基于图像处理技术的面粉麸星检测技术研究与实现
|
摘要
面粉中麸星含量的多少是评价面粉等级的一个重要指标,它不仅能够反映小麦品种的优劣,而且能够体现出面粉生产工艺的水平。目前国内绝大多数与面粉制品有关的科研院所、生产厂家等检测机构还是采用操作人员在放大镜的帮助下肉眼识别的方式来完成检测工作,这种传统的人工检测方式往往达不到精度要求而且费时费力,因此检测结果很难令人信服。
针对目前存在的这些问题,本文提出设计一个智能的面粉麸星检测系统,该系统可以自动完成面粉装载、运输、拍照等一系列工作,同时该系统的上位机软件可以实时的完成对面粉图像的处理和麸星的快速检测,从而有效避免了传统人工检测方式中存在的诸多不足。
在麸星检测系统的硬件设计中,将光照度检测及控制技术添加到检测仪器中,从而避免了其它仪器在检测时缺少对于检测环境实时监控的不足。在此基础上,为了满足光照度准确检测的设计要求,研究运用改进的BP神经网络来实现A/D采样数据与标准光照度值之间的数据拟合。仿真实验表明：这种改进的BP算法可以有效的避免局部极小化问题,提高了网络的收敛速度。
本文还对图像灰度化、二值化、平滑滤波、纹理分析、边缘检测等多种数字图像处理技术进行了综合的比较研究,并参考模式识别的相关理论,提出了一种新的麸星快速识别和归一化的算法。然后,根据这些图像处理算法的基本原理设计编写了一款软件,该软件可以完成麸星个数、面积、面积百分比等参数的快速有效检测。最后,本文指出了该系统目前存在的一些不足,有待于日后改进和完善。
The number of bran specks contained in the flour is an import indicator to evaluate the rank of flour, which not only reflects the pros and cons of wheat varieties, but also reflects the level of the flour production process. Currently, operators in most of the scientific research institutes, manufacturers and other testing organizations related with flour products, still use the way of visually identified with the help of a magnifying glass to complete the inspection work, which was the traditional manual testing method often do not meet accuracy requirement and time-consuming effort, so the test results is hardly convincing.
In response to these problems, this paper presents to design and develop an intelligent measure system of bran specks in flour. This system can automatically complete flour loading, transportation, photograph and other works, while the Host Computer Software can complete real-time image processing and fast detection of bran, effectively overcomes the shortcomings in traditional manual testing method.
In the hardware design of bran specks measure system, the technology of illuminance detect and control is added to the instrument, and thus avoiding the deficiency of lack of real-time monitoring for testing environment in other instruments. On this basis, in order to satisfy the design requirements of accuration for illuminace detection, research to apply improved BP neural network to achieve data fitting between A/D sampling data and the standard values of illuminace. The simulation result shows that the improved BP algorithm can effectively avoid the local minimization problem, and improve the network convergence speed.
This paper also implements a comprehensive comparative study with a variety of digital image processing technology, such as, the image gray-based, binarization, smoothing filtering, texture analysis, edge detection and so on. After the reference to the relevant pattern recognition theory, a new bran specks rapid identification and normalization algorithm is presented. Then, designs an intelligent software based on these basic principles of image processing algorithms. This software can quickly detect number, area, area percentage and other parameters of bran specks. Finally, the paper also proposed some shortcomings in the system which to be improved and perfected in the future.
针对目前存在的这些问题,本文提出设计一个智能的面粉麸星检测系统,该系统可以自动完成面粉装载、运输、拍照等一系列工作,同时该系统的上位机软件可以实时的完成对面粉图像的处理和麸星的快速检测,从而有效避免了传统人工检测方式中存在的诸多不足。
在麸星检测系统的硬件设计中,将光照度检测及控制技术添加到检测仪器中,从而避免了其它仪器在检测时缺少对于检测环境实时监控的不足。在此基础上,为了满足光照度准确检测的设计要求,研究运用改进的BP神经网络来实现A/D采样数据与标准光照度值之间的数据拟合。仿真实验表明：这种改进的BP算法可以有效的避免局部极小化问题,提高了网络的收敛速度。
本文还对图像灰度化、二值化、平滑滤波、纹理分析、边缘检测等多种数字图像处理技术进行了综合的比较研究,并参考模式识别的相关理论,提出了一种新的麸星快速识别和归一化的算法。然后,根据这些图像处理算法的基本原理设计编写了一款软件,该软件可以完成麸星个数、面积、面积百分比等参数的快速有效检测。最后,本文指出了该系统目前存在的一些不足,有待于日后改进和完善。
The number of bran specks contained in the flour is an import indicator to evaluate the rank of flour, which not only reflects the pros and cons of wheat varieties, but also reflects the level of the flour production process. Currently, operators in most of the scientific research institutes, manufacturers and other testing organizations related with flour products, still use the way of visually identified with the help of a magnifying glass to complete the inspection work, which was the traditional manual testing method often do not meet accuracy requirement and time-consuming effort, so the test results is hardly convincing.
In response to these problems, this paper presents to design and develop an intelligent measure system of bran specks in flour. This system can automatically complete flour loading, transportation, photograph and other works, while the Host Computer Software can complete real-time image processing and fast detection of bran, effectively overcomes the shortcomings in traditional manual testing method.
In the hardware design of bran specks measure system, the technology of illuminance detect and control is added to the instrument, and thus avoiding the deficiency of lack of real-time monitoring for testing environment in other instruments. On this basis, in order to satisfy the design requirements of accuration for illuminace detection, research to apply improved BP neural network to achieve data fitting between A/D sampling data and the standard values of illuminace. The simulation result shows that the improved BP algorithm can effectively avoid the local minimization problem, and improve the network convergence speed.
This paper also implements a comprehensive comparative study with a variety of digital image processing technology, such as, the image gray-based, binarization, smoothing filtering, texture analysis, edge detection and so on. After the reference to the relevant pattern recognition theory, a new bran specks rapid identification and normalization algorithm is presented. Then, designs an intelligent software based on these basic principles of image processing algorithms. This software can quickly detect number, area, area percentage and other parameters of bran specks. Finally, the paper also proposed some shortcomings in the system which to be improved and perfected in the future.
引文
[1]田建珍,李利民,孙卫政等.小麦粉麸星的量化检测与分析[J].粮食与饲料工业,2007，11(10)：10-12.
[2]王震.浅谈影响面粉加工精度的因素[J].粮食加工,2007，32(1)：25-27.
[3]纪建海,王彦霞,闵卫红.关于减少面粉中含砂量和麸星的探讨[J].粮油加工,2005,6(12)：30-32.
[4]李同强.面粉麸星的计算机检测[J].中国粮油学报,2005，4(2)：71-74.
[5]刘兴信.关于我国小麦粉质量标准问题的探讨[J].中国粮油学报,2002，5(1)：1-6.
[6]殷晓慧.面粉麸星白度检测计算机系统[J].粮食与饲料工业,2007，8(3)：14-16.
[7]李林轩.小麦粉粉色麸星的测定方法[J].粮食与食品工业,2009,16(1)：51-52.
[8]张有兵.面粉麸星的识别与测量[D].[硕士论文].浙江工商大学,2009.
[9]陆勤丰,曾益昆.小麦加工工艺对面粉色泽的影响[J].粮油食品科技,2008,16(3)：2-5.
[10]陈筠,施正墩.小麦粉检测情况市场调查报告[J].面粉通讯,2007,7(1)：24-26.
[11]康志钰,王建军.面粉色泽与小麦理化特性的关系[J].农业科技通讯,2009,6(1)：27-30.
[12]霍权恭,杨红卫,周展明等.小麦粉粉色与麸星检测方法研究[J].中国粮油学报,21(3)：21-37.
[13]GB1355-1986,小麦粉国家标准[S].
[14]李树高.面粉灰分含量对面制品的影响[J].粮食与食品工业,2008，15(5)：11-18.
[15]刘丹.光照度计全自动检定系统的误差分析研究[D].[硕士论文].合肥工业大学,2007.
[16]白泽生,白宗文.一种简易光照度检测电路的设计[J].现代电子技术,2006，
11(26)：91-92.
[17]何松林,蒋要卫,王政等.外施C02时光照度对大花蕙兰试管苗生长和叶片气孔特征的影响[J].河南农业大学学报,2009,43(6)：625-629.
[18]纪鹏,王毅,陈宗瑜等.UV-B滤减处理下烟草光合作用参数对光照度的响应[J].生态学杂志,2009,28(7)：1218-1223.
[19]王士峰,赵馨,崔宇.国产ZCR型光电池工作特性及应用[J].长春理工大学学报,2006,26(2)：14-17.
[20]杜梅芳,姜志进.光电池非线性区PN结光生伏特效应的研究[J].上海理工大学学报,2002,24(1)：65-67.
[21]Firtat B, Nedeleu O, Moldovan, et al.Design and Manufaeturing of A Pressure Sensor with Capacitive Read out[J].CMOS Compatible, CAS 2001 International Conferenee, Sinaia Proeeedings,2001:553-556.
[22]侯文辉.高精度照度计的设计[D].[硕士论文].大连理工大学,2007.
[23]霍戌文,李伟,李进等.光电探测微信号放大器设计[J].浙江理工大学学报,2005,22(3)：259-262.
[24]刘正岐,付文羽.影响光电检测电路信噪比的因素[J].延安大学学报,2003,22(4)：41-43.
[25]刘彬,张秋掸.光电检测前置放大电路的设计[J].燕山大学学报,2003，27(3)：193-196.
[26]鲁慧.基于ATmegal28单片机的运动控制系统的设计与实现[D].[硕士论文].华中科技大学,2007.
[27]李立.双处理器控制数字化焊接电源单片机系统的研究[D].[硕士论文].天津大学,2007.
[28]徐金增.单片机编程仿真实验系统的设计与实现[D].[硕士论文].山东师范大学,2009.
[29]李蒙.基于STC89单片机的实验教学系统[D].[硕士论文].天津大学,2008.
[30]曾酷昭.神经网络优化方法及其在信息处理中的应用研究[D].[博士论文].湖
南大学,2008.
[31]He Y, Wu M, She J H. Delay-Dependent Stability Criteria for Linear Systems with Multiple Time Delays[J]. IEEE Proceedings-Control Theory and Applications,2006, 153:447-452.
[32]Syed Ali M, Balasubramaniam P. Exponential Stability of Uncertain Stochastic Fuzzy BAM Neural Networks with Time-Varying Delays[J]. Neurocomputing, 2009,72:1347-1354.
[33]高明.时滞神经网络的稳定性与同步研究[D].[博士论文].江南大学,2009.
[34]Zhang H G, Wang Z S. Stability Analysis of BAM Neural Networks with Time-Varying Delays[J].Progress in Natural Science,2007,17:206-211.
[35]Rubanov N.S. The Layer Wise Method and the Back Propagation Hybrid Approach to Learning a Feed Forward Neural Network[J]. IEEE Trans. Neural Networks, 2000,11(2):295-305.
[36]Leung Yee, Chen Kaizhou, Jiao Yongchang, Gao Xingbao, et al. A New Gradient-Based Neural Network for Solving Linear and Quadratic Programming Problems[J]. IEEE Trans Neural Networks,2001,12(5):580-594.
[37]Huang G, Cao J D. Multistability in Bidirectional Associative Memory Neural Networks[J]. Physics Letters A,2008,372:2842-2854.
[38]黄丽.BP神经网络算法改进及应用研究[D].[硕士论文].重庆师范大学,2008.
[39]夏玫.BP神经网络泛化能力研究[D].[硕士论文].太原科技大学,2009.
[40]舒红平,蒋建民.基于灰度最优阈值的图像分割方法及应用[J].重庆工商大学学报(自然科学版),2003,8(12)：51-53.
[41]李君.基于web的分布式图像处理技术研究与系统实现[D].[硕士论文].浙江工业大学,2009.
[42]熊艳.面向嵌入式图像处理系统的中间件研究[D].[硕士论文].华东交通大学,2008.
[43]黄春艳,杨国胜,侯艳丽.基于熵的图像二值化方法比较研究[J].河南大学学 报,2005,6(2)：76-78.
[44]杜晓晨,刘建平.改进的模糊阈值图像分割方法[J].光电工程,2005，3(10)：51-53.
[45]Carlos O'Ryan, Douglas C. Schmidt, Fred Kuhns et al. The Design and Performance of a Real-time CORBA ORB Endsystem[J]. The Journal of Concurrency:Practice and Experience, Wiley and Sons,2006.
[46]John A. Stankovic. Misconceptions about Real-Time Computing:A Serious Problem for Next-Generation Systems[J]. Computer, October 2005,Vol.21(10): 1019.
[47]Nagao. Takashi M atsuyama. Edge Preserving Smoothing[J]. Computer Graphics and Image Processing,1979,9:394-407.
[48]Ichiro Mizunuma, Chia Shen, and Morikazu Takegaki. Middleware for Distributed Industrial Real-Time Systems on ATM Networks[C]. Proceeding of the 17th IEEE Real-Time Systems Symposium, Washington,DC,USA. December 2006:3238.
[49]朱菊华,杨新,李俊,施鹏飞.基于纹理分析的保细节平滑滤波器[J].中国图像图形学报,2001,6(11)：1058-1064.
[50]许存禄.图像纹理分析的新方法及其应用[D].[博士论文].复旦大学,2005.
[51]程光权,成礼智.基于小波的方向自适应图像插值[J].电子与信息学报,2009,31(2)：265-269.
[52]谭林秋.基于VC++的数字图像处理系统的开发及算法研究[D].[硕士论文].西安理工大学,2008.
[53]求是科技.C++数字图像处理典型算法与实现[M].北京：人民邮电出版社,2006.
[54]于连杰,纪玉波.基于CAGH检测和投影法的车牌定位算法[J].科学技术与工程,2008,8(7)：3990-3992.
[55]周彩霞,匡纲要等.基于差影法粗分割与多模板匹配的人脸检测[J].计算机工程与设计,2004，25(10)：1645-1650.
[56]田娟,郑郁正.模板匹配技术在图像识别中的应用[J].传感器与微系统,2008,27(1)：112-114.
[57]刘佳,肖晓明,彭骏驰.基于改进的Laplacian算子的图像边缘检测[J].电子技术应用,2006，11：31-32.
[58]Pellegrino F A, Vanzella W. Edge Detection Revisited[J]. IEEE Trans on Systems, Man and Cybernetics,2004,34(3):1500-1518.
[59]曹菲,杨小冈.一种通用的边缘检测方法及其实现[J].计算机工程,2005,31(11)：30-31.
[60]李弼程,邵美珍,黄浩.模式识别原理与应用[M].西安：西安电子科技大学出版社,2008.
[61]Douglas C. Schmidt. Middleware Techniques and Optimizations for Real-time Embedded Systems[C]. In the Proceedings of the 12th International Symposium On System Synthesis, IEEE, San Jose,CA,USA. Nov 2005.
[62]Richard Williams. Increase Image Processing System Performance with FPGAs[J]. XcellJomal,2004,16(2):10-11.
[63]Moncreff M, Cotton S, Claridge E, Hall P. Spectrophoto metric intracutaneous analysis:a new technique for imaging pigmented skin lesions[J]. Br J Dermat, 2002,146:448-457.
[64]杨晓胜.基于模式识别的鞋底花纹自动识别与分类[D].[硕士论文].大连海事大学,2005.
[65]罗斌.C++Builder精彩编程实例集锦[M].北京：中国水利水电出版社,2005.
[66]Henri Maitre.现代数字图像处理[M].北京：电子工业出版社,2006.
[67]张弘.数字图像处理与分析[M].北京：机械工业出版社,2007.
[68]陆宗骐.C/C++图像处理编程[M].北京：清华大学出版社,2005.
[69]蒙祖强,龚涛.C++Builder程序员成长攻略[M].北京：中国水利水电出版社,2007.
[2]王震.浅谈影响面粉加工精度的因素[J].粮食加工,2007，32(1)：25-27.
[3]纪建海,王彦霞,闵卫红.关于减少面粉中含砂量和麸星的探讨[J].粮油加工,2005,6(12)：30-32.
[4]李同强.面粉麸星的计算机检测[J].中国粮油学报,2005，4(2)：71-74.
[5]刘兴信.关于我国小麦粉质量标准问题的探讨[J].中国粮油学报,2002，5(1)：1-6.
[6]殷晓慧.面粉麸星白度检测计算机系统[J].粮食与饲料工业,2007，8(3)：14-16.
[7]李林轩.小麦粉粉色麸星的测定方法[J].粮食与食品工业,2009,16(1)：51-52.
[8]张有兵.面粉麸星的识别与测量[D].[硕士论文].浙江工商大学,2009.
[9]陆勤丰,曾益昆.小麦加工工艺对面粉色泽的影响[J].粮油食品科技,2008,16(3)：2-5.
[10]陈筠,施正墩.小麦粉检测情况市场调查报告[J].面粉通讯,2007,7(1)：24-26.
[11]康志钰,王建军.面粉色泽与小麦理化特性的关系[J].农业科技通讯,2009,6(1)：27-30.
[12]霍权恭,杨红卫,周展明等.小麦粉粉色与麸星检测方法研究[J].中国粮油学报,21(3)：21-37.
[13]GB1355-1986,小麦粉国家标准[S].
[14]李树高.面粉灰分含量对面制品的影响[J].粮食与食品工业,2008，15(5)：11-18.
[15]刘丹.光照度计全自动检定系统的误差分析研究[D].[硕士论文].合肥工业大学,2007.
[16]白泽生,白宗文.一种简易光照度检测电路的设计[J].现代电子技术,2006，
11(26)：91-92.
[17]何松林,蒋要卫,王政等.外施C02时光照度对大花蕙兰试管苗生长和叶片气孔特征的影响[J].河南农业大学学报,2009,43(6)：625-629.
[18]纪鹏,王毅,陈宗瑜等.UV-B滤减处理下烟草光合作用参数对光照度的响应[J].生态学杂志,2009,28(7)：1218-1223.
[19]王士峰,赵馨,崔宇.国产ZCR型光电池工作特性及应用[J].长春理工大学学报,2006,26(2)：14-17.
[20]杜梅芳,姜志进.光电池非线性区PN结光生伏特效应的研究[J].上海理工大学学报,2002,24(1)：65-67.
[21]Firtat B, Nedeleu O, Moldovan, et al.Design and Manufaeturing of A Pressure Sensor with Capacitive Read out[J].CMOS Compatible, CAS 2001 International Conferenee, Sinaia Proeeedings,2001:553-556.
[22]侯文辉.高精度照度计的设计[D].[硕士论文].大连理工大学,2007.
[23]霍戌文,李伟,李进等.光电探测微信号放大器设计[J].浙江理工大学学报,2005,22(3)：259-262.
[24]刘正岐,付文羽.影响光电检测电路信噪比的因素[J].延安大学学报,2003,22(4)：41-43.
[25]刘彬,张秋掸.光电检测前置放大电路的设计[J].燕山大学学报,2003，27(3)：193-196.
[26]鲁慧.基于ATmegal28单片机的运动控制系统的设计与实现[D].[硕士论文].华中科技大学,2007.
[27]李立.双处理器控制数字化焊接电源单片机系统的研究[D].[硕士论文].天津大学,2007.
[28]徐金增.单片机编程仿真实验系统的设计与实现[D].[硕士论文].山东师范大学,2009.
[29]李蒙.基于STC89单片机的实验教学系统[D].[硕士论文].天津大学,2008.
[30]曾酷昭.神经网络优化方法及其在信息处理中的应用研究[D].[博士论文].湖
南大学,2008.
[31]He Y, Wu M, She J H. Delay-Dependent Stability Criteria for Linear Systems with Multiple Time Delays[J]. IEEE Proceedings-Control Theory and Applications,2006, 153:447-452.
[32]Syed Ali M, Balasubramaniam P. Exponential Stability of Uncertain Stochastic Fuzzy BAM Neural Networks with Time-Varying Delays[J]. Neurocomputing, 2009,72:1347-1354.
[33]高明.时滞神经网络的稳定性与同步研究[D].[博士论文].江南大学,2009.
[34]Zhang H G, Wang Z S. Stability Analysis of BAM Neural Networks with Time-Varying Delays[J].Progress in Natural Science,2007,17:206-211.
[35]Rubanov N.S. The Layer Wise Method and the Back Propagation Hybrid Approach to Learning a Feed Forward Neural Network[J]. IEEE Trans. Neural Networks, 2000,11(2):295-305.
[36]Leung Yee, Chen Kaizhou, Jiao Yongchang, Gao Xingbao, et al. A New Gradient-Based Neural Network for Solving Linear and Quadratic Programming Problems[J]. IEEE Trans Neural Networks,2001,12(5):580-594.
[37]Huang G, Cao J D. Multistability in Bidirectional Associative Memory Neural Networks[J]. Physics Letters A,2008,372:2842-2854.
[38]黄丽.BP神经网络算法改进及应用研究[D].[硕士论文].重庆师范大学,2008.
[39]夏玫.BP神经网络泛化能力研究[D].[硕士论文].太原科技大学,2009.
[40]舒红平,蒋建民.基于灰度最优阈值的图像分割方法及应用[J].重庆工商大学学报(自然科学版),2003,8(12)：51-53.
[41]李君.基于web的分布式图像处理技术研究与系统实现[D].[硕士论文].浙江工业大学,2009.
[42]熊艳.面向嵌入式图像处理系统的中间件研究[D].[硕士论文].华东交通大学,2008.
[43]黄春艳,杨国胜,侯艳丽.基于熵的图像二值化方法比较研究[J].河南大学学 报,2005,6(2)：76-78.
[44]杜晓晨,刘建平.改进的模糊阈值图像分割方法[J].光电工程,2005，3(10)：51-53.
[45]Carlos O'Ryan, Douglas C. Schmidt, Fred Kuhns et al. The Design and Performance of a Real-time CORBA ORB Endsystem[J]. The Journal of Concurrency:Practice and Experience, Wiley and Sons,2006.
[46]John A. Stankovic. Misconceptions about Real-Time Computing:A Serious Problem for Next-Generation Systems[J]. Computer, October 2005,Vol.21(10): 1019.
[47]Nagao. Takashi M atsuyama. Edge Preserving Smoothing[J]. Computer Graphics and Image Processing,1979,9:394-407.
[48]Ichiro Mizunuma, Chia Shen, and Morikazu Takegaki. Middleware for Distributed Industrial Real-Time Systems on ATM Networks[C]. Proceeding of the 17th IEEE Real-Time Systems Symposium, Washington,DC,USA. December 2006:3238.
[49]朱菊华,杨新,李俊,施鹏飞.基于纹理分析的保细节平滑滤波器[J].中国图像图形学报,2001,6(11)：1058-1064.
[50]许存禄.图像纹理分析的新方法及其应用[D].[博士论文].复旦大学,2005.
[51]程光权,成礼智.基于小波的方向自适应图像插值[J].电子与信息学报,2009,31(2)：265-269.
[52]谭林秋.基于VC++的数字图像处理系统的开发及算法研究[D].[硕士论文].西安理工大学,2008.
[53]求是科技.C++数字图像处理典型算法与实现[M].北京：人民邮电出版社,2006.
[54]于连杰,纪玉波.基于CAGH检测和投影法的车牌定位算法[J].科学技术与工程,2008,8(7)：3990-3992.
[55]周彩霞,匡纲要等.基于差影法粗分割与多模板匹配的人脸检测[J].计算机工程与设计,2004，25(10)：1645-1650.
[56]田娟,郑郁正.模板匹配技术在图像识别中的应用[J].传感器与微系统,2008,27(1)：112-114.
[57]刘佳,肖晓明,彭骏驰.基于改进的Laplacian算子的图像边缘检测[J].电子技术应用,2006，11：31-32.
[58]Pellegrino F A, Vanzella W. Edge Detection Revisited[J]. IEEE Trans on Systems, Man and Cybernetics,2004,34(3):1500-1518.
[59]曹菲,杨小冈.一种通用的边缘检测方法及其实现[J].计算机工程,2005,31(11)：30-31.
[60]李弼程,邵美珍,黄浩.模式识别原理与应用[M].西安：西安电子科技大学出版社,2008.
[61]Douglas C. Schmidt. Middleware Techniques and Optimizations for Real-time Embedded Systems[C]. In the Proceedings of the 12th International Symposium On System Synthesis, IEEE, San Jose,CA,USA. Nov 2005.
[62]Richard Williams. Increase Image Processing System Performance with FPGAs[J]. XcellJomal,2004,16(2):10-11.
[63]Moncreff M, Cotton S, Claridge E, Hall P. Spectrophoto metric intracutaneous analysis:a new technique for imaging pigmented skin lesions[J]. Br J Dermat, 2002,146:448-457.
[64]杨晓胜.基于模式识别的鞋底花纹自动识别与分类[D].[硕士论文].大连海事大学,2005.
[65]罗斌.C++Builder精彩编程实例集锦[M].北京：中国水利水电出版社,2005.
[66]Henri Maitre.现代数字图像处理[M].北京：电子工业出版社,2006.
[67]张弘.数字图像处理与分析[M].北京：机械工业出版社,2007.
[68]陆宗骐.C/C++图像处理编程[M].北京：清华大学出版社,2005.
[69]蒙祖强,龚涛.C++Builder程序员成长攻略[M].北京：中国水利水电出版社,2007.