模糊车牌、污迹车牌和多车牌的定位与校正
|
摘要
车牌识别技术是智能交通系统中的关键技术,而车牌的定位与校正又是车牌识别技术的主要步骤之一,复杂情况下车牌的定位与校正更是其中的难点。本文在介绍复杂情况下车牌识别的国内外研究概况的基础上,研究了一些新的处理方法,主要工作如下:
1、提出了基于混沌粒子群和Contourlet域正则化的图像复原算法。Contourlet变换是一种新的多尺度几何变换方法,建立Contourlet域中的正则化模型,引入混沌粒子群算法选取正则化参数,利用其快速准确的搜索能力,找出泛函的极值解。实验结果表明,该方法具有更好的视觉效果,且峰值信噪比更高。
2、研究了一种基于对偶树复小波变换的的污迹车牌图像修复方法。将原有的小波方法扩展到复数域,使其具有了优良的平移不变性、方向选择性以及可精确的重构性;然后利用Criminisi算法思想,通过确定像素优先级、搜索最佳匹配块填充待修复区域,再进行小波逆变换得到修复后的图像。结果表明该方法的峰值信噪比高于传统小波方法。
3、给出了一种基于改进Sobel边缘检测算子和数学形态学的多车牌定位方法。对输入图像先用改进的Sobel算子进行边缘检测,接着再生成边缘密度图,对边缘密度图二值化并进行有效的非线性滤波,然后用数学形态学方法做膨胀处理,通过连通域分析找到目标的外接矩形,最后根据车牌的几何特征确定最终的车牌区域。结果显示该方法有更高的检出率。
4、实现了基于Tent映射混沌粒子群和车牌纹理特征相结合的车牌精确定位算法。采用两种不同的方法进行车牌纹理特征的提取:①用三组不同的一维滤波器提取车牌的纹理特征,引入车牌纹理的一致性度量作为判决条件,构造一种能够准确反映车牌区域的特征向量;②根据车牌区域的重点特征,提取7种能够准确反映车牌区域的特征向量,构成整个车牌的特征矢量;然后利用Tent映射的混沌粒子群算法,并结合车牌特征矢量,搜索车牌区域的最佳定位参量。实验结果表明该方法误检率更低且运算时间较短。
5、给出了一种基于混沌粒子群和字符旋转投影的车牌图像倾斜校正方法。分别将车牌字符区域向水平和垂直方向进行投影,利用混沌粒子群优化算法搜索投影的最小距离,从而获得水平错切角度以及垂直倾斜角度,最后按照该角度分别进行旋转得到校正后的车牌图像。结果表明该方法收敛精度更高且运行时间较短。
The vehicle plate recognition technology is the key of intelligent transportation system, and plate position and correction is the main step, which is a challenging task. After the introduction of current development of vehicle plate recognition in condition of complex background, researches on the new methods are included in this paper. All the work of the paper is described as follows:
Firstly, an image restoration method based on chaotic particle swarm optimization and regularized parameter by contourlet transform is realized. Contourlet transform is a new multi-scale geometric distortion. Then the regularization model based on contourlet-domain is established. Chaotic particle swarm optimization is adopted to choose the optimal regularized parameter. At last, the extrmal solution of function is found by making use of the fast and exact ability of chaotic particle swarm optimization.The results show that this method has better visual effects and higher peak signal-to-noise ratio(PSNR).
Secondly, an image inpainting method of stain vehicle plate based on dual--tree complex wavelet transform is given. It expands primary wavelet transform to plural-domain, which has the good shift invariance, directional selectivity and perfect reconstruction. Then this method confirms the pixel priority and search the optimal matching patch to fill in the inpainting area, which is based on Criminisi idea. At last, the inpainting image is got by wavelet inverse transform. The results show that this method has higher PSNR than primary wavelet transform.
Thirdly, a multi-vehicle plate position method based on improved Sobel operator and morphology is given. The image edge is detected by the improved Sobel operator, and then the edge density chart is generated. Afterward, it is binaryzationed and filtered based on non-linear. Then, the image is dilated by morphology method. The external rectangle of the object is found by connected component analyse, and the final vehicle plate is confirmed areas based on the geometric character of it. The experimental results show that the method has higher relevance ratio.
Fourthly, an accurate license plate location method based on Tent chaotic particle swarm optimization and texture features is realized. It adapts two different methods to extract the vehicle plate texture features: (1) get the texture feature vector by three one-dimensional filters, and construct the fitness function by leading the texture coherence into the judgment, which could stand for the plate area accurately; (2) get the texture feature vector by seven different vectors and construct the fitness function based on the important characters of plate area. Then the optimal character parameter with tent chaotic particle swarm optimization by combining the texture features of plate area is found. The results show that this method has lower miss ratio and shorter running time.
Fifthly, a vehicle plate tilt correction method based on chaotic particle swarm optimization and character rotation projection is proposed. The projection on horizontal and vertical coordinate is used on character region of the rotated vehicle license plate. Then the projection minimum distance is searched by chaotic particle swarm optimization, which is used to get the optimal vertical tilt and horizontal sheer angle. At last, it rotates the image with the anle to get the corrected result. The results show that this method has higher constringent precision and shorter running time.
1、提出了基于混沌粒子群和Contourlet域正则化的图像复原算法。Contourlet变换是一种新的多尺度几何变换方法,建立Contourlet域中的正则化模型,引入混沌粒子群算法选取正则化参数,利用其快速准确的搜索能力,找出泛函的极值解。实验结果表明,该方法具有更好的视觉效果,且峰值信噪比更高。
2、研究了一种基于对偶树复小波变换的的污迹车牌图像修复方法。将原有的小波方法扩展到复数域,使其具有了优良的平移不变性、方向选择性以及可精确的重构性;然后利用Criminisi算法思想,通过确定像素优先级、搜索最佳匹配块填充待修复区域,再进行小波逆变换得到修复后的图像。结果表明该方法的峰值信噪比高于传统小波方法。
3、给出了一种基于改进Sobel边缘检测算子和数学形态学的多车牌定位方法。对输入图像先用改进的Sobel算子进行边缘检测,接着再生成边缘密度图,对边缘密度图二值化并进行有效的非线性滤波,然后用数学形态学方法做膨胀处理,通过连通域分析找到目标的外接矩形,最后根据车牌的几何特征确定最终的车牌区域。结果显示该方法有更高的检出率。
4、实现了基于Tent映射混沌粒子群和车牌纹理特征相结合的车牌精确定位算法。采用两种不同的方法进行车牌纹理特征的提取:①用三组不同的一维滤波器提取车牌的纹理特征,引入车牌纹理的一致性度量作为判决条件,构造一种能够准确反映车牌区域的特征向量;②根据车牌区域的重点特征,提取7种能够准确反映车牌区域的特征向量,构成整个车牌的特征矢量;然后利用Tent映射的混沌粒子群算法,并结合车牌特征矢量,搜索车牌区域的最佳定位参量。实验结果表明该方法误检率更低且运算时间较短。
5、给出了一种基于混沌粒子群和字符旋转投影的车牌图像倾斜校正方法。分别将车牌字符区域向水平和垂直方向进行投影,利用混沌粒子群优化算法搜索投影的最小距离,从而获得水平错切角度以及垂直倾斜角度,最后按照该角度分别进行旋转得到校正后的车牌图像。结果表明该方法收敛精度更高且运行时间较短。
The vehicle plate recognition technology is the key of intelligent transportation system, and plate position and correction is the main step, which is a challenging task. After the introduction of current development of vehicle plate recognition in condition of complex background, researches on the new methods are included in this paper. All the work of the paper is described as follows:
Firstly, an image restoration method based on chaotic particle swarm optimization and regularized parameter by contourlet transform is realized. Contourlet transform is a new multi-scale geometric distortion. Then the regularization model based on contourlet-domain is established. Chaotic particle swarm optimization is adopted to choose the optimal regularized parameter. At last, the extrmal solution of function is found by making use of the fast and exact ability of chaotic particle swarm optimization.The results show that this method has better visual effects and higher peak signal-to-noise ratio(PSNR).
Secondly, an image inpainting method of stain vehicle plate based on dual--tree complex wavelet transform is given. It expands primary wavelet transform to plural-domain, which has the good shift invariance, directional selectivity and perfect reconstruction. Then this method confirms the pixel priority and search the optimal matching patch to fill in the inpainting area, which is based on Criminisi idea. At last, the inpainting image is got by wavelet inverse transform. The results show that this method has higher PSNR than primary wavelet transform.
Thirdly, a multi-vehicle plate position method based on improved Sobel operator and morphology is given. The image edge is detected by the improved Sobel operator, and then the edge density chart is generated. Afterward, it is binaryzationed and filtered based on non-linear. Then, the image is dilated by morphology method. The external rectangle of the object is found by connected component analyse, and the final vehicle plate is confirmed areas based on the geometric character of it. The experimental results show that the method has higher relevance ratio.
Fourthly, an accurate license plate location method based on Tent chaotic particle swarm optimization and texture features is realized. It adapts two different methods to extract the vehicle plate texture features: (1) get the texture feature vector by three one-dimensional filters, and construct the fitness function by leading the texture coherence into the judgment, which could stand for the plate area accurately; (2) get the texture feature vector by seven different vectors and construct the fitness function based on the important characters of plate area. Then the optimal character parameter with tent chaotic particle swarm optimization by combining the texture features of plate area is found. The results show that this method has lower miss ratio and shorter running time.
Fifthly, a vehicle plate tilt correction method based on chaotic particle swarm optimization and character rotation projection is proposed. The projection on horizontal and vertical coordinate is used on character region of the rotated vehicle license plate. Then the projection minimum distance is searched by chaotic particle swarm optimization, which is used to get the optimal vertical tilt and horizontal sheer angle. At last, it rotates the image with the anle to get the corrected result. The results show that this method has higher constringent precision and shorter running time.
引文
[1] Yuntao Cui, Qian Huang. Automatic license extraction from moving vehicles[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 77(4):126~130.
[2] Young Sung Soh, Byung Tae Chun. Design of real time vehicle identification system[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1994, 7(6):86~91.
[3] Takashi Naito, Toshihiko Tsukada. Moving vehicle license plate recognition method robust to changes in lighting conditions[J]. System and Computer in Japan, 2000, 31(11):82~92.
[4] Masataka Kagesawa, Shinichi Ueno. Vehicle recongnition system in infrared images using IMAP parallel vision board[J]. Electronics and Communications in Japan, 2003, 86(5):Part3.
[5]张引,潘云鹤.彩色汽车图像牌照定位新方法[J].中国图象图形学报,2001, 6(4):374~377.
[6]赵兵,鲁敏,匡纲要,等.基于混合特征的车牌定位算法[J].计算机工程与设计, 2007, 28(23):5668~5670.
[7]王昱,赵正校,杨硕.基于直线边缘识别的图像区域定位算法[J].计算机工程, 1999, 25(9) :61~62.
[8] Zheng D N, Zhao Y N, Wang J X. An efficient method of license plate location[J]. Pattern Recognition Letters, 2005, 26(15):2431~2438.
[9]李刚,曾锐利,林凌,王蒙军.基于数学形态学的车牌定位算法[J].仪器仪表学报, 2007, 28(7):1323~1327.
[10] Feng Y, Zheng M. Vehicle license plate location based on histogramming and mathematical morphology[C]. Proceedings of Fourth IEEE Worksho Pon Automatic Identification Advanced Technologies, 2005:89~94.
[11]熊军,高敦堂,都思丹,等.应用遗传算法进行车牌定位[J].计算机应用, 2004, 24:163~165.
[12]张玲,刘勇,何伟.自适应遗传算法在车牌定位中的应用[J].计算机应用, 2008, 28(1):184~186.
[13]盛小明,吴冬敏,芮延年.基于遗传算法的神经网络用于汽车牌照识别的研究[J].机电一体化, 2005, (6):52~54.
[14] Wen C Y, Yu C C. A 3D Transformation to improve the legibility of license plate numbers[J]. Journal of Forensic Sciences, 2002, 47(3): 578~585.
[15]杨立刚,张兴会,李兰友.车牌照字符倾斜校正方法的研究[J].仪器仪表学报, 2004, 25(4):696~697.
[16]周冠玮,平西建,程娟.基于改进Hough变换的文本图像倾斜校正方法[J].计算机应用, 2007, 27(7):1813~1816.
[17]贡丽霞,白艳萍.基于Radon变换和坎尼边缘检测的倾斜车牌校正方法研究[J].太原师范学院学报, 2010, 9(1):61~63.
[18]贡丽霞,白艳萍. Radon变换在倾斜车牌图像校正中的应用[J].测试技术学报, 2009, 23(5):452~456.
[19] Wang H Q, Song Z H. Improved PCA with optimized sensor locations for process monitoring and fault diagnosis[C]. Proceedings of the 39th IEEE Conferenceon Decisionand Control, Sydney, Australia, 2000: 4353~4358.
[20]朱程辉,吴德会.基于主元分析的倾斜车牌图像校正方法研究[J].微电子学与计算机, 2006, 23(1):177~180.
[21]黄骥,吴一全.基于颜色对特征点主成分分析的车牌校正方法[J].中国图象图形学报, 2008, 13(4):642~646.
[22]李文举,梁德群,崔连延,等.一种新的车牌倾斜校正方法[J].信息与控制, 2004, 33(2):231~235.
[23]路小波,包明,黄卫.基于投影的车牌倾斜检测方法[J].交通运输工程与信息学报, 2004, 2(4):10~15.
[24]孙淑娟,李世祥,王枚.利用投影最小距离的车牌校正优化算法[J].太原理工大学学报, 2009, 40(4):361~364.
[25]雷超阳,刘军华,李桥.基于SOM神经网络聚类的车牌号码倾斜校正算法[J].计算机工程与设计, 2009, 30(14):3406~3408.
[26]吴一全,丁坚.基于K-L展开式的车牌倾斜校正方法[J].仪器仪表学报, 2008, 29(8):1690~1694.
[27]潘梅森,郭国强.基于图像矩的车牌号码倾斜校正[J].计算机辅助设计与图形学学报, 2007, 19(8):1041~1045.
[28]王晶,彭国华,赵丛.基于正则化技术的超分辨图像盲复原[J].计算机工程与应用, 2008, 44(6):42~45.
[29]薛梅,邹采荣,杨娟,等.一种空间自适应正则化图象盲复原算法[J].中国图象图形学报, 2002, 7A(4):356~362.
[30]张新明,沈兰荪.在小波变换域内实现图像的超分辨率复原[J].计算机学报, 2003, 26(9):1183~1188.
[31]江洁,邓琼,张广军.基于小波变换的正则化盲图像复原算法[J].光学精密工程,2007,15(4):582-586.
[32]王强,彭国华,徐华楠.基于多孔多方向小波的SAR图像正则化超分辨重构[J].计算机工程与应用, 2010, 46(26):173~175.
[33]卿粼波,何小海等.基于最小二乘准则的模糊估计和图像复原[J].四川大学学报, 2008, 20(2):129~133.
[34]郭永彩,高潮,王婀娜.基于小波变换和非负支撑域递归逆滤波算法的盲目图像复原[J].光学学报, 2009, 29(11):3000~3003.
[35]陈云龙,王平,王鹏.基于L-R非线性迭代的降质图像复原算法[J].计算机工程, 2010, 36(4):202~204.
[36]狄金海.基于自适应小生境遗传算法的图像复原[J].计算机工程与应用, 2009, 45(25):195~197.
[37]吴伟巍,曾庆山,刚轶金.基于遗传算法的盲超分辨率图像的重建[J].计算机工程与应用, 2009, 45(35):199~201.
[38]聂笃宪.基于PSO自适应正则化参数图像恢复的研究[J].计算机技术与发展, 2009, 19(1):106~108.
[39]聂笃宪,袁利国,文有为.应用粒子群优化算法选择正则化参数[J].计算机工程与应用, 2009, 45(12):195~197.
[40] Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting[A]. In: Proceedings of international conference on computer graphics and interactive techniques [C]. New Orleans, Louisiana, USA, 2000:417~424.
[41]曾勋勋,陈飞,王美清.基于BSCB模型的图像修补算法[J].福州大学学报, 2009, 37(5):657~661.
[42] Chan T F, Shen J H. Non-texture inpainting by curvature-drivendiffusions ( CDD ) [J] . Journal of Visual Communication and Image Representation, 2001, 12(4): 436~449.
[43]邵肖伟,刘政凯,宋璧.一种基于TV模型的自适应图像修复方法[J].电路与系统学报, 2004, 9(2):113~117.
[44] Tsai A, Yezzi J A, Willsky A S. Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation and magnification [J]. IEEE Transactions on Image Processing, 2001, 10(8): 1169~1186.
[45]沈民奋,陈家亮,代龙泉,等.基于图像分解和区域分割的数字图像修复[J].电子测量与仪器学报, 2009, 23(9):11~17.
[46]汪忠庆,檀结庆,何蕾.方向性纹理图像的修复算法[J].计算机工程与应用, 2006, (34):29~32.
[47]钟凡,莫铭臻,秦学英,等.基于WSSD的不规则图像块快速匹配[J].中国图象图形学报,2010, 15(3):495~501.
[48] Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004, 13(9): 1200~1212.
[49]张平,檀结庆,何蕾.基于离散小波变换的图像修补方法[J].计算机应用研究, 2007, 24(9):287~289.
[50]肖志云,张文霞,姜玉莉.基于小波变换的图像修复算法[J].内蒙古工业大学学报, 2008, 27(4):259~263.
[51]肖志云,张文霞.小波域的纹理图像快速修复算法[J].仪器仪表学报, 2008, 29(7):1422~1425.
[52] Tsuji T,Hattori H,Watanabe M. Development of night-vision system[J]. IEEE Transactions on Intelligent Transportation, 2006, 7(2):215~219.
[53] Zhou Jie, Gao Da-shan, Zhang David. Moving vehicle detection for automatic traffic monitoring[J]. IEEE Transactions on Vehicle Technology, 2007, 56(1):51~59.
[54]任德华.自然复杂环境中基于颜色的多车牌定位研究[J].中国图象图形学报, 2009, 14(12):2517~2526.
[55]梁玮,罗剑锋,贾云得,等.一种复杂背景下的多车牌图像分割与识别方法[J].北京理工大学学报, 2003, 23(1):91~95.
[56]陈寅鹏,丁晓青.复杂车辆图像中的车牌定位与字符分割方法[J].红外与激光工程, 2004, 33(1):29~33.
[57]朱春满,房斌,尚赵伟,等.复杂背景下的多车牌定位技术研究[J].公路交通科技, 2010, 27(7):147~153.
[58]张变莲,唐慧君,闫奇.一种复杂车辆图像中的多车牌定位方法[J].光子学报, 2007, 36(1):184~187.
[59]陈蓓,曹文伦,张洪才.复杂背景中多车牌粗定位算法研究[J].计算机工程与应用, 2009, 45(17):228~230.
[60] Chen Yan-peng, Ding Xiao-qing. License-plate location and character segmentation in complex vehicle images[J]. Infrared and Laser Engineering(红外与激光工程), 2004, 33(1):29~33. (in Chinese)
[61] Bai Jie, Tian Rui-li, Liu Nan. Research of vehicle license plate location algorithm based on color features and plate processions [A].Proceeding of International Conference on Machine Learning and Computing[C]. 2006, 1077~1085.
[62]王枚,苏光大,王国宏.多目标、多类型车牌融合定位算法[J].光电子·激光, 2009 ,20(9):1228~1233.
[63] Zou Mou-yan. Deconvolution and signal recovery[M]. Beijing: National Defense Industry Press, 2001.
[64] Sousa T, Silva A, Neves A. Particle swarm based data mining algorithms for classification tasks[J]. Parallel Computing , 2004, 30 (526):767~783.
[65]刘洪波,王秀坤,谭国真.粒子群优化算法的收敛性分析及其混沌改进算法[J].控制与决策, 2006, 21(6):636~640.
[66]孟红记,郑鹏,梅国晖,谢植.基于混沌序列的粒子群优化算法[J].控制与决策, 2006, 21(3):263~266.
[67]张晶晶,方勇华.基于contourlet变换的遥感图像去噪新算法[J].光学学报, 2008, 28(3):462~466.
[68]娄帅,丁振良,袁峰.基于contourlet变换的迭代图像复原算法[J].光学学报, 2009, 29(10):2768~2773.
[69]王强,彭国华,陈晓.在多尺度contourlet域中的SAR图像正则化超分辨[J].计算机工程与应用, 2010, 46(3):186~188.
[70] Do M, Vetterli M. The contourlet Transform: An efficient directional multiresolution image representation[J]. IEEE Transactions on Image Processing, 2003, 14(12):2091~2106.
[71] Morozov V A. Methods for solving incorrectly posed problems[M]. New York: Springer Verlag, 1984.
[72]张翔,张建奇,秦翰林,等.基于对偶树复小波变换的红外弱小目标背景抑制[J].光子学报, 2010, 39(9):1672~1677.
[73]王小军,何同弟.基于对偶树复小波-Curvelet变换的自适应多传感图像融合算法[J].信息与控制, 2010, 39(3):308~314.
[74] Nick Kingsbury. The dual-tree complex wavelet transform: A new efficient tool for image restoration and enhancement [C]. European Signal Processing Conference, EUSIPCO 98 Rhodes, 1998:319~322.
[75]鲍虎,张海丹,孙巍.基于改进Sobel算子的边缘检测车牌定位方法[J].海军航空工程学院学报, 2005, 20(5):585~587.
[76] SONG H SH, WANG G Q. The high performance car license plate recognition system and its core techniques[C]. Proceedings of IEEE International Conference on Vehicular Electronics and Safety, 2005, 42~45.
[77] Tholudur A, Ramirez W F. Obtaining smoother singular arc policies using a modified iterative dynamic programming algorithm[J]. International Journal of Control, 1997, 8(5):1115~1128.
[78]单梁,强浩,李军.基于Tent映射的混沌优化算法[J].控制与决策, 2005, (2): 179~182.
[79]贾东立,张家树.基于混沌变异的小生境粒子群算法[J].控制与决策, 2007, 22(1):117~120.
[80]程志刚,张立庆,李小林,吴晓华.基于Tent映射的混沌混合粒子群优化算法[J].系统工程与电子技术, 2007, 29(1):103~106.
[81]勾丽杰,郑玉兴,兰静.基于粒子群的车牌定位识别的神经网络方法[J].辽宁省交通高等专科学校学报, 2007, 9(2):51~53.
[82]黄振华,吴诚一.模式识别原理[M].浙江大学出版社, 1991.
[2] Young Sung Soh, Byung Tae Chun. Design of real time vehicle identification system[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1994, 7(6):86~91.
[3] Takashi Naito, Toshihiko Tsukada. Moving vehicle license plate recognition method robust to changes in lighting conditions[J]. System and Computer in Japan, 2000, 31(11):82~92.
[4] Masataka Kagesawa, Shinichi Ueno. Vehicle recongnition system in infrared images using IMAP parallel vision board[J]. Electronics and Communications in Japan, 2003, 86(5):Part3.
[5]张引,潘云鹤.彩色汽车图像牌照定位新方法[J].中国图象图形学报,2001, 6(4):374~377.
[6]赵兵,鲁敏,匡纲要,等.基于混合特征的车牌定位算法[J].计算机工程与设计, 2007, 28(23):5668~5670.
[7]王昱,赵正校,杨硕.基于直线边缘识别的图像区域定位算法[J].计算机工程, 1999, 25(9) :61~62.
[8] Zheng D N, Zhao Y N, Wang J X. An efficient method of license plate location[J]. Pattern Recognition Letters, 2005, 26(15):2431~2438.
[9]李刚,曾锐利,林凌,王蒙军.基于数学形态学的车牌定位算法[J].仪器仪表学报, 2007, 28(7):1323~1327.
[10] Feng Y, Zheng M. Vehicle license plate location based on histogramming and mathematical morphology[C]. Proceedings of Fourth IEEE Worksho Pon Automatic Identification Advanced Technologies, 2005:89~94.
[11]熊军,高敦堂,都思丹,等.应用遗传算法进行车牌定位[J].计算机应用, 2004, 24:163~165.
[12]张玲,刘勇,何伟.自适应遗传算法在车牌定位中的应用[J].计算机应用, 2008, 28(1):184~186.
[13]盛小明,吴冬敏,芮延年.基于遗传算法的神经网络用于汽车牌照识别的研究[J].机电一体化, 2005, (6):52~54.
[14] Wen C Y, Yu C C. A 3D Transformation to improve the legibility of license plate numbers[J]. Journal of Forensic Sciences, 2002, 47(3): 578~585.
[15]杨立刚,张兴会,李兰友.车牌照字符倾斜校正方法的研究[J].仪器仪表学报, 2004, 25(4):696~697.
[16]周冠玮,平西建,程娟.基于改进Hough变换的文本图像倾斜校正方法[J].计算机应用, 2007, 27(7):1813~1816.
[17]贡丽霞,白艳萍.基于Radon变换和坎尼边缘检测的倾斜车牌校正方法研究[J].太原师范学院学报, 2010, 9(1):61~63.
[18]贡丽霞,白艳萍. Radon变换在倾斜车牌图像校正中的应用[J].测试技术学报, 2009, 23(5):452~456.
[19] Wang H Q, Song Z H. Improved PCA with optimized sensor locations for process monitoring and fault diagnosis[C]. Proceedings of the 39th IEEE Conferenceon Decisionand Control, Sydney, Australia, 2000: 4353~4358.
[20]朱程辉,吴德会.基于主元分析的倾斜车牌图像校正方法研究[J].微电子学与计算机, 2006, 23(1):177~180.
[21]黄骥,吴一全.基于颜色对特征点主成分分析的车牌校正方法[J].中国图象图形学报, 2008, 13(4):642~646.
[22]李文举,梁德群,崔连延,等.一种新的车牌倾斜校正方法[J].信息与控制, 2004, 33(2):231~235.
[23]路小波,包明,黄卫.基于投影的车牌倾斜检测方法[J].交通运输工程与信息学报, 2004, 2(4):10~15.
[24]孙淑娟,李世祥,王枚.利用投影最小距离的车牌校正优化算法[J].太原理工大学学报, 2009, 40(4):361~364.
[25]雷超阳,刘军华,李桥.基于SOM神经网络聚类的车牌号码倾斜校正算法[J].计算机工程与设计, 2009, 30(14):3406~3408.
[26]吴一全,丁坚.基于K-L展开式的车牌倾斜校正方法[J].仪器仪表学报, 2008, 29(8):1690~1694.
[27]潘梅森,郭国强.基于图像矩的车牌号码倾斜校正[J].计算机辅助设计与图形学学报, 2007, 19(8):1041~1045.
[28]王晶,彭国华,赵丛.基于正则化技术的超分辨图像盲复原[J].计算机工程与应用, 2008, 44(6):42~45.
[29]薛梅,邹采荣,杨娟,等.一种空间自适应正则化图象盲复原算法[J].中国图象图形学报, 2002, 7A(4):356~362.
[30]张新明,沈兰荪.在小波变换域内实现图像的超分辨率复原[J].计算机学报, 2003, 26(9):1183~1188.
[31]江洁,邓琼,张广军.基于小波变换的正则化盲图像复原算法[J].光学精密工程,2007,15(4):582-586.
[32]王强,彭国华,徐华楠.基于多孔多方向小波的SAR图像正则化超分辨重构[J].计算机工程与应用, 2010, 46(26):173~175.
[33]卿粼波,何小海等.基于最小二乘准则的模糊估计和图像复原[J].四川大学学报, 2008, 20(2):129~133.
[34]郭永彩,高潮,王婀娜.基于小波变换和非负支撑域递归逆滤波算法的盲目图像复原[J].光学学报, 2009, 29(11):3000~3003.
[35]陈云龙,王平,王鹏.基于L-R非线性迭代的降质图像复原算法[J].计算机工程, 2010, 36(4):202~204.
[36]狄金海.基于自适应小生境遗传算法的图像复原[J].计算机工程与应用, 2009, 45(25):195~197.
[37]吴伟巍,曾庆山,刚轶金.基于遗传算法的盲超分辨率图像的重建[J].计算机工程与应用, 2009, 45(35):199~201.
[38]聂笃宪.基于PSO自适应正则化参数图像恢复的研究[J].计算机技术与发展, 2009, 19(1):106~108.
[39]聂笃宪,袁利国,文有为.应用粒子群优化算法选择正则化参数[J].计算机工程与应用, 2009, 45(12):195~197.
[40] Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting[A]. In: Proceedings of international conference on computer graphics and interactive techniques [C]. New Orleans, Louisiana, USA, 2000:417~424.
[41]曾勋勋,陈飞,王美清.基于BSCB模型的图像修补算法[J].福州大学学报, 2009, 37(5):657~661.
[42] Chan T F, Shen J H. Non-texture inpainting by curvature-drivendiffusions ( CDD ) [J] . Journal of Visual Communication and Image Representation, 2001, 12(4): 436~449.
[43]邵肖伟,刘政凯,宋璧.一种基于TV模型的自适应图像修复方法[J].电路与系统学报, 2004, 9(2):113~117.
[44] Tsai A, Yezzi J A, Willsky A S. Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation and magnification [J]. IEEE Transactions on Image Processing, 2001, 10(8): 1169~1186.
[45]沈民奋,陈家亮,代龙泉,等.基于图像分解和区域分割的数字图像修复[J].电子测量与仪器学报, 2009, 23(9):11~17.
[46]汪忠庆,檀结庆,何蕾.方向性纹理图像的修复算法[J].计算机工程与应用, 2006, (34):29~32.
[47]钟凡,莫铭臻,秦学英,等.基于WSSD的不规则图像块快速匹配[J].中国图象图形学报,2010, 15(3):495~501.
[48] Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004, 13(9): 1200~1212.
[49]张平,檀结庆,何蕾.基于离散小波变换的图像修补方法[J].计算机应用研究, 2007, 24(9):287~289.
[50]肖志云,张文霞,姜玉莉.基于小波变换的图像修复算法[J].内蒙古工业大学学报, 2008, 27(4):259~263.
[51]肖志云,张文霞.小波域的纹理图像快速修复算法[J].仪器仪表学报, 2008, 29(7):1422~1425.
[52] Tsuji T,Hattori H,Watanabe M. Development of night-vision system[J]. IEEE Transactions on Intelligent Transportation, 2006, 7(2):215~219.
[53] Zhou Jie, Gao Da-shan, Zhang David. Moving vehicle detection for automatic traffic monitoring[J]. IEEE Transactions on Vehicle Technology, 2007, 56(1):51~59.
[54]任德华.自然复杂环境中基于颜色的多车牌定位研究[J].中国图象图形学报, 2009, 14(12):2517~2526.
[55]梁玮,罗剑锋,贾云得,等.一种复杂背景下的多车牌图像分割与识别方法[J].北京理工大学学报, 2003, 23(1):91~95.
[56]陈寅鹏,丁晓青.复杂车辆图像中的车牌定位与字符分割方法[J].红外与激光工程, 2004, 33(1):29~33.
[57]朱春满,房斌,尚赵伟,等.复杂背景下的多车牌定位技术研究[J].公路交通科技, 2010, 27(7):147~153.
[58]张变莲,唐慧君,闫奇.一种复杂车辆图像中的多车牌定位方法[J].光子学报, 2007, 36(1):184~187.
[59]陈蓓,曹文伦,张洪才.复杂背景中多车牌粗定位算法研究[J].计算机工程与应用, 2009, 45(17):228~230.
[60] Chen Yan-peng, Ding Xiao-qing. License-plate location and character segmentation in complex vehicle images[J]. Infrared and Laser Engineering(红外与激光工程), 2004, 33(1):29~33. (in Chinese)
[61] Bai Jie, Tian Rui-li, Liu Nan. Research of vehicle license plate location algorithm based on color features and plate processions [A].Proceeding of International Conference on Machine Learning and Computing[C]. 2006, 1077~1085.
[62]王枚,苏光大,王国宏.多目标、多类型车牌融合定位算法[J].光电子·激光, 2009 ,20(9):1228~1233.
[63] Zou Mou-yan. Deconvolution and signal recovery[M]. Beijing: National Defense Industry Press, 2001.
[64] Sousa T, Silva A, Neves A. Particle swarm based data mining algorithms for classification tasks[J]. Parallel Computing , 2004, 30 (526):767~783.
[65]刘洪波,王秀坤,谭国真.粒子群优化算法的收敛性分析及其混沌改进算法[J].控制与决策, 2006, 21(6):636~640.
[66]孟红记,郑鹏,梅国晖,谢植.基于混沌序列的粒子群优化算法[J].控制与决策, 2006, 21(3):263~266.
[67]张晶晶,方勇华.基于contourlet变换的遥感图像去噪新算法[J].光学学报, 2008, 28(3):462~466.
[68]娄帅,丁振良,袁峰.基于contourlet变换的迭代图像复原算法[J].光学学报, 2009, 29(10):2768~2773.
[69]王强,彭国华,陈晓.在多尺度contourlet域中的SAR图像正则化超分辨[J].计算机工程与应用, 2010, 46(3):186~188.
[70] Do M, Vetterli M. The contourlet Transform: An efficient directional multiresolution image representation[J]. IEEE Transactions on Image Processing, 2003, 14(12):2091~2106.
[71] Morozov V A. Methods for solving incorrectly posed problems[M]. New York: Springer Verlag, 1984.
[72]张翔,张建奇,秦翰林,等.基于对偶树复小波变换的红外弱小目标背景抑制[J].光子学报, 2010, 39(9):1672~1677.
[73]王小军,何同弟.基于对偶树复小波-Curvelet变换的自适应多传感图像融合算法[J].信息与控制, 2010, 39(3):308~314.
[74] Nick Kingsbury. The dual-tree complex wavelet transform: A new efficient tool for image restoration and enhancement [C]. European Signal Processing Conference, EUSIPCO 98 Rhodes, 1998:319~322.
[75]鲍虎,张海丹,孙巍.基于改进Sobel算子的边缘检测车牌定位方法[J].海军航空工程学院学报, 2005, 20(5):585~587.
[76] SONG H SH, WANG G Q. The high performance car license plate recognition system and its core techniques[C]. Proceedings of IEEE International Conference on Vehicular Electronics and Safety, 2005, 42~45.
[77] Tholudur A, Ramirez W F. Obtaining smoother singular arc policies using a modified iterative dynamic programming algorithm[J]. International Journal of Control, 1997, 8(5):1115~1128.
[78]单梁,强浩,李军.基于Tent映射的混沌优化算法[J].控制与决策, 2005, (2): 179~182.
[79]贾东立,张家树.基于混沌变异的小生境粒子群算法[J].控制与决策, 2007, 22(1):117~120.
[80]程志刚,张立庆,李小林,吴晓华.基于Tent映射的混沌混合粒子群优化算法[J].系统工程与电子技术, 2007, 29(1):103~106.
[81]勾丽杰,郑玉兴,兰静.基于粒子群的车牌定位识别的神经网络方法[J].辽宁省交通高等专科学校学报, 2007, 9(2):51~53.
[82]黄振华,吴诚一.模式识别原理[M].浙江大学出版社, 1991.