PDF417二维条码识别技术的研究及其在Linux平台下的实现
|
摘要
随着计算机技术的不断发展,条码技术也得到了进一步的研究以及应用,由原先的一维条码发展到了现在的二维条码,条码的各方面性能得到了大大的提高。而条码技术中,条码的识别技术一直是研究的重点,也是应用中必须解决的一个难题。本文研究了一种常用的二维条码——PDF417,并研究和实现了它的识别过程。
在实际应用中,我们采集到的条码图像,不单单包括了条码,而且还有其他图案以及文本。所以我们要从图像中检测出条码所在区域,然后才能对条码进行处理。因此条码检测是条码识别的基础。本文提出了一种基于形状特征的二维条码PDF417的检测算法,因为PDF417条码的是由一些条空矩形区域堆砌而成,所以我们先找出图像中的矩形区域,然后根据条码的起始符以及终止符的条空关系来筛选出属于条码的矩形区域。实验表明了,基于形状特征的二维条码PDF417的检测算法具有良好的性能。
我们从条码图像检测到条码以后,下一步就是如何得到条码中的信息,我们称之为条码识别,条码识别是条码技术中的一个核心。在条码中,条码字符表示一个信息的基本单元,因此在对条码识别时,我们首先要把条码分割成条码字符,然后对条码字符进行识别。本文提出了利用三次卷积插值的方法对条码进行旋转定位,根据条码的水平和垂直投影的边缘特征,将条码分割成条码字符。其次建立条码字符的隐马尔科夫模型,然后利用Viterbi解码算法得到条码字符的最优码字解。最后对码字集合进行纠错译码和信息译码。实验表明,本文的识别算法具有良好的性能,能够快速准确的识别出图像中的条码信息。
最后,我们利用C语言实现了我们的条码检测与识别算法,并将它封装成了Linux操作系统下的.a库文件,同时调用该库文件实现了一个二维条码PDF417的解码系统。实验表明,该系统具有良好的稳定性以及实用性。
With the development of Computer- technology, bar-code technology is further studied and applied. And with one dimensional barcode developing to two-dimensional bar code, the properties of bar-code in all aspects are enhanced markedly. In the bar-code technology, the bar code recognition technology is always the research emphasis and difficult problem in application. A commonly used two-dimensional barcode--PDF417 is studied and realized in this paper.
Bar code detection is the basis of bar code recognition. In reality application in a bar code image not only bar code but also other images and texts are included, so the area where the bar code exists must be detected first. A detection algorithm of two-dimensional barcode- PDF417 based on Shape Feature is proposed in this paper. Because some bars and spaces with rectangle shapes compose the barcode PDF417, the rectangle areas of the barcode image is first found out. Basing on the relationships between bar code start character and end character, the ones belong to the bar code are screened. The detection algorithm is proved to have good performance through experiment.
The bar code recognition is a key component of the bar code technology. After the bar code is detected ,the bar code is cut into bar code character , which is recognized then. And this recognition is a process of finding the real edges of the bar and space of the bar code and removing the edges generated by noises. In this paper we rotate the position of the bar code by the cubic interpolation method.According to the edge features of the horizontal and vertical projection ,we divide the bar code into bar code characters,and then set up the Hidden Markov Model of PDF417, decode the bar code character by using viterbi decoding algorithm, at last we can get the imformation from the code word. Experiments show that the recognition algorithm is of good performance.
Finally, the Linux system and the programming environment within it is studied. Under the environment,A PDF417 decoding system has been realized. The experiments show that this system is proved to be stable and practicable.
在实际应用中,我们采集到的条码图像,不单单包括了条码,而且还有其他图案以及文本。所以我们要从图像中检测出条码所在区域,然后才能对条码进行处理。因此条码检测是条码识别的基础。本文提出了一种基于形状特征的二维条码PDF417的检测算法,因为PDF417条码的是由一些条空矩形区域堆砌而成,所以我们先找出图像中的矩形区域,然后根据条码的起始符以及终止符的条空关系来筛选出属于条码的矩形区域。实验表明了,基于形状特征的二维条码PDF417的检测算法具有良好的性能。
我们从条码图像检测到条码以后,下一步就是如何得到条码中的信息,我们称之为条码识别,条码识别是条码技术中的一个核心。在条码中,条码字符表示一个信息的基本单元,因此在对条码识别时,我们首先要把条码分割成条码字符,然后对条码字符进行识别。本文提出了利用三次卷积插值的方法对条码进行旋转定位,根据条码的水平和垂直投影的边缘特征,将条码分割成条码字符。其次建立条码字符的隐马尔科夫模型,然后利用Viterbi解码算法得到条码字符的最优码字解。最后对码字集合进行纠错译码和信息译码。实验表明,本文的识别算法具有良好的性能,能够快速准确的识别出图像中的条码信息。
最后,我们利用C语言实现了我们的条码检测与识别算法,并将它封装成了Linux操作系统下的.a库文件,同时调用该库文件实现了一个二维条码PDF417的解码系统。实验表明,该系统具有良好的稳定性以及实用性。
With the development of Computer- technology, bar-code technology is further studied and applied. And with one dimensional barcode developing to two-dimensional bar code, the properties of bar-code in all aspects are enhanced markedly. In the bar-code technology, the bar code recognition technology is always the research emphasis and difficult problem in application. A commonly used two-dimensional barcode--PDF417 is studied and realized in this paper.
Bar code detection is the basis of bar code recognition. In reality application in a bar code image not only bar code but also other images and texts are included, so the area where the bar code exists must be detected first. A detection algorithm of two-dimensional barcode- PDF417 based on Shape Feature is proposed in this paper. Because some bars and spaces with rectangle shapes compose the barcode PDF417, the rectangle areas of the barcode image is first found out. Basing on the relationships between bar code start character and end character, the ones belong to the bar code are screened. The detection algorithm is proved to have good performance through experiment.
The bar code recognition is a key component of the bar code technology. After the bar code is detected ,the bar code is cut into bar code character , which is recognized then. And this recognition is a process of finding the real edges of the bar and space of the bar code and removing the edges generated by noises. In this paper we rotate the position of the bar code by the cubic interpolation method.According to the edge features of the horizontal and vertical projection ,we divide the bar code into bar code characters,and then set up the Hidden Markov Model of PDF417, decode the bar code character by using viterbi decoding algorithm, at last we can get the imformation from the code word. Experiments show that the recognition algorithm is of good performance.
Finally, the Linux system and the programming environment within it is studied. Under the environment,A PDF417 decoding system has been realized. The experiments show that this system is proved to be stable and practicable.
引文
[1] Pavlidis T. and Swartz J.. Fundamentals of bar code information theory.IEEE Computer, 1990, 23(4):74-86.
[2] Pavlidis T., Swartz, J. and Wang Y. P.. Information encoding with two-dimensional bar codes. IEEE Computer, 1992, 25(6):18-28.
[3] Vangils W. J.. Two-dimensional dot code for product identification. IEEE Trans. Information Theory, Sept.1987:620-631.
[4]张铎,王耀球.条码技术与电子数据交换.中国铁道出版社, 1998.
[5]中国物品编码中心,中国自动识别技术协会,条码技术基础,武汉大学出版社,2008.1
[6] Chang I. F., Chu S. J. and Liu, S. T.. Bar code scanning information entry technology and application. International Journal on Policy and Information, 1983, 7(2):165-180.
[7] Wang Y. P., Pavlidis T., Swartz J. Analysis of one-dimensional bar code. Proceedings of SPIE, v 1384, 1991:145-160.
[8] Wang Y. P., Pavlidis T. and Swartz J.. High density two dimensional bar code. Proceedings of SPIE , v 1384, 1991:169-175.
[9] Longacre A. J.. Stacked bar code symbologies. Identification Journal, 1989, 11(1):12-14.
[10] Wang Y. P.. Spatial information and coding theory. PhD thesis, SUNY, Stony Brook, Dec, 1989.
[11]中国物品编码中心,二维条码技术与应用,中国计量出版社, 2007.7.
[12] Palmer R. C.. The bar-code book. Helmers Publishing, Peterborough, 1989.
[13] Hiramoto J.. Past&present future of 2-dimension code technique. Monthly Barcode, 1996, Apr:35-39.
[14] Hiramoto J.. Expectation for 2-dimension symbolization. Monthly Barcode, 1996, Apr: 35-39.
[15] Kurosawa Y.. Application Status of 2-dimension symbol in Europe and US. Monthly Barcode, 1996,Dec:42-47.
[16] Gaston C. A.. Bar code and reading technique. IBM Technical Disclosure Bulletin, 1973,15(11).
[17] Savir D. and Laurer G.. The featureistics and decode ability of the universal product code. IBM Systems Journal, 1975, 14:16-33.
[18]刘宁钟,杨静宇.三维条码的编码理论和设计.计算机学报, 2007, 30(4):686-692.
[19]刘宁钟.高维条码识别技术和编码理论的研究.南京理工大学博士学位论文,2003.4.
[20] Jain A. K. and Chen Y.. Bar code localization using texture analysis. Proceedings of the 2nd International Conference on Document Analysis and Recognition,1993(Oct):41-44.
[21] Jain A. K. and Farrokhnia F.. Unsupervised texture segmentation using Gabor filters. Pattern Recognition, 1991, 24(12) :1167-1186.
[22] Chang C. Alec, Lo Chih-Chung and Hsieh Kuang-Han. Neural networks and Fourier descriptors for part positioning using bar code features in material handling systems. Computers & Industrial Engineering, 1997,32(2):467-476.
[23] Viard-Gaudin C., Normand N. and Barba D.. Bar code location algorithm using a two-dimensional approach.Proceedings of the 2nd International Conference on Document Analysis and Recognition, 1993(Oct):45-48.
[24] Arnould S., Awcock G. J.,and Thomas R.. Remote bar-code localization using mathematical morphology. IEE Conference Publication, v 2, n 465, 1999:642-646.
[25] Yinghong Liang,Zhiyan Wang. A Skew Detection Method For 2D Bar Code Images Based On The Least Square Method. Proceedings of the Fifth International Conference on Machine Learning and Cybernetics,Dalian,13-16 August 2006.
[26]刘宁钟.复杂背景中条码检测定位技术的研究.南京航空航天大学学报, 2005, 37(1):65-69.
[27] Kato, Hiroko, Tan, etal. Development of a Novel Finder Pattern for Effective Color 2D-Barcode Detection. Parallel and Distributed Processing with Applications, 2008. ISPA '08. International Symposium on 10-12 Dec. 2008 Page(s):1006 - 1013
[28] Kuroki Mikio, Yoneoka Takayuki, Satou Tetsuo, etal. Bar-code recognition system using image processing. IEEE Symposium on Emerging Technologies & Factory Automation, 1997:568-572.
[29] E. Ottaviani A., Pavan M., Bottazzi E., etal. Guerrero, A common image processing framework for 2D bar code reading. The Seventh International Conference on Image Processing and itsApplications, 1999:652-655.
[30] Normand N. and Viard-Guadin C.. Two dimensional bar code reader. Proceedings of SPIE, v 2181, 1994: 125-132.
[31] Shellhammer S. J., Goren D. P., Pavlidis T.. Selective sampling and edge enhancement in bar code laser scanning. SPIE Document Recognition, v 2660, 1996:354-366
[32] Shellhammer S. J., Goren David P. and Pavlidis, T.. Novel signal-processing techniques in barcode scanning. IEEE Robotics and Automation Magazine, 1999, 6(1):57-65
[33] Liao Hong Yuan, Liu Shu-Jen, Chen Liang-Hua and Tyan Hsiao-Rong. Bar-code recognitionsystem using backpropagation neural networks. Engineering Applications of Artificial Intelligence, 1995,8(1):81-90.
[34] Okol'nishnikova L. V.. Polynomial algorithm for recognition of bar codes. Pattern recognition and image analysis, 2001, 11(2):361-364.
[35] Turin W. and Boie R. A.. Bar code recovery via the EM algorithm. IEEE Trans. on Signal Processing, 1998, 46(2): 354-363.
[36] Turin W. and Boie R. A.. Minimum discrimination information bar code decoding. Proceedings of the 1996 19th Convention of Electrical and Electronics Engineers in Israel, 1996:255-258.
[37] Boie, R.A., Turin W.. Noise-limited reading of bar codes. IEEE Trans. on Industrial Electronics, 1997,44(6):816-824.
[38] Hee Il Hahn,Joung Koo Joung. Implementation of algorithm to decode two-dimensional barcode PDF-417. 6th International Conference on Signal Processing, 2002
[39] Hee Il Hahn,Jung Goo Jung. Improving performance of the decoder for two-dimensional barcode symbology PDF417. Informatics in Control,Automation and Robotics I,233-237,Springer,2006.3
[40] Ramtin Shams, Parastoo Sadeghi. Bar Code Recognition In Highly Distorted And Low Resolution Images. Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on.
[41]刘宁钟,杨静宇.基于傅立叶变换的二维条码识别.中国图像图形学报, 2003, 8(8):877-882.
[42]刘宁钟,杨静宇.基于波形分析的二维条码识别.计算机研究与发展, 2004, 41(3):463-469.
[43]刘宁钟,杨静宇.综合利用投影算法和相似距离算法的二维条码识别.模式识别与人工智能, 2003, 16(1):86-90.
[44]刘宁钟,杨静宇.基于中点检测的二维条码识别.小型微型计算机系统, 2004, 25(2):283-286.
[45] Sherin M. Youssef, Rana M. Salem.Automated barcode recognition for smart identification and inspection automation.Expert Systems with ApplicationsVolume 33, Issue 4, November 2007, Pages 968-977.
[46] AIM, 1994, Uniform Symbology Specification: PDF417.
[47]中华人民共和国国家标准GB/T17172—1997,中国标准出版社, 1998.8.
[48]章毓晋.图像处理和分析[M].清华大学出版社, 1999. 3.
[49] Milan Sonka, Vaclav Hlavac, Roger Boyle著.图像处理、分析与机器视觉(第二版)[M].艾海舟等译,人民邮电出版社,2003.9.
[50]沈庭芝,方子文.数字图像处理及模式识别.北京理工大学出版社, 1998.
[51] Kenneth. R. Castleman.数字图像处理.电子工业出版社, 1998.
[52] Rafael C. Gonzalez, Richard Eugene Woods. Digital Image Processing[M]. Prentice Hall,2007.
[53]郭德方.遥感图象的计算机处理和模式识别[M].北京:电子工业出版社, 1987.
[54]马振华等.现代应用数学手册,概率统计与随机过程卷.清华大学出版社,2000.440-457.
[55] Rabiner L R. A tutorial on hidden Markov Models and selected applications in speech recognition. In:Proceedings of the IEEE.1989,77(2):257-286.
[56] Sehuller,Gerhard Rigoll, Manfred Lang. Hidden Markov Based Speech Recognition. Proceedings of 2003 IEEE International Conference on Acoustics, Speech, &Speech Processing April 6-l0,2003.
[57] Yi-Lin Lin, Gang Wei. Speech Emotion Based on HMM and SVM. Proceedings of Fouah International Conference on Machine Learning and Cybernetics, Guangzhou, 18—21August 2005.
[58] Anigbogu, J.C., Belaid, A.. Performance evaluation of an HMM based OCR system.Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on 30 Aug.-3 Sept. 1992 Page(s):565– 568
[59]张震,任远,平西建等.基于图像质量评价量和隐马尔科夫模型的图像拼接检测.武汉大学学报, 2008.10
[60] AJ Elms and J Illingworth. Combination of HMMs for the representation of printed characters in noisy document images. Image and Vision Computing, 1995.6, 5(13):385-392
[61]李杰.隐马尔科夫模型的研究及其在图像识别中的应用.清华大学博士学位论文, 2004.6.
[62] Li J,Wang J X,Zhao Y N,et al. Self-adaptive design of hidden Markov models. Pattern Recognition Letters,2004,25(2):197-210
[63]赵炯. Linux内核完全剖析.机械工业出版社, 2007.4
[64] Daniel P. Bovet, Marco Cesati. Understanding the Linux Kernel. O'Reilly Media, Inc. 2005.11
[65]陈莉君等. Linux操作系统原理与应用.清华大学出版社, 2008.9
[66] William von Hagen. The Definitive Guide to GCC,Second Edition. Apress, 2006.8
[67] Arthur Griffith. GCC:The Complete Reference. McGraw-Hill, 2002.9
[68]董永清. Linux C编程实战.人民邮电出版社, 2008.1
[2] Pavlidis T., Swartz, J. and Wang Y. P.. Information encoding with two-dimensional bar codes. IEEE Computer, 1992, 25(6):18-28.
[3] Vangils W. J.. Two-dimensional dot code for product identification. IEEE Trans. Information Theory, Sept.1987:620-631.
[4]张铎,王耀球.条码技术与电子数据交换.中国铁道出版社, 1998.
[5]中国物品编码中心,中国自动识别技术协会,条码技术基础,武汉大学出版社,2008.1
[6] Chang I. F., Chu S. J. and Liu, S. T.. Bar code scanning information entry technology and application. International Journal on Policy and Information, 1983, 7(2):165-180.
[7] Wang Y. P., Pavlidis T., Swartz J. Analysis of one-dimensional bar code. Proceedings of SPIE, v 1384, 1991:145-160.
[8] Wang Y. P., Pavlidis T. and Swartz J.. High density two dimensional bar code. Proceedings of SPIE , v 1384, 1991:169-175.
[9] Longacre A. J.. Stacked bar code symbologies. Identification Journal, 1989, 11(1):12-14.
[10] Wang Y. P.. Spatial information and coding theory. PhD thesis, SUNY, Stony Brook, Dec, 1989.
[11]中国物品编码中心,二维条码技术与应用,中国计量出版社, 2007.7.
[12] Palmer R. C.. The bar-code book. Helmers Publishing, Peterborough, 1989.
[13] Hiramoto J.. Past&present future of 2-dimension code technique. Monthly Barcode, 1996, Apr:35-39.
[14] Hiramoto J.. Expectation for 2-dimension symbolization. Monthly Barcode, 1996, Apr: 35-39.
[15] Kurosawa Y.. Application Status of 2-dimension symbol in Europe and US. Monthly Barcode, 1996,Dec:42-47.
[16] Gaston C. A.. Bar code and reading technique. IBM Technical Disclosure Bulletin, 1973,15(11).
[17] Savir D. and Laurer G.. The featureistics and decode ability of the universal product code. IBM Systems Journal, 1975, 14:16-33.
[18]刘宁钟,杨静宇.三维条码的编码理论和设计.计算机学报, 2007, 30(4):686-692.
[19]刘宁钟.高维条码识别技术和编码理论的研究.南京理工大学博士学位论文,2003.4.
[20] Jain A. K. and Chen Y.. Bar code localization using texture analysis. Proceedings of the 2nd International Conference on Document Analysis and Recognition,1993(Oct):41-44.
[21] Jain A. K. and Farrokhnia F.. Unsupervised texture segmentation using Gabor filters. Pattern Recognition, 1991, 24(12) :1167-1186.
[22] Chang C. Alec, Lo Chih-Chung and Hsieh Kuang-Han. Neural networks and Fourier descriptors for part positioning using bar code features in material handling systems. Computers & Industrial Engineering, 1997,32(2):467-476.
[23] Viard-Gaudin C., Normand N. and Barba D.. Bar code location algorithm using a two-dimensional approach.Proceedings of the 2nd International Conference on Document Analysis and Recognition, 1993(Oct):45-48.
[24] Arnould S., Awcock G. J.,and Thomas R.. Remote bar-code localization using mathematical morphology. IEE Conference Publication, v 2, n 465, 1999:642-646.
[25] Yinghong Liang,Zhiyan Wang. A Skew Detection Method For 2D Bar Code Images Based On The Least Square Method. Proceedings of the Fifth International Conference on Machine Learning and Cybernetics,Dalian,13-16 August 2006.
[26]刘宁钟.复杂背景中条码检测定位技术的研究.南京航空航天大学学报, 2005, 37(1):65-69.
[27] Kato, Hiroko, Tan, etal. Development of a Novel Finder Pattern for Effective Color 2D-Barcode Detection. Parallel and Distributed Processing with Applications, 2008. ISPA '08. International Symposium on 10-12 Dec. 2008 Page(s):1006 - 1013
[28] Kuroki Mikio, Yoneoka Takayuki, Satou Tetsuo, etal. Bar-code recognition system using image processing. IEEE Symposium on Emerging Technologies & Factory Automation, 1997:568-572.
[29] E. Ottaviani A., Pavan M., Bottazzi E., etal. Guerrero, A common image processing framework for 2D bar code reading. The Seventh International Conference on Image Processing and itsApplications, 1999:652-655.
[30] Normand N. and Viard-Guadin C.. Two dimensional bar code reader. Proceedings of SPIE, v 2181, 1994: 125-132.
[31] Shellhammer S. J., Goren D. P., Pavlidis T.. Selective sampling and edge enhancement in bar code laser scanning. SPIE Document Recognition, v 2660, 1996:354-366
[32] Shellhammer S. J., Goren David P. and Pavlidis, T.. Novel signal-processing techniques in barcode scanning. IEEE Robotics and Automation Magazine, 1999, 6(1):57-65
[33] Liao Hong Yuan, Liu Shu-Jen, Chen Liang-Hua and Tyan Hsiao-Rong. Bar-code recognitionsystem using backpropagation neural networks. Engineering Applications of Artificial Intelligence, 1995,8(1):81-90.
[34] Okol'nishnikova L. V.. Polynomial algorithm for recognition of bar codes. Pattern recognition and image analysis, 2001, 11(2):361-364.
[35] Turin W. and Boie R. A.. Bar code recovery via the EM algorithm. IEEE Trans. on Signal Processing, 1998, 46(2): 354-363.
[36] Turin W. and Boie R. A.. Minimum discrimination information bar code decoding. Proceedings of the 1996 19th Convention of Electrical and Electronics Engineers in Israel, 1996:255-258.
[37] Boie, R.A., Turin W.. Noise-limited reading of bar codes. IEEE Trans. on Industrial Electronics, 1997,44(6):816-824.
[38] Hee Il Hahn,Joung Koo Joung. Implementation of algorithm to decode two-dimensional barcode PDF-417. 6th International Conference on Signal Processing, 2002
[39] Hee Il Hahn,Jung Goo Jung. Improving performance of the decoder for two-dimensional barcode symbology PDF417. Informatics in Control,Automation and Robotics I,233-237,Springer,2006.3
[40] Ramtin Shams, Parastoo Sadeghi. Bar Code Recognition In Highly Distorted And Low Resolution Images. Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on.
[41]刘宁钟,杨静宇.基于傅立叶变换的二维条码识别.中国图像图形学报, 2003, 8(8):877-882.
[42]刘宁钟,杨静宇.基于波形分析的二维条码识别.计算机研究与发展, 2004, 41(3):463-469.
[43]刘宁钟,杨静宇.综合利用投影算法和相似距离算法的二维条码识别.模式识别与人工智能, 2003, 16(1):86-90.
[44]刘宁钟,杨静宇.基于中点检测的二维条码识别.小型微型计算机系统, 2004, 25(2):283-286.
[45] Sherin M. Youssef, Rana M. Salem.Automated barcode recognition for smart identification and inspection automation.Expert Systems with ApplicationsVolume 33, Issue 4, November 2007, Pages 968-977.
[46] AIM, 1994, Uniform Symbology Specification: PDF417.
[47]中华人民共和国国家标准GB/T17172—1997,中国标准出版社, 1998.8.
[48]章毓晋.图像处理和分析[M].清华大学出版社, 1999. 3.
[49] Milan Sonka, Vaclav Hlavac, Roger Boyle著.图像处理、分析与机器视觉(第二版)[M].艾海舟等译,人民邮电出版社,2003.9.
[50]沈庭芝,方子文.数字图像处理及模式识别.北京理工大学出版社, 1998.
[51] Kenneth. R. Castleman.数字图像处理.电子工业出版社, 1998.
[52] Rafael C. Gonzalez, Richard Eugene Woods. Digital Image Processing[M]. Prentice Hall,2007.
[53]郭德方.遥感图象的计算机处理和模式识别[M].北京:电子工业出版社, 1987.
[54]马振华等.现代应用数学手册,概率统计与随机过程卷.清华大学出版社,2000.440-457.
[55] Rabiner L R. A tutorial on hidden Markov Models and selected applications in speech recognition. In:Proceedings of the IEEE.1989,77(2):257-286.
[56] Sehuller,Gerhard Rigoll, Manfred Lang. Hidden Markov Based Speech Recognition. Proceedings of 2003 IEEE International Conference on Acoustics, Speech, &Speech Processing April 6-l0,2003.
[57] Yi-Lin Lin, Gang Wei. Speech Emotion Based on HMM and SVM. Proceedings of Fouah International Conference on Machine Learning and Cybernetics, Guangzhou, 18—21August 2005.
[58] Anigbogu, J.C., Belaid, A.. Performance evaluation of an HMM based OCR system.Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on 30 Aug.-3 Sept. 1992 Page(s):565– 568
[59]张震,任远,平西建等.基于图像质量评价量和隐马尔科夫模型的图像拼接检测.武汉大学学报, 2008.10
[60] AJ Elms and J Illingworth. Combination of HMMs for the representation of printed characters in noisy document images. Image and Vision Computing, 1995.6, 5(13):385-392
[61]李杰.隐马尔科夫模型的研究及其在图像识别中的应用.清华大学博士学位论文, 2004.6.
[62] Li J,Wang J X,Zhao Y N,et al. Self-adaptive design of hidden Markov models. Pattern Recognition Letters,2004,25(2):197-210
[63]赵炯. Linux内核完全剖析.机械工业出版社, 2007.4
[64] Daniel P. Bovet, Marco Cesati. Understanding the Linux Kernel. O'Reilly Media, Inc. 2005.11
[65]陈莉君等. Linux操作系统原理与应用.清华大学出版社, 2008.9
[66] William von Hagen. The Definitive Guide to GCC,Second Edition. Apress, 2006.8
[67] Arthur Griffith. GCC:The Complete Reference. McGraw-Hill, 2002.9
[68]董永清. Linux C编程实战.人民邮电出版社, 2008.1