摘要
印章识别一直是一个比较困难的课题,目前银行使用的方法是手工操作,将支票上的印章像与客户留下的原始印章像进行手工折角比对,其缺点是人为因素多、准确性差、工作效率低。而实现印章管理和识别的电子化、自动化、智能化,能提高印章识别的准确性和可靠性,可以有效防止利用假印章进行诈骗的犯罪活动。
论文首先介绍了图象识别的基础知识和特征提取的相关理论作为论文的理论基础,之后完成了印章识别的总体设计,在印章预处理的基础上,重点研究了印鉴纹理的特征提取的设计及其算法的实现,以及运用神经网络的判别方法对所提取的印章特征进行判别,以识别印章的真伪。
在本文中,分析了防伪印章的特点,从图像纹理和分析的角度出发,对印章图像纹理的特征提取与选择特征参数进行了分析比较,设计了一种基于印章纹理的印章识别系统。预处理阶段:利用中值滤波去除图像的噪声后,采用基于颜色的印章图像分割技术将印章图像从背景中分割出来,在此基础上进行二值化,并通过边缘轮廓的提取是要分割出包含印章区域的最小区域。在特征提取阶段:采用灰度共生矩阵的方法来对印章纹理进行熵、能量、惯性距、局部平稳性、相关性的特征提取。在模式匹配阶段:利用BP网络的思想设计了一个真正的BP神经网络,经过样本训练后,对印章图像进行真伪的验证。
通过实验数据说明该方法可以正确提取印鉴纹理的纹理特征,在与神经元网络结合后其,通过对手头样本的测试与实验,除了个别模糊的样本外,能够鉴别大部分印章,在有限人工干预的情况下基本能够满足部分应用。该方法的算法简单,并经实验验证及数据表明,该方法是从一种新的角度进行了印章识别,提出了识别印章的新的途径。
Seal Identification has been a comparatively difficult thesis. It is done by hand in the bank at present, which is checking on the seal that customers left with the original seal through the manual folding. Its shortcomings are many personal factors, bad accuracy and low efficiency. It can be improve for seal's accuracy and reliability to carry out the seal administration and identification electronic, automated, intellectualized, which can prevent effectively making use of fake seal to commit a defrauding crime.
Firstly, the paper has introduced the relevance theory of image identification and characteristic extract, which is the theory basis. Secondly, complete the total design of seal identification. Based on the seal pretreatment, we study the design and calculation of vein characteristic extract and distinguish the seal feature abstracted using the neural networks discriminant, which is to distinguish whether the seal is truth or false.
In this paper, we analyse the characteristic of guarding against false seal, From the image vein and the analytical angle, we compare with the vein characteristic abstracts and the characteristic parameter chose and design a seal Identification system based on seal vein. Pretreatment stage: Make use of middle value wave filter the image noise, adopt carved technology based on the colour seal image to carve the seal image from the background. Base on this, we carry our the value two here and carve up out the minimal area containing seal area with border outline extract. Extract a stage in the characteristic: We extract the entropy, energy, inertia distance, part balance, correlativity on seal vein. Stage mating in the pattern: Make use of network thought BP to designe a real BP neural networks. Carry out truth or false verification on seal image after the sample trained.
Our data suggested that the vein characteristic can be extracted exactly using this method. After linking the neural network, we experiment the samplet on hand, we can distinguish most seal except individual illegibility sample. The algorithm is simple and verified. The data indicate this method which is distinguishing seal from the new angle and have brought a new approach to distinguish seal. The method can prevent effectively making use of fake seal to commit a defrauding crime.
引文
[1] Ueda. Nakamura. Automatic verification of seal impression patterns proc 7-th Int Conf[j].Pattern Recognition(ICPR),1984,(2):1019-1021.
[2] Fan T J, Tsai W H. Automatic Chinese seal identification[J].Computer Vision Graphics and Image Processing, 1984,25(2):311-330.
[3] 陈燕新,李卫东,威飞虎.基于边缘喝模版匹配的印鉴自动鉴别方法[J].上海交通大学学报,1998,32(4):44-48.
[4] Hu Qing. An automatic seal imprint verification approach. Pattern Recognition, 1995,28(8):1251-1266.
[5] 曾东武,刘重庆,陶世焰.Fourier描述符的印鉴识别方法[J].上海交通大学学报,1998,32(9):43-45.
[6] 屈志毅,李炬嵘,王玉珍.印鉴自动识别系统中影像处理与识别的方法研究[J].甘肃科学学报,2002,13(1):12-17.
[7] 杨新军,王肇,刘唯一等.基于环投影模版匹配的印鉴鉴别法[J].计算机工程与应用,2004,24(54):54-57.
[9] 刘珍丽,傅德胜.基于Bubble小波函数德印鉴鉴别[J].南京气象学院学报,2002,25(5):698-702.
[10] 张先萌,罗安玉,王翔等.用矩不变量实现印鉴自动识别.电子学报,1995,23(4):10-14.
[11] 朱勇,谭铁牛,王蕴红.基于笔迹德身份鉴别.自动化学报,2001,27(2):229-234.
[12] 尤佳,王绍纯,李希胜等.通过转炉口火焰纹理分析判断氧气顶吹转炉吹炼终点.北京科技大学学报,2000,22(6):500-505.
[13] 张兴然,赵成勇,魏清.基于小波变换的二维图像识别与信号压缩.电力科学与工程,2005,21(6):200-213.
[14] 朱虹,李晗,辛威,邓颖娜.基于多特征的多分类器融合决策印鉴识别.计算机工程与应用,2004,27(4):372-376.
[15] 余立功,王强,卜佳俊.印鉴识别相似度的计算框架.计算机辅助设计与图形学学报,2004,33(9):264-278.
[16] 郎锐.数字图像处理学VC++实现.北京:北京希望电子出版社,2002.
[17] 刘怡光,游志胜,曹丽萍.一种快速图像识别方法.计算机工程,2005,26(2):491-497.
[18] 郭娟,王广阔.灰度图像的最佳阈值分割算法.济宁师范专科学校学报,2005,30(7):43-56.
[19] 周长发.精通Visual C++图像编程,北京:电子工业出版社,2000.
[20] HUANGWei LUXiaobo LINGXiaojing. Wavelet packet based feature extraction and recognition of license plate characters. Chinese Science Bulletin (中国科学通报:英文版) ,2005, 13 (1) : 12-19.
[21] SHILei[1], HONGFan[1], LIUWei-qun[2], HUYu-ping[2], CHENZhuo[1]. A Geometrical Transformations Resistant Digital Watermarking Based on Quantization. Wuhan University Journal of Natural Sciences(武汉大学学报:自然科学英文版),2005,12(11):187-194.
[22] YANGQing CHENKe-fei. A Secure Public-key Image Authentication Plan. Wuhan University Journal of Natural Sciences (武汉大学学报:自然科学英文版),2005,26 (55):59-65.
[23] 罗琳,彭复员,徐国华.基于纹理特征的水下烟囱图像识别.华中科技大学电子与信息工程系,2004,25(5):772-776.
[24] 王大志,黄劫,徐树英.采用灰度直方图的孔型识别和二值化阈值自动匹配.四川大学制造科学与工程学院,2005,23(4):15-20.
[25] 扬淑莹.VC++图像处理程序设计.北京:清华大学出版社.北方交通大学出版社,2003,11.
[26] 徐慧,VC++数字图像实用工程案例精选.北京:人民邮电出版社,2004.
[27] 屈彦呈,王常虹,庄显义,Edge detection based on object tree image representation and wavelet transform, Journal of Harbin Institute of Technology (哈尔滨工业学报:英文版),2003,22 (6):456-467.
[28] 陈联景.金融机构大力支持生物识别技术A &S:国际中文版,2005.
[29] 王小玲,谢康林.一种新的基于区域的图像检索方法.计算机工程与应用,2005,23(4):21-15.
[30] 吴锐,刘家锋,唐降龙等.基于Gabor小波变换的汉字识别方法.哈尔滨工业大学计算机科学与技术学院,2004,24(5):650-661.
[31] 王焮,张浩.人工神经网络在图像识别中的应用,中国科教博览,2005,27(2):33-39.
[32] 温凤兰.识别图像里的文字,办公自动化,2005,30(5):47-60.
[33] 余杨,崔一平.基于取阈分解的形态学相关灰度图像识别算法改进研究.激光,2004,25(5):657-668.
[34] S. Newsam, C. Kamath, Comparing Shape and Texture Features for Pattern Recognition in Simulation Data, Algorithms and Systems Ⅳ, SPIE Electronic Imaging, January 2005.
[35] Shawn D. Newsam and Chandrika Kamath, Retrieval Using Texture Features in High Resolution Multi-spectral Satellite Imagery, Data Mining and Knowledge Discovery: Theory, Tools, and Technology VI, SPIE Defense and Security Symposium Orlando, Florida, April 12-16, 2004.
[36] John R. Smith and Shih-Fu Chang, Automated Binary Texture Feature Sets for Image Retrieval, Columbia University Department of Electrical Engineering January 2005.
[37] Anil Jain, Arun Ross, Salil Prabhakar ,FINGERPRINT MATCHIN6 USING MINUTIAE AND TEXTURE FEATURES, Michigan State University East Lansing, MI 48824, Redwood City, CA 94063 salilp fjain.
[38] N. Kehtarnavaz, Texas A&M UniversityB. N. Araabi, Texas A&M University, Classification of Simulated Elastograms Based on Texture Features, 14th IEEE Symposium on Computer-Based Medical Systems (CMBS'01).
[39] 彭仁明.基于彩色的印鉴图像分割技术.甘肃科技,2005(09):30-32.
[40] 王刚.基于人机交互的半自动土壤粗糙度测量系统.计算机工程与应用,2004(11):226-228.
[41] 邹晓,靳艳峰.基于贪心算法进行三角剖分的印鉴匹配方法.计算机工程与设计,2007(5):213-215.
[42] 张玲,张永军,何伟,郭磊民.鉴印系统中印章几何参数的计算.信息与电子工程,2006(3):40-41.
[43] 吴向君,章春娥,裘正定.签章域的防伪数字水印.北京电子科技学院学报,2005(2):30-33.
[44] 王建萍.图像信息数字化处理应用于会计法人印章识别.会计之友,2005(4):50-51.
[45] 张玲,郭磊民,何伟,陈丽敏.鉴印系统中印章的提取与修复.重庆大学学报(自然科学版),2005(3):88-91.
[46] 王胜科,王知衍,张艳青.基于非线性预处理策略的文档图像二值化处理.海南大学学报(自然科学版),2005(1):39-43.
[47] 陈志云,李志敏,赵永涛等.基于Hough变换的印鉴差值匹配识别.重庆大学学报(自然科学版),2006(2):36-38.
[48] 赵永涛,李志敏,王洪建,陈志云,王林.印章识别中的图像预处理研究.仪器仪表学报,2004(2):409-411.
[49] 艾武,彭磊,李玲玲等.用于支票印鉴鉴别的图像预处理及配准算法.计算机工程与应用,2003(3):34-37.
[50] 常军民,陈国定.一种基于神经网络判断的印鉴自动鉴别新方法。浙江工业大学学报,2005,33(3):268-271.