- 无标题文档
查看论文信息

中文题名:

 复杂背景下的激光防伪码切分与识别算法设计    

姓名:

 吕妃    

学号:

 1049721203101    

保密级别:

 公开    

论文语种:

 chi    

学科代码:

 0810    

学科名称:

 信息与通信工程    

学生类型:

 硕士    

学位:

 工学硕士    

学校:

 武汉理工大学    

院系:

 信息工程学院    

专业:

 信息与通信工程    

研究方向:

 智能信息处理    

第一导师姓名:

 刘泉    

第一导师院系:

 武汉理工大学    

完成日期:

 2015-03-19    

答辩日期:

 2015-05-01    

中文关键词:

 复杂背景 ; 激光防伪码切分 ; 激光防伪码识别 ; Mean Shift ; LBP    

中文摘要:

近年来,假冒伪造商品在市场上频繁出现,严重影响着我国经济的发展。因此,在现代商品的生产和销售中,商品真伪信息的自动识别技术变得越来越重要,大量防伪手段应用而生。信息防伪码技术是一种识别商品真伪的有效方案,其中激光防伪码的自动识别技术对维护市场的正常运营起了重要作用。然而由于激光防伪码打码位置的不固定,导致激光防伪码背景复杂多变,而传统的字符自动识别技术通常针对背景单纯的高质量字符,因此研究适用于复杂背景下激光防伪码的切分与识别算法具有重要意义。

本文针对复杂背景下的激光防伪码图像,提出了基于MeanShift算法的防伪码字符提取方法,并设计了三种字符的切分方法,分别能够实现正常字符切分、交叉粘连字符切分和重叠字符切分,最后通过提取单个防伪码字符的局部二值模式(Local Binary Pattern,LBP)特征进行识别。论文主要研究工作如下:

(1)研究了MeanShift算法原理,并对原始的MeanShift算法进行了改进,将其应用于防伪码字符提取中。实验表明,本文所提出的防伪码字符提取算法能有效地从复杂的背景干扰和噪声中提取出较纯净的防伪码字符。此外,还研究了Hough变换原理,并将其应用到防伪码图像倾斜校正中,获得了较好的倾斜校正效果。。

(2)研究了防伪码字符的排列特点,将防伪码字符分为常规字符,交叉和粘连字符,重叠字符三类。针对三类不同排列规则的字符,分别采用投影法、曲线切分法和滑动窗口识别法进行切分。实验结果表明,本文的防伪码字符切分算法能够获得较多的正确切分的单个字符,对切分结果进行识别能够获得较高的识别正确率。

(3)研究了模板匹配算法和LBP算子原理,并将LBP特征用于防伪码字符识别中,比较分析了基于LBP特征、基于灰度和基于网格特征的分类结果,证明本文采用的基于LBP特征的识别算法能有效抵御背景干扰和笔画残缺变形的影响。

实验结果表明,本文提出的字符切分和识别算法可以很好的抑制复杂背景干扰及字符笔画断裂和变形等影响,在防伪码识别中获得了97.69%的高识别率。该方法已在激光防伪码识别手持终端中得到实际应用,效果良好。

参考文献:

[1] 徐大雄. 大力发展我国信息网络防伪技术 [J]. 中国数据通信, 2001,01.

[2] 蔡义望, 罗平, 彭小宁. 综合数字防伪方案 [J]. 清华大学学报(自然科学版), 2003,01: 90-93.

[3] 朱海燕. 激光标志技术迈入不断更新时代 [J]. 中国包装工业, 2012,14: 48-50.

[4] 郭虹. 卷烟包装防伪技术现状及发展方向 [J]. 中国包装工业, 2006,01:2-3.

[5] 陈大明,张荣贵,孙先胜,李彩平. 卷烟真伪鉴别及防伪技术研究 [J]. 中国包装工业,2002,05:38-42.

[6] Chang C I, Du Y, Wang J, Guo S M, Thouin P D. Survey and comparative analysis of entropy and relative entropy thresholding techniques [J]. Ieee Proceedings-Vision Image and Signal Processing, 2006, 153 (6): 837-50.

[7] Ashtari A H, Nordin M J, Fathy M. An Iranian license plate recognition [J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 5 (7): 1690-1705.

[8] 陈国彬,张广泉.一种基于特征加权模板匹配方法在纸币字符识别中的应用 [J]. 微电子学与计算机,2013,30(03):115-117.

[9] Zanibbi R, Blostein D, Recognition and retrieval of mathematical expressions [J] . International Journal on Document Analysis and Recognition (IJDAR),2011, 15: 331-357.

[10] Li N X, Jin L W, A Bayesian_based method of unconstrained handwritten offline Chinese text line recognition [J]. International Journal on Document Analysis and Recognition (IJDAR), 2013, 16: 17-31.

[11] Tanvir Parvez M, Mahmoud S A. Arabic handwriting recognition using structural and syntactic pattern attributes [J]. Pattern Recognition, 2013, 46 (1): 141-54.

[12] Jayadevan R, Kolhe S R, Patil P M, Pal U. Offline recognition of Devanagari script: A Survey [J]. Ieee Transactions on Systems Man and Cybernetics Part C-Applications and Reviews,2011, 41(6): 782-796.

[13] Awaidah S W, Mahmoud S A. A multiple feature/resolution scheme to Arabic (Indian) numerals recognition using hidden Markov models [J]. Signal Processing, 2009, 89: 1176-1184.

[14] Boulmerka A, Allili M S, Ait-Aoudia S. A generalized multiclass histogram thresholding approach based on mixture modelling [J]. Pattern Recognition, 2014, 47 (3): 1330-48.

[15] Niblack W. An introduction to digital image processing [J]. Strandberg Publishing Company, 1985.

[16] Kwon S H. Threshold selection based on cluster analysis [J]. Pattern Recognition Letters, 2004, 25 (9): 1045-50.

[17] Jing-Hao Xue, Yu-Jin Zhang, Ridler and Calvard's, Kittler land Illingworth's and Otsu's methods for image thresholding [J]. Pattern Recognition, 2012, 33(6): 793-797.

[18] Otsu N. A threshold selection method from gray-level histograms [J]. Automatica, 1975, 11 (285-296): 23-7.

[19] Niblack W. An introduction to digital image processing: Strandberg Publishing Company, 1985.

[20] Sahoo P K, Arora G. Image thresholding using two-dimensional Tsallis-Havrda-Charvat entropy [J]. Pattern Recognition Letters, 2006, 27 (6): 520-8.

[21] Max Mignotte. A de-texturing and spatially constrained K-means approach for image segmentation [J]. Pattern Recognition Letters, 2011, 32(2): 359-367.

[22] 林开颜, 吴军辉, 徐立鸿. 彩色图像分割方法综述 [J]. 中国图象图形学报, 2005, 10(1): 1-5.

[23] Muthukannan K, Merlin Moses M. Color image segmentation using K-means clustering and optimal Fuzzy C-Means clustering [C]. Proceedings of the International Conference on Communication and Computational Intelligence, 2010: 229-234.

[24] 林开颜, 徐立鸿. 快速模糊C均值聚类彩色图像分割方法 [J]. 中国图象图形学报, 2004, 9 (32): 160-163.

[25] 李宏益, 吴素萍. Mean Shift图像分割算法的并行化 [J]. 中国图象图形学报, 2013, 18(122): 1610-1619.

[26] 周家香, 朱建军, 梅晓明, 马慧云. 多维特征自适应Mean Shift遥感图像分割方法 [J]. 武汉大学学报(信息科学版), 2012, 4 (37): 419-422.

[27] Frank Y, Shih, Shouxian Cheng. Automatic seeded region growing for color image segmentation [J]. Image and Vision Computing, 2005, 23(10): 877-886.

[28] 杨彬蔚, 陆系群, 陈纯. 一种纺织印染团的多尺度彩色分割方法 [J]. 浙江大学学报(工学版), 2005, 39 (4): 530-533.

[29] Dinggang Shen, Horace H S Ip. A Hopfield neural network for adaptive image segmentation: An active surface paradigm[J]. Pattern Recognition Letters, 1997, 18 (1): 37-48.

[30] 刘群群. 不定长车牌字符分割算法研究 [D]. 浙江: 浙江大学, 2011.

[31] Tanvir Parvez M, Mahmoud S A. Arabic handwriting recognition using structural and syntactic pattern attributes [J]. Pattern Recognition, 2013, 46: 141-154.

[32] 万金娥, 袁保社, 李小, 古朝, 米尔沙力江沙吾提. 一种改进的印刷体维吾尔文投影切分法 [J]. 计算机工程, 2013:263-266.

[33] Congede G, Dimauro G, Impedovo S, Pirlo G. Segmentation of numeric strings [J]. IEEE Computer Society, 1995, 2: 1038-1041.

[34] Sadri J, Suen C Y, Bui T D. A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings [J]. Pattern Recognition, 2007, 40 (3): 898-919.

[35] M. Chen, W. Wu, X. Yang, and X. He, "Hidden-Markov-Model-Based Segmentation Confidence Applied to Container Code Character Extraction," Ieee Transactions on Intelligent Transportation Systems, vol. 12, pp. 1147-1156, Dec 2011.

[36] Dan Liu, Weiguo Fang, Hong Zhou, Yan Li. Bigram Chinese word segmentation by Viterbi algorithm [J]. Pattern Recognition, 2010, 43(1): 369-377.

[37] 赵巍, 刘家锋, 唐降龙, 吴锐. 连续字符识别的级联HMM训练算法 [J]. 计算机学报, 2007(12): 2142-50.

[38] 张勇. 基于统计法和结构法的手写数字识别研究 [D]. 武汉: 华中科技大学, 2011.

[39] Bindu S Moni, Raju G. Handwritten character recognition system using a simple feature [C]. Proceedings of the International Conference on Advances in Computing, Communications and Informatics, 2012: 728-734.

[40] Ali Broumandnia, Jamshid Shanbehzadeh. Fast Zernike Wavelet moments for farsi character recognition [J]. Image and Vision Computing, 2007, 25 (5): 717-726.

[41] 肖明, 贾振红. 基于轮廓特征的HMM手写数字识别 [J]. 计算机工程与应用, 2010(33): 172-174.

[42] 赖英超, 曾剑铭, 沈海斌. 基于连笔消除的空间手写字符识别方法 [J]. 计算机程, 2013,38(19): 154-158.

[43] Wang X, Ding X, Liu C. Gabor filters-based feature extraction for character recognition [J]. Pattern Recognition, 2005, 38 (3): 369-79.

[44] 王慧. 基于模板匹配的手写体字符识别算法研究 [D]. 北京:北京交通大学, 2012.

[45] Desai A A. Gujarati handwritten numeral optical character reorganization through neural network [J]. Pattern Recognition, 2010, 43: 2582-2589.

[46] Kumawat P, Lhatri A, Nagaria B. Offline handwriting recognition using invariant moments and curve let transform with combined SVM-HMM [C]. Communication Systems and Network Technologies(CSNT), 2013, 12: 144-148.

[47] Luts J, Ojeda F, Van de Plas R, De Moor B, Van Huffel S, Suykens J A K. A tutorial on support vector machine-based methods for classification problems in chemometrics [J]. Analytica Chimica Acta, 2010, 665 (2): 129-45.

[48] Leiguang Wang, Guoying Liu, Qingling Dai. Optimization of segmentation algorithms through Mean-Shift filtering preprocessing [J]. Geoscience and Remote Sensing Letters, IEEE, 2013, 11 (3): 622-626.

[49] Bin Li, Jian Zhang, Zheng Zhang, Yong Xu. A people counting method based on head detection and tracking [C]. Smart Computing(SMARTCOMP), 2014: 136-141.

[50] Lebourgeois F, Drira F, Gaceb D, Duong J. Fast intergral MeanShift application to color segmentation of document images [C]. Document Analysis and Recognition(ICDAR), 2013: 53-56.

[51] 刘锦峰. 图像模板匹配快速算法研究 [D]: 中南大学, 2007.

[52] 赵怀勋, 徐锋, 陈家勇. 基于多尺度LBP的人脸识别 [J]. 计算机应用于软件, 2012, 1 (29): 257-259.

[53] Zhihua Xie, Zhengzi Wang. Joint encoding of multi-scale LBP for infrared face recognition [J]. Genetic and Evolutionary Computing, 2015, 329:269-276.

[54] Ghada Shams, Mohamed Ismail, Sohier Bassiouny, Nagia Ghanem. Face and palmprint recognition using hierarchical multiscale adaptive LBP with directional statiscal features [J]. Image Analysis and Recognition, 2014, 8815: 102-111.

[55] Yasuko Takahashi, Hisako Tanaka, Pakira Suzuki. License plate recognition using gray image template matching with noise reduction filters and character alignment [J]. Systems and Computers, 2013, 3(38):49-61.

中图分类号:

 TP391.41    

馆藏号:

 TP391.41/3101/2015    

备注:

 403-西院分馆博硕论文库;203-余家头分馆博硕论文库    

无标题文档

   建议浏览器: 谷歌 火狐 360请用极速模式,双核浏览器请用极速模式