09)。
[34]尤玉虎,周孝宽,数字图像最佳插值算法研究,中国空间科学技术, 2005,(03)。
[35]王艳莉.插值算法应用在图像缩放中的研究,烟台教育学院学报, 2005,(01)。
[36]孙宇,胡琳娜,曹宁.立方卷积插值法在H.26L中的应用,河海大学常州分校学报,2003,(03)。
[37]曹宁,孙宇,胡琳娜. H.26L中基于双线性和立方卷积的混合插值算法,电路与系统学报,2005,(01)。
[38]王建军,徐西鹏,黄辉.高斯滤波在花岗石表面粗糙度研究中的应用,计量学报,2006,(02)。
[39]许景波,袁怡宝,朴伟英, J.F.Song, T.V.Vorburger.表面粗糙度测量中的高斯滤波快速算法,计量学报,2005,(04)。
[40]王筱艳,汪天富,李德玉,林江莉,一种改进的各向异性高斯滤波算法,西南民族大学学报(自然科学版),2007,(01)。
[41]徐同莹,彭定明,王卫星,改进的直方图均衡化算法,兵工自动化,2006,(07)。
[42]王国权,仲伟波,灰度图像增强算法的改进与实现研究,计算机应用研究,2004,(12)。
[43]吴铁洲,熊才权,直方图匹配图像增强技术的算法研究与实现,湖北工业大学学报,2005,(02)。
[44]江开猛,湛宁,基于灰度直方图的图像增强算法,信阳农业高等专科学校学报,2005,(03)。
[45]赵春燕,郑永果,王向葵,基于直方图的图像模糊增强算法,计算机工程,2005,(12)。
[46]刘云秀,李悦,直方图修改技术增强数字图像方法研究,吉林工程技术师范学院学报,2005,(03)。
[47]张锁平,张春田,基于同态滤波的海表图像照度校正,海洋技术,2007,(01)。
[48]王晓勇,胡福乔,赵宇明,同态滤波在图像角点提取中的应用,计算机工程,2006,(11)。
[49]李琦,王骐,李自勤,李霖,尚铁梁.局部统计同态滤波用于CO2激光成像的图像处理,激光与红外,2002,(04)。
[50]闻莎,游志胜,性能优化的同态滤波空域算法,计算机应用研究,2000,(03)。
[51]王保平,刘怀亮,李南京,谢维信,一种新的自适应图像模糊增强算法,西安电子科技大学学报,2005,(02)。
[52]张家树,李明华,一种新的图象模糊增强技术,西南师范大学学报(自然科学版),1994,(01)。
[53]程茜,胡学龙,宋鸣,一种基于模糊逻辑的图像增强算法,现代电子技术,2005,(16)。
[54]周德龙,潘泉,张洪才,图象模糊边缘检测的改进算法,中国图象图形学报,2001,(04)。
[55]王龙辉,邱道尹,文成林,沈宪章,侯丽亚,一种适度增强的模糊增强算法,郑州工业大学学报,1998,(04)。
[56]李了了,邓善熙,丁兴号,基于大津法的图像分块二值化算法,微计算机信息,2005,(14)。
[57]柴本成,基于最大方差比的图像二值化算法,浙江万里学院学报,2005,(04)。
[58]刘建平,二维最大类间方差和遗传算法在红外图像分割中的应用,浙江理工大学学报,2005,(04)。
[59]曹婧华,冉彦忠,刘沛先,Canny算法在细胞图像边缘检测中的应用,中国医学装备,2007,(01)。
[60]梅跃松,杨树兴,莫波,基于Canny算子的改进的图像边缘检测方法,激光与红外,2006,(06)。
[61]聂祥飞,基于反锐化掩模法的图像增强研究,中国有线电视,2004,(Z2)。
[62] Casey R G, Lecolinenl E. A survey of methods and strategies in character segmention.IEEE trans.PAMI,1996,18(7),p690-709.
[63] Lu Y.Machine printed character segmentation-an overview. P.R.1995 ,28(1),p67一80.
[64] Lu Y.et al. An accurate machine-printed text.U S Conference,1992,p93一105 and efficient system for segmenting Postal Service 5th Advanced Technology.
[65]徐正光,鲍东来,张利欣,基于递归的二值图像连通域像素标记算法,计算机工程,2006,(24)。
[66]李欢,杨捷,求解二值图像连通域的改进算法,计算机与现代化, 2005,(04)。
[67]王亮,黄飞,冯少彤,聂守平,王鸣,一种改进的二值图像像素标记算法,南京师范大学学报(工程技术版),2006,(02)。
[68]张玉姣,史忠科,基于连通体检测及投影法的牌照字符切分。小型微型计算机系统,2004(4 ):564-566。
[69] Richard G.Casey, Eric Lecolinet, A Survey of Methods and Strategies in Character Segmentation . IEEE Transaction On Pattern Analysis And Machine Intelligence.vol.18,no.7,1996(7):690-706.
[70] G.Senl,E.CohenExternal.Word Segmentation of Off-Line Handwriten Text Lines.Pattern Recognition.vol.27,no.1,1994(1):41一52.
[71]邵平,杨路明,黄海滨,基于积分图像的灰度分布标准化快速算法,计算机应用研究,2007,(03)。
[72]赵丽红,人脸检测和识别算法的研究与实现,博士学位论文,东北大学, 2006。
[73]芮挺,沈春林,张金林.车牌识别中倾斜牌照的快速矫正算法,计算机工程,2004,(13)。
[74]路小波,包明,黄卫,基于投影的车牌倾斜检测方法,交通运输工程与信息学报,2004,(04)。
[75]杨立刚,张兴会,李兰友,车牌照字符倾斜校正方法的研究,仪器仪表学报,2004,(S1)。
[76]娄正良,中文邮政地址识别研究,博士学位论文,中国科学院研究生院(计算技术研究所),,2004。
[77]梁涌,印刷体汉字识别系统的研究与实现,博士学位论文,西北工业大学,2006。
[78]吴晓兵,印刷体光学字符识别的研究,博士学位论文,.北京中国科学院自动化研究所,2003。
[79]荆涛,王仲,光学字符识别技术与展望,计算机工程,2003,(02)。
[80]张皓,OCR文字识别与图文库检索技术初探,大学图书情报学刊,2003,(03)。
[81]凌山,OCR汉字识别技术,工程设计CAD与智能建筑,1999,(06)。
[82]林东胜,OCR汉字识别技术进展,职业教育研究,2004,(S1)。
[83]吴丽芸,王文伟,张平,陈俊,手写混合字符集识别的多特征多级分类器设计,计算机应用,2005,(12)。
[84]卢海霞,杨耀权,苏杰,周晓辉,基于图像处理的手写体数字识别,仪器仪表与分析监测,2005,(03)。
[85]赵万鹏,古乐野,基于Adaboost的手写体数字识别,计算机应用,2005,(10)。
[86]韩宏,多分类器组合及其在手写体数字识别中的应用,博士学位论文,南京理工大学,2000。
[87]叶晨洲,廖金周,车辆牌照字符识别系统,计算机系统应用,1999年第5期:1012。
[88]刘效静,成瑜.汽车牌照自动识别技术研究南京航空航天大学学报,1998,10(5)。
[89]黄风岗,宋克欧,模式识别,哈尔滨工程大学出版社,1998年。
[90]边肇棋,张学工等,模式识别,第二版清华大学出版社,2000年。
[91]章毓晋,图象分割,科学出版社,2001年。
[92] Toru Wakahara, Kazumi Odaka, Adaptive Normalization of Handwritten Characters Using Global/Local Affine Transformation, IEEE Trans. Pattem Analysis and Machine Intelligence, 20(12),1332-1341,(1998).
[93] Jinhai Cai and Zhi-Qiang Liu, Integration of structural and Statistical Information for Unconstrained Handwritten Numeral Recognition, IEEE Trans . Pattem Analysis and Machine Intelligence, 2 1 (3), 263-270( 1999).
[94] Bailing Zhang, Minyue Fu, Hong Yan, and Marwan A.Jabri,Handwritten Digit Reconition by Adaptive-Subspace Self-Organizing Map, IEEE Trans. Neural Networks, 10(4),939-953(July, 1999).
[95] Hee-Seon Park Seong-Wan Lees, off-line recognition ofLarge-Set Handwritten Characters With Multiple Hidden Markov Models, Pattem Recognition, 29(4), 663-675 (1 996).
[96] Y.C Chim, A.A.Kassim, and Y.Ibrahim, Character Recognition Using Statistical Moments, Image and Vision Computing, 17,299-307 (1999).
[97].D.Trier,Anil K.Jain and Torfinn Taxt, Feature Extraction Methods for Character Recognition-A Survey, Pattem recognition, 29(4), 641-662( 1996).
[98] Adnan Amin, Humoudal-Sadoun and Stephen Fischer,Hand-Printed Arabic Character Recogition System Using An Artificial Network, Pattem Recognition, Vo1.29,No.4, PP663-675, (1 996).
[99] Jun Sun; Yinghai Wang; Tianhong Pan; Genetic Neural Network and Its Application in Recognition of Tire Code, Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on 6-8 April 2008 Page(s):842– 846.
[100] U.Pal, A. Belaid, B.B.Chaudhuri,“A system for Bangla Handwritten Numeral Recognition”, Int Conf. On Knowledge Based Computer Systems, India, 2002.
[101] B.B. Chaudhuri, U. Pal,“A complete printed Bangla OCR system”, Pattern Recognition, Vol.31, pp.531-549, 1998.
[102] U. Pal and B.B. Chaudhuri,“Automatic Recognition of Unconstrained Off-Line Bangla Handwritten Numerals”, Advances in Multimodal Interfaces - ICMI 2000: Third International Conference, China, pp.371-378, 2000.
[103] U. Bhattacharya, T. K. Das, A. Dutta, S. K. Parui and B. B. Chaudhuri,“A Hybrid scheme for handwritten numeral recognition based on Self Organizing Network and MLP”, IJPRAI,Volume 16, pp.845-864, 2002.
[104] A. Majumdar and B.B. Chaudhuri,“A MLP Classifier for Both Printed and Handwritten Bangla Numeral Recognition”, ICVGIP 2006, LNCS 4338, pp.796-804, 2006.
[105] K.Roy, T.Pal, U.Pal and F.Kimura,“A system for Bangla Handwritten Numeral Recognition based of Directional Feature”, Proc. Int. Conf. on Cognition and Recognition, pp. 497-505, 2005.
[106] H.Liu and R.Setiono,“Chi2: Feature selection and discretization of numeric attributes”, Proc.7th IEEE Intl. Conf. Tools with Al, pp. 388-391, 1995.
[107] J. R. Quinlan,“Induction of Decision trees”, Machine 1160 Learning, Vol. 6, pp. 81-106, 1986.
[108] T. Srinivasan, M.Sathish, Vamsi G. Krishna, Vinodh Krishnamoorthy,“TC-ID3: A TESTCODE Based ID3 Classifier for Protein Coding Region Identification”, CIMCA/IAWTIC2006, pp. 110.
[109] F. Provost, P. Domingos,“Tree Induction for Probability-Based Ranking”, Machine Learning, Vol. 52, No. 3, pp. 199-215, 2003.
[110] F. Yoav, E. S. Robert,“A decision-theoretic generalization of on-line learning and an application to boosting”, Journal of Computer and System Sciences, Vol. 55, No. 1, pp. 119-139, 1997.
[111] Y. Freund, R. E. Schapire,“A short introduction to Boosting”, Journal of Japanese Society for Artificial Intelligence, Vol. 14, No. 5, pp. 771-780, 1999.
[112] Soon-man choi., "A segmentation-free recognition of handwritten touching numeral pairs using modular neural network," International Journal of Pattern Recognition and Artificial Intelligence, 2001,Vol.15, No. 6:946-966.
[113] Feng Lu ,Wei Lu, Handwritten Numeral Recognition Based on DCT Coefficients and Neural Network, IEEE, 2005, 219-221.
[114]Trier Oivind,JainAnil.k.,Taxt Torfinn,Feature extraction methods for character recognition----A Survey,Pattern Recognition,1996,29(4):641-662.
[115] KeLiu,C.Y.Suen et al,Automatic Extraction of Baselines and Data form Check Images,Automatic Bankcheck Processing,World Scientific Publishing Co.Pte.Ltd.,1997,p213-236.
[116] Roberts L G. Machine perception of three-dimensional solids. Optical and Electro Information Processing, 1 965: 159-197.
[117] Peli T, Malah D. A study of edge determination algorithms.CGIP,1982,20:1-20.
[118] Buf J M H, Campbell T G. A quantiative comparison of edge-preserving smoothing techniques. Signal Processing,1990,21:289301
[119] Wilkinson M H F. Optimizing edge detectors for robust automatic threshold selection. GMIP,1998,60(4):385401
[120] Williams D J,Shah M. Edge characterization using normalized edge detector CVGIP,1993,55:315328
[121] Fu K S,Mui J K. A survey on image segmentation. Pattern Recognition,1981,13:3-16.
[122] Haralick R M,Shapiro L G. Image segmentation techniques.CVGIP,1985,29:100132.
[123] DavisL S .A survey of edge detection techniques.C GIP,1975,4: 248270.
[124]刘文耀,数字图像采集与处理,电子工业出版社,2007年。
[125]冈萨雷斯,数字图像处理第二版,电子工业出版社。
[126]郁道银,谈恒英,工程光学,北京:机械工业出版社,2006。
[127]陈黎,黄心汉,王敏,李炜,基于聚类分析的车牌字符分割方法,计算机工程与应用,2002,6。
[128]周开军,陈三宝,徐江陵,复杂背景下的车牌定位和字符分割研究,计算机工程,2007,第33卷第4期。
[129] S.Mori,C.YSuen and K.Yamamoto. Historical Review of OCR Research and Development. Proceedings of the IEEE.1992,80 :1029-1058.
[130] S.V. Rice, G. Nagy and T.A. Nartker. Optical Character Recognition: An Illustrated guide to the frontier. Kluwer Academic Publishers,1999.
[131]孙广玲,手写字符识别中关键技术研究,博士学位论文,哈尔滨工业大学,2005年。
[132]Zhong Y, Karu k, Jain A K. Locating text in complex color images. Pattern Recognition, 1995, 28: 1223-1236.
[133]Jain A K, Yu B. Automatic text location in images and video frames. Pattern recognition, 1998, 31(12):2055-2076.
[134]李闯,丁晓青,吴佑寿,基于边缘的字符串定位算法,清华大学学报,2005,45(10):1335-1338。
[135]王冠,敖志刚,刘永跃,王真军,基于快速连通域标记的车牌字符分割,计算机与现代化,2007,第6期。
[136]王琳琬,杨扬,颉斌,杨毅,基于连通域单元和穿越算法的汉字切分,信息技术,2004,28(4):30-35。
[2]刘连云,以胎号为中心的轮胎管理系统,轮胎工业,2003,23:392-396。
[3]孙俊,李正明,杨继昌,汽车轮胎信息识别与管理系统的设计,江苏大学学报(自然科学版),2004,25(5):397– 400。
[4]朱金陆,黄有平等,激光轮胎打码机的开发及应用,2007年第27卷第1期,p61-62。
[5] Jianhai Cao:A Study on Recognizing and Checking of the Pressed Protuberant Character on a Metal Label, Jinan:Shangdong University,2004(In Chinses).
[6] GunSeo koo,HaeSeok Oh , MCBP Neural Network Formation for Efficient Recognition of Tire Sorting Code by Image Processing,1996 IEEE,T6-PC6.1 - T6-PC6.4,P524-527.
[7]王方智,条码在轮胎工业中的应用,轮胎工业,1999, 19: 176-177。
[8]陈礼宾,朱金陆,陈绍文,条码技术在轮胎生产管理中的应用,轮胎工业,2005年第25卷第10期,p623-625。
[9] BYTEWISE,“Automatic Tire Identification and DOT Code Recognition Using Very-High-Speed Laser Profile Sensors”http://www.bytewise.com/files/DOT_Code_Recognition_IntroV4.pdf.
[10]王先波,轮胎胎号自动识别录入装置的设计与软件实现,华南理工大学硕士学位论文,2002年。
[11]于清溪,工程轮胎生产现状与发展前景,橡塑技术与装备,2007年第33卷,p1-15。
[12]蔡为民,国内外轮胎发展分析,2007年第27卷第12期,p707-711。
[13]邓海燕,轮胎产品DOT认证概述,2002年第22卷第7期,p394-397。
[14]卢晋人,黄元庆,激光三角法测量表面形貌,厦门大学学报(自然科学版),2004年第43卷第l期。
[15]周祥,轮胎胎号自动识别系统的研究与设计,江苏大学硕士学位论文,2005年。
[16]冯慧平,蔡习训等,LED阵列光源之照明设计,中国机械工程学会第二十四届全国学术研讨会论文集,论文编号:E05-0002。
[17]胡海蕾,LED照明光学系统的设计及其阵列光照度分布研究,福建师范大学硕士学位论文,2005年。
[18] J.R.Coaton,A.M.Marsden,光源与照明,第四版,上海复旦大学出版社,2000。
[19]刘潮东,史忠科,各向异性扩散-中值滤波在红外图像处理中的应用[J]弹箭与制导学报,2006,(03)。
[20]张文攀,吴军辉,朱震,李华,王强,基于准十字窗口的中值滤波法在红外图像处理中的应用,电光与控制,2006,(01)。
[21]仲兆满,韩其睿,王电化,一种基于方向梯度的图像滤波算法,淮阴师范学院学报(自然科学版),2005,(03)。
[22]李冰,王艳,耿则勋,一种改进的遥感图像自适应加权滤波算法,测绘学院学报,2005,(02)。
[23]张霞,葛芦生,自适应中值滤波算法的研究与应用,微计算机信息,2007,(06)。
[24]薛小强,使用迭代重加权最小二乘法求解平面度误差,中国农机化,2005,(03)。
[25]陈良泽,用矩阵运算实现曲线拟合中的最小二乘法,传感器技术,2001,(02)。
[26]刘海香,张彩明,梁秀霞,平面上散乱数据点的二次曲线拟合,计算机辅助设计与图形学学报,2004,(11)。
[27]徐国旺,廖明潮,拟合圆的几种方法,武汉工业学院学报,2002,(04)。
[28]田社平,张守愚,李定学,俞朴,平面圆圆心及半径的最小二乘拟合,实用测试技术,1995,(05)。
[29]曾清红,卢德唐,基于移动最小二乘法的曲线曲面拟合,工程图学学报, 2004,(01)。
[30]李全信,圆曲线的拟合方法与精度分析,北京测绘,2001,(03)。
[31]孔兵,王昭,谭玉山,基于圆拟合的激光光斑中心检测算法,红外与激光工程,2002,(03)。
[32]冯慧君,陶素娟,李隆,基于双线性插值算法的图像放缩技术与实现,计算机应用与软件,2004,(07)。
[33]孙成叶,桑农,张天序,王新赛,图像双线性插值无级放大及其运算量分析,计算机工程,2005,(09)。
[34]尤玉虎,周孝宽,数字图像最佳插值算法研究,中国空间科学技术, 2005,(03)。
[35]王艳莉.插值算法应用在图像缩放中的研究,烟台教育学院学报, 2005,(01)。
[36]孙宇,胡琳娜,曹宁.立方卷积插值法在H.26L中的应用,河海大学常州分校学报,2003,(03)。
[37]曹宁,孙宇,胡琳娜. H.26L中基于双线性和立方卷积的混合插值算法,电路与系统学报,2005,(01)。
[38]王建军,徐西鹏,黄辉.高斯滤波在花岗石表面粗糙度研究中的应用,计量学报,2006,(02)。
[39]许景波,袁怡宝,朴伟英, J.F.Song, T.V.Vorburger.表面粗糙度测量中的高斯滤波快速算法,计量学报,2005,(04)。
[40]王筱艳,汪天富,李德玉,林江莉,一种改进的各向异性高斯滤波算法,西南民族大学学报(自然科学版),2007,(01)。
[41]徐同莹,彭定明,王卫星,改进的直方图均衡化算法,兵工自动化,2006,(07)。
[42]王国权,仲伟波,灰度图像增强算法的改进与实现研究,计算机应用研究,2004,(12)。
[43]吴铁洲,熊才权,直方图匹配图像增强技术的算法研究与实现,湖北工业大学学报,2005,(02)。
[44]江开猛,湛宁,基于灰度直方图的图像增强算法,信阳农业高等专科学校学报,2005,(03)。
[45]赵春燕,郑永果,王向葵,基于直方图的图像模糊增强算法,计算机工程,2005,(12)。
[46]刘云秀,李悦,直方图修改技术增强数字图像方法研究,吉林工程技术师范学院学报,2005,(03)。
[47]张锁平,张春田,基于同态滤波的海表图像照度校正,海洋技术,2007,(01)。
[48]王晓勇,胡福乔,赵宇明,同态滤波在图像角点提取中的应用,计算机工程,2006,(11)。
[49]李琦,王骐,李自勤,李霖,尚铁梁.局部统计同态滤波用于CO2激光成像的图像处理,激光与红外,2002,(04)。
[50]闻莎,游志胜,性能优化的同态滤波空域算法,计算机应用研究,2000,(03)。
[51]王保平,刘怀亮,李南京,谢维信,一种新的自适应图像模糊增强算法,西安电子科技大学学报,2005,(02)。
[52]张家树,李明华,一种新的图象模糊增强技术,西南师范大学学报(自然科学版),1994,(01)。
[53]程茜,胡学龙,宋鸣,一种基于模糊逻辑的图像增强算法,现代电子技术,2005,(16)。
[54]周德龙,潘泉,张洪才,图象模糊边缘检测的改进算法,中国图象图形学报,2001,(04)。
[55]王龙辉,邱道尹,文成林,沈宪章,侯丽亚,一种适度增强的模糊增强算法,郑州工业大学学报,1998,(04)。
[56]李了了,邓善熙,丁兴号,基于大津法的图像分块二值化算法,微计算机信息,2005,(14)。
[57]柴本成,基于最大方差比的图像二值化算法,浙江万里学院学报,2005,(04)。
[58]刘建平,二维最大类间方差和遗传算法在红外图像分割中的应用,浙江理工大学学报,2005,(04)。
[59]曹婧华,冉彦忠,刘沛先,Canny算法在细胞图像边缘检测中的应用,中国医学装备,2007,(01)。
[60]梅跃松,杨树兴,莫波,基于Canny算子的改进的图像边缘检测方法,激光与红外,2006,(06)。
[61]聂祥飞,基于反锐化掩模法的图像增强研究,中国有线电视,2004,(Z2)。
[62] Casey R G, Lecolinenl E. A survey of methods and strategies in character segmention.IEEE trans.PAMI,1996,18(7),p690-709.
[63] Lu Y.Machine printed character segmentation-an overview. P.R.1995 ,28(1),p67一80.
[64] Lu Y.et al. An accurate machine-printed text.U S Conference,1992,p93一105 and efficient system for segmenting Postal Service 5th Advanced Technology.
[65]徐正光,鲍东来,张利欣,基于递归的二值图像连通域像素标记算法,计算机工程,2006,(24)。
[66]李欢,杨捷,求解二值图像连通域的改进算法,计算机与现代化, 2005,(04)。
[67]王亮,黄飞,冯少彤,聂守平,王鸣,一种改进的二值图像像素标记算法,南京师范大学学报(工程技术版),2006,(02)。
[68]张玉姣,史忠科,基于连通体检测及投影法的牌照字符切分。小型微型计算机系统,2004(4 ):564-566。
[69] Richard G.Casey, Eric Lecolinet, A Survey of Methods and Strategies in Character Segmentation . IEEE Transaction On Pattern Analysis And Machine Intelligence.vol.18,no.7,1996(7):690-706.
[70] G.Senl,E.CohenExternal.Word Segmentation of Off-Line Handwriten Text Lines.Pattern Recognition.vol.27,no.1,1994(1):41一52.
[71]邵平,杨路明,黄海滨,基于积分图像的灰度分布标准化快速算法,计算机应用研究,2007,(03)。
[72]赵丽红,人脸检测和识别算法的研究与实现,博士学位论文,东北大学, 2006。
[73]芮挺,沈春林,张金林.车牌识别中倾斜牌照的快速矫正算法,计算机工程,2004,(13)。
[74]路小波,包明,黄卫,基于投影的车牌倾斜检测方法,交通运输工程与信息学报,2004,(04)。
[75]杨立刚,张兴会,李兰友,车牌照字符倾斜校正方法的研究,仪器仪表学报,2004,(S1)。
[76]娄正良,中文邮政地址识别研究,博士学位论文,中国科学院研究生院(计算技术研究所),,2004。
[77]梁涌,印刷体汉字识别系统的研究与实现,博士学位论文,西北工业大学,2006。
[78]吴晓兵,印刷体光学字符识别的研究,博士学位论文,.北京中国科学院自动化研究所,2003。
[79]荆涛,王仲,光学字符识别技术与展望,计算机工程,2003,(02)。
[80]张皓,OCR文字识别与图文库检索技术初探,大学图书情报学刊,2003,(03)。
[81]凌山,OCR汉字识别技术,工程设计CAD与智能建筑,1999,(06)。
[82]林东胜,OCR汉字识别技术进展,职业教育研究,2004,(S1)。
[83]吴丽芸,王文伟,张平,陈俊,手写混合字符集识别的多特征多级分类器设计,计算机应用,2005,(12)。
[84]卢海霞,杨耀权,苏杰,周晓辉,基于图像处理的手写体数字识别,仪器仪表与分析监测,2005,(03)。
[85]赵万鹏,古乐野,基于Adaboost的手写体数字识别,计算机应用,2005,(10)。
[86]韩宏,多分类器组合及其在手写体数字识别中的应用,博士学位论文,南京理工大学,2000。
[87]叶晨洲,廖金周,车辆牌照字符识别系统,计算机系统应用,1999年第5期:1012。
[88]刘效静,成瑜.汽车牌照自动识别技术研究南京航空航天大学学报,1998,10(5)。
[89]黄风岗,宋克欧,模式识别,哈尔滨工程大学出版社,1998年。
[90]边肇棋,张学工等,模式识别,第二版清华大学出版社,2000年。
[91]章毓晋,图象分割,科学出版社,2001年。
[92] Toru Wakahara, Kazumi Odaka, Adaptive Normalization of Handwritten Characters Using Global/Local Affine Transformation, IEEE Trans. Pattem Analysis and Machine Intelligence, 20(12),1332-1341,(1998).
[93] Jinhai Cai and Zhi-Qiang Liu, Integration of structural and Statistical Information for Unconstrained Handwritten Numeral Recognition, IEEE Trans . Pattem Analysis and Machine Intelligence, 2 1 (3), 263-270( 1999).
[94] Bailing Zhang, Minyue Fu, Hong Yan, and Marwan A.Jabri,Handwritten Digit Reconition by Adaptive-Subspace Self-Organizing Map, IEEE Trans. Neural Networks, 10(4),939-953(July, 1999).
[95] Hee-Seon Park Seong-Wan Lees, off-line recognition ofLarge-Set Handwritten Characters With Multiple Hidden Markov Models, Pattem Recognition, 29(4), 663-675 (1 996).
[96] Y.C Chim, A.A.Kassim, and Y.Ibrahim, Character Recognition Using Statistical Moments, Image and Vision Computing, 17,299-307 (1999).
[97].D.Trier,Anil K.Jain and Torfinn Taxt, Feature Extraction Methods for Character Recognition-A Survey, Pattem recognition, 29(4), 641-662( 1996).
[98] Adnan Amin, Humoudal-Sadoun and Stephen Fischer,Hand-Printed Arabic Character Recogition System Using An Artificial Network, Pattem Recognition, Vo1.29,No.4, PP663-675, (1 996).
[99] Jun Sun; Yinghai Wang; Tianhong Pan; Genetic Neural Network and Its Application in Recognition of Tire Code, Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on 6-8 April 2008 Page(s):842– 846.
[100] U.Pal, A. Belaid, B.B.Chaudhuri,“A system for Bangla Handwritten Numeral Recognition”, Int Conf. On Knowledge Based Computer Systems, India, 2002.
[101] B.B. Chaudhuri, U. Pal,“A complete printed Bangla OCR system”, Pattern Recognition, Vol.31, pp.531-549, 1998.
[102] U. Pal and B.B. Chaudhuri,“Automatic Recognition of Unconstrained Off-Line Bangla Handwritten Numerals”, Advances in Multimodal Interfaces - ICMI 2000: Third International Conference, China, pp.371-378, 2000.
[103] U. Bhattacharya, T. K. Das, A. Dutta, S. K. Parui and B. B. Chaudhuri,“A Hybrid scheme for handwritten numeral recognition based on Self Organizing Network and MLP”, IJPRAI,Volume 16, pp.845-864, 2002.
[104] A. Majumdar and B.B. Chaudhuri,“A MLP Classifier for Both Printed and Handwritten Bangla Numeral Recognition”, ICVGIP 2006, LNCS 4338, pp.796-804, 2006.
[105] K.Roy, T.Pal, U.Pal and F.Kimura,“A system for Bangla Handwritten Numeral Recognition based of Directional Feature”, Proc. Int. Conf. on Cognition and Recognition, pp. 497-505, 2005.
[106] H.Liu and R.Setiono,“Chi2: Feature selection and discretization of numeric attributes”, Proc.7th IEEE Intl. Conf. Tools with Al, pp. 388-391, 1995.
[107] J. R. Quinlan,“Induction of Decision trees”, Machine 1160 Learning, Vol. 6, pp. 81-106, 1986.
[108] T. Srinivasan, M.Sathish, Vamsi G. Krishna, Vinodh Krishnamoorthy,“TC-ID3: A TESTCODE Based ID3 Classifier for Protein Coding Region Identification”, CIMCA/IAWTIC2006, pp. 110.
[109] F. Provost, P. Domingos,“Tree Induction for Probability-Based Ranking”, Machine Learning, Vol. 52, No. 3, pp. 199-215, 2003.
[110] F. Yoav, E. S. Robert,“A decision-theoretic generalization of on-line learning and an application to boosting”, Journal of Computer and System Sciences, Vol. 55, No. 1, pp. 119-139, 1997.
[111] Y. Freund, R. E. Schapire,“A short introduction to Boosting”, Journal of Japanese Society for Artificial Intelligence, Vol. 14, No. 5, pp. 771-780, 1999.
[112] Soon-man choi., "A segmentation-free recognition of handwritten touching numeral pairs using modular neural network," International Journal of Pattern Recognition and Artificial Intelligence, 2001,Vol.15, No. 6:946-966.
[113] Feng Lu ,Wei Lu, Handwritten Numeral Recognition Based on DCT Coefficients and Neural Network, IEEE, 2005, 219-221.
[114]Trier Oivind,JainAnil.k.,Taxt Torfinn,Feature extraction methods for character recognition----A Survey,Pattern Recognition,1996,29(4):641-662.
[115] KeLiu,C.Y.Suen et al,Automatic Extraction of Baselines and Data form Check Images,Automatic Bankcheck Processing,World Scientific Publishing Co.Pte.Ltd.,1997,p213-236.
[116] Roberts L G. Machine perception of three-dimensional solids. Optical and Electro Information Processing, 1 965: 159-197.
[117] Peli T, Malah D. A study of edge determination algorithms.CGIP,1982,20:1-20.
[118] Buf J M H, Campbell T G. A quantiative comparison of edge-preserving smoothing techniques. Signal Processing,1990,21:289301
[119] Wilkinson M H F. Optimizing edge detectors for robust automatic threshold selection. GMIP,1998,60(4):385401
[120] Williams D J,Shah M. Edge characterization using normalized edge detector CVGIP,1993,55:315328
[121] Fu K S,Mui J K. A survey on image segmentation. Pattern Recognition,1981,13:3-16.
[122] Haralick R M,Shapiro L G. Image segmentation techniques.CVGIP,1985,29:100132.
[123] DavisL S .A survey of edge detection techniques.C GIP,1975,4: 248270.
[124]刘文耀,数字图像采集与处理,电子工业出版社,2007年。
[125]冈萨雷斯,数字图像处理第二版,电子工业出版社。
[126]郁道银,谈恒英,工程光学,北京:机械工业出版社,2006。
[127]陈黎,黄心汉,王敏,李炜,基于聚类分析的车牌字符分割方法,计算机工程与应用,2002,6。
[128]周开军,陈三宝,徐江陵,复杂背景下的车牌定位和字符分割研究,计算机工程,2007,第33卷第4期。
[129] S.Mori,C.YSuen and K.Yamamoto. Historical Review of OCR Research and Development. Proceedings of the IEEE.1992,80 :1029-1058.
[130] S.V. Rice, G. Nagy and T.A. Nartker. Optical Character Recognition: An Illustrated guide to the frontier. Kluwer Academic Publishers,1999.
[131]孙广玲,手写字符识别中关键技术研究,博士学位论文,哈尔滨工业大学,2005年。
[132]Zhong Y, Karu k, Jain A K. Locating text in complex color images. Pattern Recognition, 1995, 28: 1223-1236.
[133]Jain A K, Yu B. Automatic text location in images and video frames. Pattern recognition, 1998, 31(12):2055-2076.
[134]李闯,丁晓青,吴佑寿,基于边缘的字符串定位算法,清华大学学报,2005,45(10):1335-1338。
[135]王冠,敖志刚,刘永跃,王真军,基于快速连通域标记的车牌字符分割,计算机与现代化,2007,第6期。
[136]王琳琬,杨扬,颉斌,杨毅,基于连通域单元和穿越算法的汉字切分,信息技术,2004,28(4):30-35。
© 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 |