运动模糊车牌图像恢复、定位与校正的研究
|
摘要
随着计算机和数字图像处理技术的发展,车牌自动识别系统己成为智能交通系统的重要组成部分。
运动模糊图像车牌识别系统的关键技术在于数字图像预处理技术、车牌定位技术和智能字符识别技术。本文应用运动模糊方向和尺度检测算法、车牌定位技术、字符分割技术、神经网络识别技术等来解决车牌识别问题。确定车牌识别的环节与流程,根据各环节要求实现的功能,筛选方法和算法,对关键环节和算法通过实验,进行比较分析,对有关算法进行了改进或提出新的算法。
首先,基于图像的方向微分原理以及基于自相关的点扩散函数尺度鉴别的原理,提出了求极值的优化算法,准确而迅速的鉴别出运动模糊参数(运动模糊方向和运动模糊距离)。
其次,对基于车牌灰度分布特征的车牌定位算法作了改进,扩大了分割区域的宽度,综合其他方法如霍夫变换等对可能产生的多个候选区域进行筛选判别,使之对发生倾斜的车牌或者背景较为复杂的车牌图像也能正确分割。
再次,基于单应性矩阵方法研究了图像校正技术。该方法的关键问题在于边缘检测及寻找边缘的交点。本文针对发生倾斜或仿射形变的车牌图像的校正提出了一种自动化的边缘提取算法。该方法通过对霍夫变换得到的直线进行合并、分类、排序等方法来自动获取图像边缘并计算相应的交点。对校正后的图像因为长宽比例不同而产生的问题,作了分析和相应处理。该方法保留了单应性矩阵恢复算法的方便性,同时速度更快,取得的效果也比较良好。
最后,针对字符分割,提出了一种剔除车牌边框的算法,该方法能够有效的除去车牌图像的边框,利于后续的字符分割。
The License Plate Recognition (LPR) system becomes an important part of Intelligent Traffic System(ITS) with the rapid development of computer science and digital image processing.
The essential technology of the recognition of the motion-blurred images of vehicle's license plate system lies in the digital image pretreatment technology, the plate location technology and the intelligent character recognition technology. The paper applies the identification of motion blur direction and the blur extent, the license location technology, the character division technology, the license character recognition technology based on BP networks to the LPR system. By considering the processes of the vehicle's license plate identification, screening methods and algorithms according to the demands of each link function, the paper makes a comparative analysis of the key links and algorithms by experiments, and the related algorithms are improved or some new algorithms were put forward.
Firstly, improve the identify approach for motion-blur parameters (motion-blur direction and motion-blur extent)from motion-blurred image based on directional derivation and autocorrelation method, put forward a optimized algorithm to search the extremum, which makes the solution fast.
Secondly, approved the license plate location algorithm based on the characteristic of license plate’s gray-scale. Extend the width of the segmentation area and synthesize other methods such as hough transfer to screen the candidate regions to make it successful in handling the declining images or images with complicated background.
Thirdly, Study the image calibration based on homography matrix method. The key of this method is to detect edges and their intersections. A new automatic edge detection method was put forward to the calibration of license plates. This method obtains the edges of pictures and their intersections through merging, sorting and ranging based on hough transformation automatically. For the problems result from different proportions of length and width, this paper also gave an analysis and made relative processing. Simulation result shows that this method has good performance as well as preserving the convenience of homography matrix calibration.
At last, to the problem of character division, an edge rejecting algorithm was put forward. This algorithm can reject the edges of vehicle's license plate efficiently, which is very convenient for the following treatments.
运动模糊图像车牌识别系统的关键技术在于数字图像预处理技术、车牌定位技术和智能字符识别技术。本文应用运动模糊方向和尺度检测算法、车牌定位技术、字符分割技术、神经网络识别技术等来解决车牌识别问题。确定车牌识别的环节与流程,根据各环节要求实现的功能,筛选方法和算法,对关键环节和算法通过实验,进行比较分析,对有关算法进行了改进或提出新的算法。
首先,基于图像的方向微分原理以及基于自相关的点扩散函数尺度鉴别的原理,提出了求极值的优化算法,准确而迅速的鉴别出运动模糊参数(运动模糊方向和运动模糊距离)。
其次,对基于车牌灰度分布特征的车牌定位算法作了改进,扩大了分割区域的宽度,综合其他方法如霍夫变换等对可能产生的多个候选区域进行筛选判别,使之对发生倾斜的车牌或者背景较为复杂的车牌图像也能正确分割。
再次,基于单应性矩阵方法研究了图像校正技术。该方法的关键问题在于边缘检测及寻找边缘的交点。本文针对发生倾斜或仿射形变的车牌图像的校正提出了一种自动化的边缘提取算法。该方法通过对霍夫变换得到的直线进行合并、分类、排序等方法来自动获取图像边缘并计算相应的交点。对校正后的图像因为长宽比例不同而产生的问题,作了分析和相应处理。该方法保留了单应性矩阵恢复算法的方便性,同时速度更快,取得的效果也比较良好。
最后,针对字符分割,提出了一种剔除车牌边框的算法,该方法能够有效的除去车牌图像的边框,利于后续的字符分割。
The License Plate Recognition (LPR) system becomes an important part of Intelligent Traffic System(ITS) with the rapid development of computer science and digital image processing.
The essential technology of the recognition of the motion-blurred images of vehicle's license plate system lies in the digital image pretreatment technology, the plate location technology and the intelligent character recognition technology. The paper applies the identification of motion blur direction and the blur extent, the license location technology, the character division technology, the license character recognition technology based on BP networks to the LPR system. By considering the processes of the vehicle's license plate identification, screening methods and algorithms according to the demands of each link function, the paper makes a comparative analysis of the key links and algorithms by experiments, and the related algorithms are improved or some new algorithms were put forward.
Firstly, improve the identify approach for motion-blur parameters (motion-blur direction and motion-blur extent)from motion-blurred image based on directional derivation and autocorrelation method, put forward a optimized algorithm to search the extremum, which makes the solution fast.
Secondly, approved the license plate location algorithm based on the characteristic of license plate’s gray-scale. Extend the width of the segmentation area and synthesize other methods such as hough transfer to screen the candidate regions to make it successful in handling the declining images or images with complicated background.
Thirdly, Study the image calibration based on homography matrix method. The key of this method is to detect edges and their intersections. A new automatic edge detection method was put forward to the calibration of license plates. This method obtains the edges of pictures and their intersections through merging, sorting and ranging based on hough transformation automatically. For the problems result from different proportions of length and width, this paper also gave an analysis and made relative processing. Simulation result shows that this method has good performance as well as preserving the convenience of homography matrix calibration.
At last, to the problem of character division, an edge rejecting algorithm was put forward. This algorithm can reject the edges of vehicle's license plate efficiently, which is very convenient for the following treatments.
引文
[1] 王丰元, 计算机视觉在交通工程测量中的应用,中国公路学报, 15(7), 1999, P32-34
[2] 张炜,王庆,赵荣椿, 汽车牌照实时识别,信号处理, 16(4), P372-375
[3] 张中, 汉字识别技术综述, 语言文字应用, No.2, 1997
[4] 吴佑寿,丁晓青, 汉字识别原理方法与实现, 高等教育出版社, 1992
[5] 胡家忠, 计算机文字识别技术, 气象出版社, 1994
[6] K. Mori and I. Masuda, Advances in Recognition of Chinese Characters, Proc. Of 5th Inter. Conf. on Pattern Recognition (1980), P692-720
[7] Q. R. Wang, C. Y. Sun, Analysis and Design of a Decision Tree Based on Entroy Reduction and Its Application to Large Character Set Recognition, IEEE Trans. Vol. PAMI-6 No. 4(1984), P407-417
[8] Michio Umedu, Recognition of Multi-Font Printed Chinese Character, Proc.6 th IJCPR(1982), P793-796
[9] V. K. Govindan, Character Recognition- A Review, Pattern Recognition, 23(7), 1990, P671-675
[10] 郑南宁,张西宁,戴莹,朱海安,行驶车辆牌照自动识别系统,西安交通大学学报,1991,25(1),43-53
[11] 叶晨洲,车辆牌照字符识别系统,计算机系统应用,1999,Vol.5,P10-13
[12] V. K. Govindan, Character Recognition-A Review, Pattern Recognition, 23(7), 1990, P676-683
[13] 黄德双,神经模式识别系统理论,电子工业出版社,北京,1996
[14] 王建平,姜滔,朱程辉, 基于小波和矩的图像字符特征提取方法研究,信号处理,已投
[15] 赵健,俞卞章,小波与神经网络在模式识别中的应用,仪器仪表学报, 2001.6
[16] 是湘全,何苑凌,蔡孟波,遗传算法在车牌定位中的应用,公路交通科技, 2000(4)
[17] 黎明,杨小芹,刘高航, 基于多个前向神经网络和遗传算法的边界检测法, 南昌航空工业学院学报, 2004(6)
[18] 黎明,严超华,刘高航,基于前向神经网络和 Hopfield 反馈神经网络的边界检测法,中国图像图形学报, 1999(8)
[19]张汉江,曹焱,黄升华等, 模糊 ART 神经网络在目标运动识别中的应用, 模糊系统与数学, 1998(4).
[20] 余玉梅,熊汉, 模糊模式是方法研究,云南民族学院学报(自然科学版), 1998(1)
[21] 张得喜,马少平等, 基于统计与神经元方法相组合的手写体相似字识别, 中文信息学报,21(2), 1999
[22] 陆浩远,杨源远, 手写体汉字识别问题综述, 计算机应用与软件, 11(2), 1992,P1-8
[23] 中国人工智能学会,中国人工智能进展,北京邮电大学出版社,2001,P1-6
[24] S C Som. Analysis of the effect linear smear on photographic images. Opt. Soc. Am., 1971, 61,P859-864.
[25] O Header, S R Rotman, N S Kopeika. Target acquisition modeling of forward-motion considerations for airborne reconnaissance over hostile territory. Opt. Eng., 1994, 22,P3106-3117.
[26] O header, I Dror, N S Kopeika. Image resolution limits resulting from mechanical vibration. Opt. Eng., 1994, 33, P566-578.
[27] 李红阳,运动图像恢复 [工程硕士学位论文], 北京,清华大学,2002.
[28] 马明,运动模糊图像的判定与恢复 [硕士学位论文], 大连,大连理工大学, 2006
[29] Y Yitzhaky, N S Kopeika. Identification of blur parameters from motion blurred images. CVGIP: Graphical Models and Image Processing,1997,59(5), P310-320
[30] Y Yitzhaky, Rusian Milberg, Sergei Yohaev et al.Comparison of derect blind deconvolution methods for motiono-blurred images. Applied Optics, 1999,38(20), P4325-4332
[31] 陈宝林,最优化理论与算法, 清华大学出版社,2004, P301-305
[32] 陈前荣,陆启生,成礼智, 运动模糊图像的运动模糊方向鉴别, 国防科技大学学报,2004,26(1),P41-45
[33] 陈前荣,陆启生,成礼智, 基于方向微分和加权平均的运动模糊方向的鉴别, 计算机工程与应用,2004,29,P1-5
[34] 陈前荣,陆启生,成礼智,运动模糊图像点扩散函数尺度鉴别, 计算机工程与应用, 2004,23,P15-19
[35] Rafael C. Gonzalez, Richard E. Woods, 数字图像处理,第二版,北京,电子工业出版社,P175-215
[36] White Rechard L, Image Restoration Usatg the Damped Rechardson- Lucy Method[C], In Astronomical Data Analysis Software and Systems Ⅲ, ASP Conference Series, Vol.61, 1994.
[37] Mery Domatgo, Dieter Filbert, A Fast Non- iterative Algorith for the Removal of Blur Caused by Uniform Latear Motion at X-ray Images, In: At Proceedings of the 15th World Conference on Non-Destructive Testatg ( WCNDT 2000), Roma, Oct.15-21,2000
[38] 张树波,赖剑煌,车牌定位和分割的一种综合方法,中山大学学报(自然科学版),2004.3,42(2)
[39] 李文举,梁德群,张群等,基于边缘颜色对的车牌定位新方法,计算机学报, 2004.2, 27(2)
[40] 陆锋,顾新艳,基于边缘检测和多特征扫描的车牌快速定位方法,南京工程学院学报,2005.9, 3(3)
[41] 后俊,车牌图像分割与智能字符识别方法的研究,[硕士学位论文],合肥, 合肥工业大学,2004
[42] 张振强,杜树新,一种新的复杂背景下快速车牌定位方法,科技通报,2007.9, 23(5)
[43] 曹晓光,朱风云,Ahmed Hassanen,基于互相关矢量图的车牌定位新算法, 北京航空航天大学学报,2004.3, 30(3)
[44] 王良红,冷建华,汽车倾斜牌照中字符定位与提取,电视技术,2003, (4)
[45] 潘武模,焦扬,王庆人, Hough 变换在中文名片图像倾斜校正中的应用, 中文信息学报, 2001, 15(3),P50-56
[46] 虞耀君,吴德会,一种车牌图像校正新方法,微计算机信息, 2007, 24(5-3),P310-312
[47] 后俊,车牌图像分割与智能字符识别方法的研究,[硕士学位论文],合肥,合肥工业大学 ,2004,14-17
[48] 叶齐祥,图像和视频检测技术研究,[博士学位论文],北京,中国科学院研究生院,2006
[49] 马颂德, 张正友,计算机视觉,计算机理论与算法基础,北京,科学出版社,1998
[50] 李挺,三维配准和融合研究,[硕士学位论文], 北京,中国科学院自动化研究所, 2005
[51] Rafael C. Gonzalez, Richard E. Woods, 数字图像处理,第二版,北京,电子工业出版社,2003.3,P192-193
[52] 赵宏,王丽敏,王工艺,汽车牌照自动识别中的二值化方法的研究,应用科技,2004.3.(31-3)
[53] 傅建平,张培林,李国章, 基于类间最大方差法的铁谱磨粒彩色图像自动分割,军械工程学院学报,2006.2, 18(1)
[56] 王巍,杨国庆,吴仁彪,一种自适应车牌字符分割算法, 现代电子信息技术理论与应用, 2005.9, 866-867
[55] 马腾飞,郑永果,赵卫东,基于边缘检测与 Hough 变换的车牌字符分割算法,系统仿真学报,2006.8(第 18 卷增刊 1)
[56] Shunji Mari, Kazauhiko Yamamoto, Historical Review Of OCR Research and Development, Processing of IEEE, 1992, 80(7), P1029-1057
[57] 朱小燕,史一凡,马少平,手写体字符识别研究,模式识别与人工智能,2000,13(2), P174-180
[58] 郭戈,闫继宏,蒋红梅等,基于结构特征的汉字识别,甘肃工业大学学报, 2003, 29(1),P81-85
[59] 路小波,凌小静,刘斌, 基于组合特征的车牌字符识别仪器仪表学报,2006, 27(17),P698-701
[60] Shen-Zheng Wang, His-Jian Lee, Detection and Recognition of License Plate Characters with Different Appearances, IEEE, 2003,P979-984
[61] 张晓清,王国文,曹海云, 基于细化的手写汉字的笔段提取方法,哈尔滨工业大学学报,1999,31 (5),P107-110
[62] 叶斌,彭嘉雄, 伪 Zemike 矩不变性分析及其改进研究,中国图象图形学报, 2003,8(3),P246-252
[63] 张庆丰,毛万胜,苏新,基于图论分析的车牌数字字符识别研究与应用,电脑知识与技术,2006,P201-202
[64] Hu Chengwen,Zhao Yannan, Wang Jiaxin,Yang Zehong, An improved method for the character recognition based on SVM. Proceeding of the 24th IASTE International Multi Conference Artificial intelligence and applications, 2006,P457-461
[65] Shokri Gendy, Clifton L.Smith,Stefan Lachowcz. Automatic Car Registration Plate Recognition Using Fast Hough Transform. IEEE, 1997,P209-218
[66] Luisa De Vena, Number Plate Recognition by Hierarchical Neural Networks, Proceedings of 1993 International Joint Conference on Neural Networks, IEEE, 1993,P2105-2108
[67] 王森,基于神经网络的车牌识别技术研究,[中山大学硕士学位论文],广州,中山大学,2007.04.30
[68] C Suen , C Nadal, R Legault, et al., Computer recognition of unconstrained handwritten numerals, Proceedings of the lEEE,6(7), P1162-1180
[69] 崔金魁,杨扬,颉斌,一种基于集成 BP 网络的手写汉字识别方法,微电子学与计算机,2006,23 (8), P121-124
[70] Hansen L K, Salamon P, Neural network ensembles, IEEE Trans Pattern Analysis and Machine intelligence,l990,12(10), P993-1001
[2] 张炜,王庆,赵荣椿, 汽车牌照实时识别,信号处理, 16(4), P372-375
[3] 张中, 汉字识别技术综述, 语言文字应用, No.2, 1997
[4] 吴佑寿,丁晓青, 汉字识别原理方法与实现, 高等教育出版社, 1992
[5] 胡家忠, 计算机文字识别技术, 气象出版社, 1994
[6] K. Mori and I. Masuda, Advances in Recognition of Chinese Characters, Proc. Of 5th Inter. Conf. on Pattern Recognition (1980), P692-720
[7] Q. R. Wang, C. Y. Sun, Analysis and Design of a Decision Tree Based on Entroy Reduction and Its Application to Large Character Set Recognition, IEEE Trans. Vol. PAMI-6 No. 4(1984), P407-417
[8] Michio Umedu, Recognition of Multi-Font Printed Chinese Character, Proc.6 th IJCPR(1982), P793-796
[9] V. K. Govindan, Character Recognition- A Review, Pattern Recognition, 23(7), 1990, P671-675
[10] 郑南宁,张西宁,戴莹,朱海安,行驶车辆牌照自动识别系统,西安交通大学学报,1991,25(1),43-53
[11] 叶晨洲,车辆牌照字符识别系统,计算机系统应用,1999,Vol.5,P10-13
[12] V. K. Govindan, Character Recognition-A Review, Pattern Recognition, 23(7), 1990, P676-683
[13] 黄德双,神经模式识别系统理论,电子工业出版社,北京,1996
[14] 王建平,姜滔,朱程辉, 基于小波和矩的图像字符特征提取方法研究,信号处理,已投
[15] 赵健,俞卞章,小波与神经网络在模式识别中的应用,仪器仪表学报, 2001.6
[16] 是湘全,何苑凌,蔡孟波,遗传算法在车牌定位中的应用,公路交通科技, 2000(4)
[17] 黎明,杨小芹,刘高航, 基于多个前向神经网络和遗传算法的边界检测法, 南昌航空工业学院学报, 2004(6)
[18] 黎明,严超华,刘高航,基于前向神经网络和 Hopfield 反馈神经网络的边界检测法,中国图像图形学报, 1999(8)
[19]张汉江,曹焱,黄升华等, 模糊 ART 神经网络在目标运动识别中的应用, 模糊系统与数学, 1998(4).
[20] 余玉梅,熊汉, 模糊模式是方法研究,云南民族学院学报(自然科学版), 1998(1)
[21] 张得喜,马少平等, 基于统计与神经元方法相组合的手写体相似字识别, 中文信息学报,21(2), 1999
[22] 陆浩远,杨源远, 手写体汉字识别问题综述, 计算机应用与软件, 11(2), 1992,P1-8
[23] 中国人工智能学会,中国人工智能进展,北京邮电大学出版社,2001,P1-6
[24] S C Som. Analysis of the effect linear smear on photographic images. Opt. Soc. Am., 1971, 61,P859-864.
[25] O Header, S R Rotman, N S Kopeika. Target acquisition modeling of forward-motion considerations for airborne reconnaissance over hostile territory. Opt. Eng., 1994, 22,P3106-3117.
[26] O header, I Dror, N S Kopeika. Image resolution limits resulting from mechanical vibration. Opt. Eng., 1994, 33, P566-578.
[27] 李红阳,运动图像恢复 [工程硕士学位论文], 北京,清华大学,2002.
[28] 马明,运动模糊图像的判定与恢复 [硕士学位论文], 大连,大连理工大学, 2006
[29] Y Yitzhaky, N S Kopeika. Identification of blur parameters from motion blurred images. CVGIP: Graphical Models and Image Processing,1997,59(5), P310-320
[30] Y Yitzhaky, Rusian Milberg, Sergei Yohaev et al.Comparison of derect blind deconvolution methods for motiono-blurred images. Applied Optics, 1999,38(20), P4325-4332
[31] 陈宝林,最优化理论与算法, 清华大学出版社,2004, P301-305
[32] 陈前荣,陆启生,成礼智, 运动模糊图像的运动模糊方向鉴别, 国防科技大学学报,2004,26(1),P41-45
[33] 陈前荣,陆启生,成礼智, 基于方向微分和加权平均的运动模糊方向的鉴别, 计算机工程与应用,2004,29,P1-5
[34] 陈前荣,陆启生,成礼智,运动模糊图像点扩散函数尺度鉴别, 计算机工程与应用, 2004,23,P15-19
[35] Rafael C. Gonzalez, Richard E. Woods, 数字图像处理,第二版,北京,电子工业出版社,P175-215
[36] White Rechard L, Image Restoration Usatg the Damped Rechardson- Lucy Method[C], In Astronomical Data Analysis Software and Systems Ⅲ, ASP Conference Series, Vol.61, 1994.
[37] Mery Domatgo, Dieter Filbert, A Fast Non- iterative Algorith for the Removal of Blur Caused by Uniform Latear Motion at X-ray Images, In: At Proceedings of the 15th World Conference on Non-Destructive Testatg ( WCNDT 2000), Roma, Oct.15-21,2000
[38] 张树波,赖剑煌,车牌定位和分割的一种综合方法,中山大学学报(自然科学版),2004.3,42(2)
[39] 李文举,梁德群,张群等,基于边缘颜色对的车牌定位新方法,计算机学报, 2004.2, 27(2)
[40] 陆锋,顾新艳,基于边缘检测和多特征扫描的车牌快速定位方法,南京工程学院学报,2005.9, 3(3)
[41] 后俊,车牌图像分割与智能字符识别方法的研究,[硕士学位论文],合肥, 合肥工业大学,2004
[42] 张振强,杜树新,一种新的复杂背景下快速车牌定位方法,科技通报,2007.9, 23(5)
[43] 曹晓光,朱风云,Ahmed Hassanen,基于互相关矢量图的车牌定位新算法, 北京航空航天大学学报,2004.3, 30(3)
[44] 王良红,冷建华,汽车倾斜牌照中字符定位与提取,电视技术,2003, (4)
[45] 潘武模,焦扬,王庆人, Hough 变换在中文名片图像倾斜校正中的应用, 中文信息学报, 2001, 15(3),P50-56
[46] 虞耀君,吴德会,一种车牌图像校正新方法,微计算机信息, 2007, 24(5-3),P310-312
[47] 后俊,车牌图像分割与智能字符识别方法的研究,[硕士学位论文],合肥,合肥工业大学 ,2004,14-17
[48] 叶齐祥,图像和视频检测技术研究,[博士学位论文],北京,中国科学院研究生院,2006
[49] 马颂德, 张正友,计算机视觉,计算机理论与算法基础,北京,科学出版社,1998
[50] 李挺,三维配准和融合研究,[硕士学位论文], 北京,中国科学院自动化研究所, 2005
[51] Rafael C. Gonzalez, Richard E. Woods, 数字图像处理,第二版,北京,电子工业出版社,2003.3,P192-193
[52] 赵宏,王丽敏,王工艺,汽车牌照自动识别中的二值化方法的研究,应用科技,2004.3.(31-3)
[53] 傅建平,张培林,李国章, 基于类间最大方差法的铁谱磨粒彩色图像自动分割,军械工程学院学报,2006.2, 18(1)
[56] 王巍,杨国庆,吴仁彪,一种自适应车牌字符分割算法, 现代电子信息技术理论与应用, 2005.9, 866-867
[55] 马腾飞,郑永果,赵卫东,基于边缘检测与 Hough 变换的车牌字符分割算法,系统仿真学报,2006.8(第 18 卷增刊 1)
[56] Shunji Mari, Kazauhiko Yamamoto, Historical Review Of OCR Research and Development, Processing of IEEE, 1992, 80(7), P1029-1057
[57] 朱小燕,史一凡,马少平,手写体字符识别研究,模式识别与人工智能,2000,13(2), P174-180
[58] 郭戈,闫继宏,蒋红梅等,基于结构特征的汉字识别,甘肃工业大学学报, 2003, 29(1),P81-85
[59] 路小波,凌小静,刘斌, 基于组合特征的车牌字符识别仪器仪表学报,2006, 27(17),P698-701
[60] Shen-Zheng Wang, His-Jian Lee, Detection and Recognition of License Plate Characters with Different Appearances, IEEE, 2003,P979-984
[61] 张晓清,王国文,曹海云, 基于细化的手写汉字的笔段提取方法,哈尔滨工业大学学报,1999,31 (5),P107-110
[62] 叶斌,彭嘉雄, 伪 Zemike 矩不变性分析及其改进研究,中国图象图形学报, 2003,8(3),P246-252
[63] 张庆丰,毛万胜,苏新,基于图论分析的车牌数字字符识别研究与应用,电脑知识与技术,2006,P201-202
[64] Hu Chengwen,Zhao Yannan, Wang Jiaxin,Yang Zehong, An improved method for the character recognition based on SVM. Proceeding of the 24th IASTE International Multi Conference Artificial intelligence and applications, 2006,P457-461
[65] Shokri Gendy, Clifton L.Smith,Stefan Lachowcz. Automatic Car Registration Plate Recognition Using Fast Hough Transform. IEEE, 1997,P209-218
[66] Luisa De Vena, Number Plate Recognition by Hierarchical Neural Networks, Proceedings of 1993 International Joint Conference on Neural Networks, IEEE, 1993,P2105-2108
[67] 王森,基于神经网络的车牌识别技术研究,[中山大学硕士学位论文],广州,中山大学,2007.04.30
[68] C Suen , C Nadal, R Legault, et al., Computer recognition of unconstrained handwritten numerals, Proceedings of the lEEE,6(7), P1162-1180
[69] 崔金魁,杨扬,颉斌,一种基于集成 BP 网络的手写汉字识别方法,微电子学与计算机,2006,23 (8), P121-124
[70] Hansen L K, Salamon P, Neural network ensembles, IEEE Trans Pattern Analysis and Machine intelligence,l990,12(10), P993-1001
© 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 |