身份证识别系统研究
|
摘要
身份证是我国18岁以上成年人的有效证件，记载了持有人的基本个人信息和一个唯一的身份证编号。在目前大多数情况下，身份证登记采用人工方式，很不方便。随着计算机技术、图像处理和字符识别算法的成熟，利用计算机进行身份证自动识别录入已经成为可能。身份证识别系统可以广泛用于服务性行业、交通系统和公安系统等需要身份证检验的部门，节省大量的人力物力，具有广阔的应用前景。
本文对身份证识别进行了比较深入的研究，在一个简化模型的基础上，详细阐述了系统的处理流程：行分割、预处理、识别前处理、特征提取、识别以及编号的识别后处理。针对身份证识别的特殊性，调整了预处理顺序：先在灰度图像下完成行分割、再进行图像增强、二值化，然后才作单字分割。文中提出了灰度图像下的行分割方法和基于最大宽度回溯算法的单字分割算法，从而实现了字符的精确定位。选用合适的二值化算法，完成了灰度图像到二值文本的转化。针对编号行数字，选取了能较全面地体现它们的结构和统计特性的31维特征向量作为原始特征。对汉字识别采取粗、细二级分类方法，分别选择了4维和72维特征向量。本文对31维特征向量运用因子分析法，得到了7个彼此独立的公因子变量。该方法不仅消除了变量之间的相关性，而且相当于给原变量加了合适的权值，使类间的方差更大，从而有利于识别。本文还充分利用了身份证中的先验知识，对编号进行了后处理，能修正部分数字的误判，并给出整体识别结果正确与否的判断，进一步提高了编号识别的正确率。实验表明了本文算法的有效性。
The ID card is an important certificate for the adults above 18 years of our country. It has the holder's basic personal information and has a unique ID card serial number. Since most of the ID cards are registered by manual now, a more convenient method is expected. With the progress of computer science, image processing and character recognition, it has been possible for us using computer to identify the information in ID card image automatically. The ID card recognition system can be applied in many departments, such as transportation, public security office etc. Since it can save large quantity of manpower, it has vast of application foreground.
In this thesis, the ID card recognition system based on a simplification model is investigated. It includes the detail process: line segmentation, image preprocess, recognition preprocess, feature extraction, recognition and the serial number's after-recognition. To fit the special character recognition, preprocess sequence is adjusted as: line segmentation under the gray level image, image enhance, binary, character segmentation. We provide the algorithm of line segmentation under gray level image and character segmentation based on the biggest width backtracking algorithm to get the accurate position of characters. Gray image is converted to binary
one by suitable threshold. A 31-dimension feature vector is selected which can best resemble the digit's characteristic of construction and statistics. Gross and fine classification methods are used for Chinese character recognition, respectively with a 4- dimension and 72-dimension vector. Factor analysis method is applied on the 31-dimension vector to get independent variables. It decreases the relations among the variables, but also changes their weights to get the bigger variance among different classes, which benefits for the recognition. We process the after-recognition for the serial number with pre-knowledge from the ID card. So we can know
whether the number recognized is correct, and revise some wrong decisions. Experiments verify the validation of the algorithms.
本文对身份证识别进行了比较深入的研究，在一个简化模型的基础上，详细阐述了系统的处理流程：行分割、预处理、识别前处理、特征提取、识别以及编号的识别后处理。针对身份证识别的特殊性，调整了预处理顺序：先在灰度图像下完成行分割、再进行图像增强、二值化，然后才作单字分割。文中提出了灰度图像下的行分割方法和基于最大宽度回溯算法的单字分割算法，从而实现了字符的精确定位。选用合适的二值化算法，完成了灰度图像到二值文本的转化。针对编号行数字，选取了能较全面地体现它们的结构和统计特性的31维特征向量作为原始特征。对汉字识别采取粗、细二级分类方法，分别选择了4维和72维特征向量。本文对31维特征向量运用因子分析法，得到了7个彼此独立的公因子变量。该方法不仅消除了变量之间的相关性，而且相当于给原变量加了合适的权值，使类间的方差更大，从而有利于识别。本文还充分利用了身份证中的先验知识，对编号进行了后处理，能修正部分数字的误判，并给出整体识别结果正确与否的判断，进一步提高了编号识别的正确率。实验表明了本文算法的有效性。
The ID card is an important certificate for the adults above 18 years of our country. It has the holder's basic personal information and has a unique ID card serial number. Since most of the ID cards are registered by manual now, a more convenient method is expected. With the progress of computer science, image processing and character recognition, it has been possible for us using computer to identify the information in ID card image automatically. The ID card recognition system can be applied in many departments, such as transportation, public security office etc. Since it can save large quantity of manpower, it has vast of application foreground.
In this thesis, the ID card recognition system based on a simplification model is investigated. It includes the detail process: line segmentation, image preprocess, recognition preprocess, feature extraction, recognition and the serial number's after-recognition. To fit the special character recognition, preprocess sequence is adjusted as: line segmentation under the gray level image, image enhance, binary, character segmentation. We provide the algorithm of line segmentation under gray level image and character segmentation based on the biggest width backtracking algorithm to get the accurate position of characters. Gray image is converted to binary
one by suitable threshold. A 31-dimension feature vector is selected which can best resemble the digit's characteristic of construction and statistics. Gross and fine classification methods are used for Chinese character recognition, respectively with a 4- dimension and 72-dimension vector. Factor analysis method is applied on the 31-dimension vector to get independent variables. It decreases the relations among the variables, but also changes their weights to get the bigger variance among different classes, which benefits for the recognition. We process the after-recognition for the serial number with pre-knowledge from the ID card. So we can know
whether the number recognized is correct, and revise some wrong decisions. Experiments verify the validation of the algorithms.
引文
1．边肇琪，张学工．模式识别．清华大学出版社，2000
2．陈廷标，夏良正．数字图象处理．人民邮电出版社，1990
3．陈友斌，丁晓青，吴佑寿．一种手写汉字特征抽取的新方法．信号处理．1998，14(2)：117-122，109
4．丁晓青，郭繁复．汉字识别研究和技术的发展与现状．电子与电脑．1995，(2)：109-112
5．杜敏，辛大欣．基于混合特征提取的手写体数字识别方法的研究．西安交通大学学报．1996，30(9)：93-98，112
6．范承亚．多体印刷汉字识别系统的识别模型和预处理技术．计算机工程与应用．1995，(4)：50-54
7．郭美义，王保保，杨晓丽．银行支票自动识别研究．现代电子技术．1997，(1)：13-15，27
8．韩永强．汽车牌照识别与管理系统．上海交通大学硕士研究生学位论文．1997
9．何斌，马天予，王运坚，朱红莲．Visual C++数字图像处理．人民邮电出版社，2001
10．何晓群．现代统计分析方法与应用．中国人民大学出版社，1998
11．胡正平．卡片自动录入系统算法的研究．燕山大学硕士研究生学位论文．1999
12．黄心晔，王茂祥，富煜清，陆佶人．基于结构分析的手写体数字识别算法．电子工程师．1999，(9)：23-25
13．荆仁杰，叶秀清，徐胜荣，陈存椿．计算机图像处理．浙江大学出版社，1990
14．卢纹岱，朱一力，沙捷，朱红兵．SPSS for Windows 从入门到精通．电子工业出版社，1997
15．吕凤军．数字图象处理编程入门．清华大学出版社，1999
16．马少平，夏莹，朱小燕．汉字的层次轮廓特征及其应用．清华大学学报(自然科学版)．1995，35(5)：79-83
17．毛忠萍．印刷体汉字识别系统的研究．北京机械工业学院学报．1994，9(2)：77-80
18．邱东．多指标综合评价方法地系统分析．中国统计出版社，1991
19．阮秋琦．数字图像处理学．电子工业出版社，2001
20．孙仲康，沈振康．数字图象处理及其应用．国防工业出版社，1985
21．陶志刚．啤酒瓶标识文字的自动识别．西安交通大学硕士学位论文．2001
22．王晓华，赵为平，高庆急，张茂川．采用基于结构特征的统计法识别火车车号．东北电力学院学报．1998，18(3)：79-83
23．王新成．高级图像处理技术．中国科学技术出版社，2001
24．王耀南，李树涛，毛建旭．计算机图像处理与识别技术．高等教育出版社，2001
25．吴雪菁，施鹏飞．质心层次特征的无约束手写体数字识别．上海交通大学学报．1998，32(9)：31-34
26．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
27．张纯，张涛，黄笑．中文商务名片识别系统的实现．中文信息学报．1999，14(2)：21-25
28．张元，王广宇，吕运朋．数字图像的不变特性与特征提取．郑州大学学报(自然科学版)．2000，32(4)：57-59
29．张晓明，周修光．手持扫描输入印刷体汉字特征提取方法的研究．计算机与数字工程．1995，23(2)：55-58
30．张炘中．汉字识别技术．清华大学出版社，广西科学技术出版社，1992
31．叶乃奉，张炘中，夏莹．汉字微型计算机与汉字识别．机械工业出版社，1989
32．赵宏宇．模糊神经网络用于手写体数字识别的研究．西南交通大学硕士学位论文．1995
33．赵荣椿，赵忠民，崔甦生．数字图象处理导论．西北工业大学出版社，1995
34．朱方．基于彩色图像处理的车牌识别系统的研究与开发．西安交通大学硕士学位论文．2001
35．余英林．数字图象处理与模式识别．华南理工大学出版社，1990
36．A．罗申菲尔特，A．C．卡克．余英林等译．数字图象处理．人民邮电出版社，1982
37．A．罗申菲尔特．陈彩廷等译．数字图象分析．科学出版社，1987
38. Abdall S. K. Feature Extraction Algorithm. Pattern Recognition. 1989, (1): 3-21
39. Alexits C. N. String Similarity and Misspellings. Communications of the Association for Computing Machinery. 1987, Vol. 10(5): 312-331
40. Bwonke H., Fliu San A. Chinese character recognition. Scientific World. 1989
41. Cui Guowei, Shu Wenhao. A microcomputer-based printed Chinese character recognition system. International Conference on Computer Processing of C. O. L. 1988: 96-99
42. D. Gou. Study on Subject-free Off-line Handwritten Chinese Character Recognition, PhD. Dissertation of Tsinghua University. 1995
43. Dayin Gou, Xiaoqing Ding, Youshou Wu. A Handwritten Chinese Character Recognition
Method Based on Image Shape Correction, Proc. Of 1st National Conference on Multimedia and Information Networks(CMIN), Beijing, 1995:254-259
44． Hilderbrandt T.H., Liu W.T. Optical Recognition of Handwratten Chinese Characters: Advances Since 1980． Pattern Recognition. 1993, Vol. 26(2) : 205-225
45． J. Kittler, J. Lingworth, J. Foglein, and K. Pater. Threshold Selection Based on A Simple Image Statistics. Computer Vision Graphics Image Process. 1985, Vol. 30: 125-147
46． J. S. Weszka. A Survey of Threshed Selection Techniques. Computer Graphics and Image Processing. 1978, Vol. 7(2) : 259-265
47． Jun Guo, Ning Sun, et al. Recognition of Handwritten Characters Using Pattern Transformation Method with Cosine Function. IEICE. 1993, Vol.J76-D-Ⅱ, No.4: 835-842
48． Keinosuke Fuku naka: Classification Error for a Very Large Number of Classes, IEEE Trans, on PAMI, 1984, Vol. PAMI-16(6) :779-788
49． Lewis P. M. Character Selection Problem in recognition System. IRE Tran. On Information Threory IT-8． 1962, (2) : 171-178
50． N. Otsu. A threshold selection method form gray-level histogram. IEEE Trans, on. 1979, Vol. (SMC-9) : ,62-69
51． Seong-Wham Lee and Jeong-Seon Park. Nonlinear Shape Normalization Methods for the Recognition of Large-set Handwritten Characters. Pattern Recognition. 1994, Vol 27: 895-902
52． T.Takahashi, I.Masuda. Handprinted Chinese Character Recognition using Stroke Extraction Method with Referral to Peripheral Structural Information. J. IECE. 1984,Vol. J67-D(9) : 1052-1059
53． Trier φ D, Jain A. K. Taxt T. Feature extraction methods for character recognition-a survey. Pattern Recognition. 1996,Vol. 29(4) :641-662
54． Y.S. Chungg, K..P. Chan. Modified Fuzzy Isodata for the Classification of Handwritten Chinese Characters. Proc. Intern. Conf. On Chinese Computing. 1986:361-364
55． Zhang Xinzhong, Feature point Method of Chinese Recognition and Its Application. Journal of Compute Science and Technol. 1990, Vol 5(4) :305-311
2．陈廷标，夏良正．数字图象处理．人民邮电出版社，1990
3．陈友斌，丁晓青，吴佑寿．一种手写汉字特征抽取的新方法．信号处理．1998，14(2)：117-122，109
4．丁晓青，郭繁复．汉字识别研究和技术的发展与现状．电子与电脑．1995，(2)：109-112
5．杜敏，辛大欣．基于混合特征提取的手写体数字识别方法的研究．西安交通大学学报．1996，30(9)：93-98，112
6．范承亚．多体印刷汉字识别系统的识别模型和预处理技术．计算机工程与应用．1995，(4)：50-54
7．郭美义，王保保，杨晓丽．银行支票自动识别研究．现代电子技术．1997，(1)：13-15，27
8．韩永强．汽车牌照识别与管理系统．上海交通大学硕士研究生学位论文．1997
9．何斌，马天予，王运坚，朱红莲．Visual C++数字图像处理．人民邮电出版社，2001
10．何晓群．现代统计分析方法与应用．中国人民大学出版社，1998
11．胡正平．卡片自动录入系统算法的研究．燕山大学硕士研究生学位论文．1999
12．黄心晔，王茂祥，富煜清，陆佶人．基于结构分析的手写体数字识别算法．电子工程师．1999，(9)：23-25
13．荆仁杰，叶秀清，徐胜荣，陈存椿．计算机图像处理．浙江大学出版社，1990
14．卢纹岱，朱一力，沙捷，朱红兵．SPSS for Windows 从入门到精通．电子工业出版社，1997
15．吕凤军．数字图象处理编程入门．清华大学出版社，1999
16．马少平，夏莹，朱小燕．汉字的层次轮廓特征及其应用．清华大学学报(自然科学版)．1995，35(5)：79-83
17．毛忠萍．印刷体汉字识别系统的研究．北京机械工业学院学报．1994，9(2)：77-80
18．邱东．多指标综合评价方法地系统分析．中国统计出版社，1991
19．阮秋琦．数字图像处理学．电子工业出版社，2001
20．孙仲康，沈振康．数字图象处理及其应用．国防工业出版社，1985
21．陶志刚．啤酒瓶标识文字的自动识别．西安交通大学硕士学位论文．2001
22．王晓华，赵为平，高庆急，张茂川．采用基于结构特征的统计法识别火车车号．东北电力学院学报．1998，18(3)：79-83
23．王新成．高级图像处理技术．中国科学技术出版社，2001
24．王耀南，李树涛，毛建旭．计算机图像处理与识别技术．高等教育出版社，2001
25．吴雪菁，施鹏飞．质心层次特征的无约束手写体数字识别．上海交通大学学报．1998，32(9)：31-34
26．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
27．张纯，张涛，黄笑．中文商务名片识别系统的实现．中文信息学报．1999，14(2)：21-25
28．张元，王广宇，吕运朋．数字图像的不变特性与特征提取．郑州大学学报(自然科学版)．2000，32(4)：57-59
29．张晓明，周修光．手持扫描输入印刷体汉字特征提取方法的研究．计算机与数字工程．1995，23(2)：55-58
30．张炘中．汉字识别技术．清华大学出版社，广西科学技术出版社，1992
31．叶乃奉，张炘中，夏莹．汉字微型计算机与汉字识别．机械工业出版社，1989
32．赵宏宇．模糊神经网络用于手写体数字识别的研究．西南交通大学硕士学位论文．1995
33．赵荣椿，赵忠民，崔甦生．数字图象处理导论．西北工业大学出版社，1995
34．朱方．基于彩色图像处理的车牌识别系统的研究与开发．西安交通大学硕士学位论文．2001
35．余英林．数字图象处理与模式识别．华南理工大学出版社，1990
36．A．罗申菲尔特，A．C．卡克．余英林等译．数字图象处理．人民邮电出版社，1982
37．A．罗申菲尔特．陈彩廷等译．数字图象分析．科学出版社，1987
38. Abdall S. K. Feature Extraction Algorithm. Pattern Recognition. 1989, (1): 3-21
39. Alexits C. N. String Similarity and Misspellings. Communications of the Association for Computing Machinery. 1987, Vol. 10(5): 312-331
40. Bwonke H., Fliu San A. Chinese character recognition. Scientific World. 1989
41. Cui Guowei, Shu Wenhao. A microcomputer-based printed Chinese character recognition system. International Conference on Computer Processing of C. O. L. 1988: 96-99
42. D. Gou. Study on Subject-free Off-line Handwritten Chinese Character Recognition, PhD. Dissertation of Tsinghua University. 1995
43. Dayin Gou, Xiaoqing Ding, Youshou Wu. A Handwritten Chinese Character Recognition
Method Based on Image Shape Correction, Proc. Of 1st National Conference on Multimedia and Information Networks(CMIN), Beijing, 1995:254-259
44． Hilderbrandt T.H., Liu W.T. Optical Recognition of Handwratten Chinese Characters: Advances Since 1980． Pattern Recognition. 1993, Vol. 26(2) : 205-225
45． J. Kittler, J. Lingworth, J. Foglein, and K. Pater. Threshold Selection Based on A Simple Image Statistics. Computer Vision Graphics Image Process. 1985, Vol. 30: 125-147
46． J. S. Weszka. A Survey of Threshed Selection Techniques. Computer Graphics and Image Processing. 1978, Vol. 7(2) : 259-265
47． Jun Guo, Ning Sun, et al. Recognition of Handwritten Characters Using Pattern Transformation Method with Cosine Function. IEICE. 1993, Vol.J76-D-Ⅱ, No.4: 835-842
48． Keinosuke Fuku naka: Classification Error for a Very Large Number of Classes, IEEE Trans, on PAMI, 1984, Vol. PAMI-16(6) :779-788
49． Lewis P. M. Character Selection Problem in recognition System. IRE Tran. On Information Threory IT-8． 1962, (2) : 171-178
50． N. Otsu. A threshold selection method form gray-level histogram. IEEE Trans, on. 1979, Vol. (SMC-9) : ,62-69
51． Seong-Wham Lee and Jeong-Seon Park. Nonlinear Shape Normalization Methods for the Recognition of Large-set Handwritten Characters. Pattern Recognition. 1994, Vol 27: 895-902
52． T.Takahashi, I.Masuda. Handprinted Chinese Character Recognition using Stroke Extraction Method with Referral to Peripheral Structural Information. J. IECE. 1984,Vol. J67-D(9) : 1052-1059
53． Trier φ D, Jain A. K. Taxt T. Feature extraction methods for character recognition-a survey. Pattern Recognition. 1996,Vol. 29(4) :641-662
54． Y.S. Chungg, K..P. Chan. Modified Fuzzy Isodata for the Classification of Handwritten Chinese Characters. Proc. Intern. Conf. On Chinese Computing. 1986:361-364
55． Zhang Xinzhong, Feature point Method of Chinese Recognition and Its Application. Journal of Compute Science and Technol. 1990, Vol 5(4) :305-311