光学显微镜图像处理技术及应用研究
|
摘要
随着光学显微镜和计算机技术的结合,光学显微镜正在向自动化和智能化方向发展。显微目标图像处理技术能极大地提高光学显微镜的性能和效用,对于光学显微镜的发展和应用有重要意义。
本文根据光学显微镜的发展趋势和光学显微镜观测目标的特点,把观测目标分为固定形态目标和非固定形态目标两类,研究了与之相关的目标识别关键技术,这些技术包括:用于扩展显微镜高倍视场下景深的多聚焦图像融合算法,单像素封闭边缘提取算法,基于SVM的固定形态目标自动识别与测量系统,基于实时学习模式的非固定形态目标分类识别系统。并通过对比实验和性能实验检验了这些算法和系统的有效性和适用性。
本文创新性工作概括如下:
1、提出了基于自适应滤波器清晰度评估函数和根据最近邻权值判断融合条件的多聚焦图像融合算法。该算法可以有效地减轻噪声影响和增加显微镜景深,在多种倍率物镜下获得很好的融合效果,有利于后继图像处理。
2、提出了单像素封闭边缘提取算法。该算法采用Canny算法获取的基础边缘与基础边缘端点灰度等高线相融合的方式产生具有单像素特征的连续封闭边缘,实验结果表明,该算法可有效地实现对灰度变化复杂图像进行封闭边缘提取,可应用于获取灰度类似的封闭区域、边缘测量等方面。
3、研究了基于SVM固定形态目标识别技术。该技术通过对固定形态目标采用支持向量机(SVM)对其多项图像特征进行训练,获取差异性特征子集及其特征参数形成匹配模板,并将此模板用于识别算法中。该技术应用在集成电路引脚平整度自动测量系统中,使得该系统的测量准确率达到93%以上,错误接受率为0。
4、研究了基于实时学习模式的非固定形态目标识别技术。该技术采用封闭边缘算法获取局部封闭区域并提取这些区域的特征,然后通过系统与用户的交互实现实时学习过程,根据用户的选择形成分类法则。该技术可用在金相组织含量分析系统中,实验表明,该系统定量分析误差仅为±1%,且适用范围更广。
With the combination of optical microscope and computer technology, the development trend of optical microscope is automation and intelligentizing which greatly enhance its performance and effectiveness and has an important significance to optical microscope’s development and application.
According to the future development tendency of optical microscope and the characteristics of microscope’s observation,the observed object can be divided into two categories: fixed shape object and non-fixed shape object. The key technologies of image recognition about two categories object are studied in this dissertation. The main contents of this dissertation includes: a multi-focus image fusion algorithm which can extend the high power microscope’s depth of field, an single pixel wide enclosing image edge extraction algorithm, an automatic identification and measurement algorithm for fixed shape microscopic image objective and a classification algorithm base on real-time learning pattern which can be applied to identify non-fixed shape microscopic image objective. The effectiveness and applicability of these algorithms was validated through the contrast and performance experiments.
The major innovations of the dissertation are summarized as follows:
1. A multi-focus image fusion algorithm based on noise adaptive filter and the nearest neighbor’s weight is developed to extend the high power microscope’s depth of field. This algorithm can effectively reduce the influence of the noise, and has very good performance in different magnifying power objective lens.
2. An algorithm based on Canny and grayscale contour line to extract single pixel wide enclosing image edge is proposed. Acquiring the initial edge which have single edge effect by using Canny algorithm. The initial edge’s threshold was automatically calculated to reduce false edge and obtain the basic edge for next steps. According to the grayscale neighborhood of the basic edge’s end points, the gray value of grayscale contour line was calculated. On the fusion condition of basic edge and grayscale contour line, the closing edge can be create from the endpoints of basic edge. Experimental results indicate that this algorithm can generate enclosing edge efficaciously which can be used to obtain enclosing region and edge measurement.
3. Technology of fixed shape object recognition base on SVM-based is studied and realized. According to the fixed shape of objects, using the SVM to training the variety of features to obtain key feature subset and feature parameters for automatic detection’s matching template. With the application of matching template to the flatness automatic detection system for Integrated Circuit pins, the accuracy is over 93% and false-acceptance error rate is 0.
4. Technology of non-fixed shape object recognition base on real-time learning pattern is studied and realized. The analysis system extracted the features of region which surrounded by enclosing edge. Through the human-computer interaction, it learned the definition of specific enclosing region selected by the user to form classification rule about features and according to these rules to classify the other region. With the application of the metallographic structure contents qualitative analysis system, experimental results indicate that the measurement error of the polyphase structure’s contents about metallographic is less than 1% and suitable for different shape metallographic structure.
本文根据光学显微镜的发展趋势和光学显微镜观测目标的特点,把观测目标分为固定形态目标和非固定形态目标两类,研究了与之相关的目标识别关键技术,这些技术包括:用于扩展显微镜高倍视场下景深的多聚焦图像融合算法,单像素封闭边缘提取算法,基于SVM的固定形态目标自动识别与测量系统,基于实时学习模式的非固定形态目标分类识别系统。并通过对比实验和性能实验检验了这些算法和系统的有效性和适用性。
本文创新性工作概括如下:
1、提出了基于自适应滤波器清晰度评估函数和根据最近邻权值判断融合条件的多聚焦图像融合算法。该算法可以有效地减轻噪声影响和增加显微镜景深,在多种倍率物镜下获得很好的融合效果,有利于后继图像处理。
2、提出了单像素封闭边缘提取算法。该算法采用Canny算法获取的基础边缘与基础边缘端点灰度等高线相融合的方式产生具有单像素特征的连续封闭边缘,实验结果表明,该算法可有效地实现对灰度变化复杂图像进行封闭边缘提取,可应用于获取灰度类似的封闭区域、边缘测量等方面。
3、研究了基于SVM固定形态目标识别技术。该技术通过对固定形态目标采用支持向量机(SVM)对其多项图像特征进行训练,获取差异性特征子集及其特征参数形成匹配模板,并将此模板用于识别算法中。该技术应用在集成电路引脚平整度自动测量系统中,使得该系统的测量准确率达到93%以上,错误接受率为0。
4、研究了基于实时学习模式的非固定形态目标识别技术。该技术采用封闭边缘算法获取局部封闭区域并提取这些区域的特征,然后通过系统与用户的交互实现实时学习过程,根据用户的选择形成分类法则。该技术可用在金相组织含量分析系统中,实验表明,该系统定量分析误差仅为±1%,且适用范围更广。
With the combination of optical microscope and computer technology, the development trend of optical microscope is automation and intelligentizing which greatly enhance its performance and effectiveness and has an important significance to optical microscope’s development and application.
According to the future development tendency of optical microscope and the characteristics of microscope’s observation,the observed object can be divided into two categories: fixed shape object and non-fixed shape object. The key technologies of image recognition about two categories object are studied in this dissertation. The main contents of this dissertation includes: a multi-focus image fusion algorithm which can extend the high power microscope’s depth of field, an single pixel wide enclosing image edge extraction algorithm, an automatic identification and measurement algorithm for fixed shape microscopic image objective and a classification algorithm base on real-time learning pattern which can be applied to identify non-fixed shape microscopic image objective. The effectiveness and applicability of these algorithms was validated through the contrast and performance experiments.
The major innovations of the dissertation are summarized as follows:
1. A multi-focus image fusion algorithm based on noise adaptive filter and the nearest neighbor’s weight is developed to extend the high power microscope’s depth of field. This algorithm can effectively reduce the influence of the noise, and has very good performance in different magnifying power objective lens.
2. An algorithm based on Canny and grayscale contour line to extract single pixel wide enclosing image edge is proposed. Acquiring the initial edge which have single edge effect by using Canny algorithm. The initial edge’s threshold was automatically calculated to reduce false edge and obtain the basic edge for next steps. According to the grayscale neighborhood of the basic edge’s end points, the gray value of grayscale contour line was calculated. On the fusion condition of basic edge and grayscale contour line, the closing edge can be create from the endpoints of basic edge. Experimental results indicate that this algorithm can generate enclosing edge efficaciously which can be used to obtain enclosing region and edge measurement.
3. Technology of fixed shape object recognition base on SVM-based is studied and realized. According to the fixed shape of objects, using the SVM to training the variety of features to obtain key feature subset and feature parameters for automatic detection’s matching template. With the application of matching template to the flatness automatic detection system for Integrated Circuit pins, the accuracy is over 93% and false-acceptance error rate is 0.
4. Technology of non-fixed shape object recognition base on real-time learning pattern is studied and realized. The analysis system extracted the features of region which surrounded by enclosing edge. Through the human-computer interaction, it learned the definition of specific enclosing region selected by the user to form classification rule about features and according to these rules to classify the other region. With the application of the metallographic structure contents qualitative analysis system, experimental results indicate that the measurement error of the polyphase structure’s contents about metallographic is less than 1% and suitable for different shape metallographic structure.
引文
[1]陈琳.显微镜的历史[J].教学仪器与实验.2007, 16(7):36
[2]章效锋.清晰的纳米世界显微镜终极目标的千年追求[M].北京:清华大学出版社,2005.
[3]陈惠民,张延武.医用光学显微镜的分类介绍[J].医疗卫生装备. 2004,(10): 39- 41
[4]何伟业,蓝红云,唐琼华.尿液中红细胞、白细胞的UF-100尿沉渣分析仪和显微镜检测结果比较[J].现代中西医结合杂志.2009,18(1):73-74.
[5]吴敏瑾,高相理,金胜航,曹寒沁,徐卫益.尿液干化学分析仪、沉渣仪与显微镜联合检测尿液有形成分的临床应用[J].浙江检验医学. 2008, 6(2): 32- 33.
[6] Ulf Rdler, Elias Horn.适用于光学显微镜的细胞培养芯片[J].生命科学仪器. 2007, 5(5): 42- 44
[7]侯晓萍.高连续变倍比体视显微镜[硕士论文].南京:南京理工大学,2007.
[8]庄琳.三维体视显微镜在文件检验中的应用[J].森林公安.2008,(02):28-29.
[9]柳雯,杨柳,许晓芳,李颂.数字化X线牙片和体视显微镜测量根管锥度的体外研究[J].牙体牙髓牙周病学杂志.2008,18(8):429-433
[10]陈宝泓. SMT线路板组装过程中的质量控制[J].电子工艺技术. 2000, 21(2): 60-63.
[11] Liguo Chen, Lingyu Ma, Lining Sun etc.. Zoom microscope based micro positioning for MEMS sensor packaging system[C]. IECON Proc., IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006, p 3863- 3867.
[12] Wang Li-Min, Li Qiu-Rong. Corrosion behavior of CuCr alloy coated with NaCl deposit [J]. Material science and technology. 2005, 13(2):196-199.
[13] http://www.leica-microsystems.com/
[14] http://cn.olympus.com/
[15] http://www.beionmed.com/chn/microxyz.asp
[16] http://www.motic.com.cn/Home.aspx?r=AP&lang=cn_s
[17] http://www.naturegene.cn/
[18] http://www.teradyne.com/china/index.htm
[19] http://vision.lusterinc.com/solution/display.aspx?ClassID=154
[20] http://www.xmfxgd.com.cn/
[21] http://www.c-ave.com/
[22]马立,荣伟彬,孙立宁,龚振邦.面向光学精密装配的微操作机器人[J].机械工程学报. 2009, 45(2): 280- 286.
[23] http://www.shchawer.com/company.htm
[24] http://bg.qincai.net/corp-255506.html
[25] http://www.szhipower.com/
[26] Rafael C.G, Richard E.W, Steven L.E. Digital image using MATLAB [M]. Beijing, China: Publishing Houses of Electronics Industry, 2006
[27] Jarvis R A. Focus optimization criteria for computer image processing [J]. Microscope. 1976, 24 (2): 163-180.
[28] Nayar S K, Nakagawa Y. Shape from focus system [J]. IEEE trans. pattern analysis and machine intelligence.1994, 16 (8) : 824～831.
[29] Je-Ho Lee, Kun-Sop Kim. Implementation of passive automatic focusing algorithm for digital still camera [ J ]. IEEE Transactions on consumer electronics. 1995, 41 (3): 449-453.
[30] Kang-Sun Choi, Sung-Jae Ko. New Auto focusing technique using the frequency selective weighted median filter for video cameras [J ]. IEEE Transactions on consumer electronics, 1999, 45(3): 820-826.
[31] TTE Yeo,S H Ong,Jayasooriah,R Sinniah. Auto focusing for Tissue Microscopes [J].Image and vision computing.1995, 11(1): 629-659.
[32]高赞,姜威,朱孔凤.基于最大梯度和阈值的自动聚焦算法[J].电子测量与仪器学报.2007,21(5): 49-53.
[33] Baina J, Dublet J. Automatic focus and iris control for video cameras [C]. Image processing and its applications fifth international conference, 1995: 232-235.
[34] Subbarao M,Choi T,Nikzad A.Focusing techniques[J]. J. Opt. Eng.1993,32(11):2824—2836
[35]菅维乐,姜威,周贤.一种基于小波变换的数字图像自动聚焦算法[J].山东大学学报(自然科学版). 2004, 34(6): 38-40.
[36]郭丙华,廖启亮,余志.基于小波变换的快速自动聚焦算法[J].中山大学学报(自然科学版). 2007, 46(2): 12- 15.
[37]王昕,刘畅.基于提升小波变换的图像清晰度评价算法[J].东北师大学报(自然科学版).2009, 41(4): 52-57.
[38]祝世平,房建成,周锐.一种新的能量谱-熵图像聚焦评价函数[J].北京航空航天大学学报. 1999, 25(6): 720-723.
[39] Li X, Liu G S, Ni J L. Autofocusing of ISAR imaging based on entropy minimization. IEEE Trans.on Aerospace and electronic system.1999, 35(4): 1240-1251.
[40]贾晓艳,萧泽新,邓仕超.基于聚焦评价函数的自动调焦方法的研究[J].光学技术.2007, 33(Z1):7-9.
[41] Jia Y.H., Fusion of Landsat TM and SAR images based on principal component analysis[J]. Remote Sensing Technology and Application.1998, 13 (1): 46-49.
[42] Burt P.J., Adelson E.H., The Laplacian pyramid as a compact image code, IEEE Trans. on Communications, 1983, 31(4): 532-540.
[43] Toet A.Image Fusion by a Ratio of Low-pass Pyramid[J].Pattern Recognition Letters,1989,9(4):255—261.
[44] Burr P J,Kolczynski R J. Enhanced image capture through fusion[C].Proc the 4th Iutl Conf on Computer Vision, Berlin, Germany, 1993:l73一l82.
[45] Ranchin T., Wald L., The wavelet transform for the analysis of remotely sensed images [J]. International Journal of Remote Sensing.1993, 14(3): 615-619.
[46] Unser M., Texture classification and segmentation using wavelet frames, IEEE Trans. On Image Processing, 1995, 11(4): 1549-1560.
[47]曾志峰,马华山.小波变换和清晰块搜索结合的图像融合算法[J].计算机工程与应用. 2008, 44(31): 199-201.
[48] Donoho D L,Duncan M R. Digital curvelet transform: Strategy, implementation and experiments [C]. Proc. of SPIE, the international society for optical engineering, Orlando, FL, USA. 2000,V4056: 12-30.
[49] DO M N, VETTERLI M. The Contourlet transform: an efficient directional mu1tiresolution image representation[J].IEEE Trans. Image Proc. 2005, 14(12): 2091—2106.
[50] LU Y,DO M N A new Contourlet transform withsharp frequency localization [c].Proc. of 2006 IEEE International Conference on Image Processing, Atlanta,USA. 2006, 1629-1632.
[51]屈小波,闫敬文,杨贵德.改进拉普拉斯能量和的尖锐频率局部化Contourlet域多聚焦图像融合方法[J].光学精密工程. 2009, 17(5):1204-1212.
[52] Tang J.S., A contrast based image fusion technique in the DCT domain [C]. Digital Signal Processing, 2004, 14(3): 218-226
[53]张建伟,张启衡.基于块遍历的直线边缘特征提取[J].光学精密工程. 2009,17(3): 662-668.
[54]陈平,潘晋孝,刘宾.CT图像边缘退化模型的建立及其在图像尺寸测量中的应用[J].光学精密工程,2009,17(9):2269-2275
[55] DENG S C, LIU T G, XIAO Z X et al.. An automatic detection system for flatness of integrated circuit pins[C]. Proc. SPIE - The International Society for Optical Engineering, 2008 International Conference on Optical Instruments and Technology: Optical Systems and Optoelectronic Instruments,Beijing. 2008, 7156: 715639
[56] Canny J.A. Computational approach to edge detection [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1986,8(6):679-698
[57]向静波.基于Contourlet变换和Canny算子的图像边缘检测方法[J].红外技术,2009,31(8):479-482
[58]黄剑玲,邹辉.一种精确的自适应图像边缘提取方法[J].计算机工程与科学. 2009, 31(9): 53-55
[59]杨凯,赵峰民,姚晓奇.基于自适应阀值Canny算法的海天线检测算法[J].舰船电子对抗. 2009, 32(4): 82-84.
[60] Mallat S, Hwang W L. Singularity detection and processing with wavelets[J]. IEEE Transactions on information theory. 1992, 38(2): 617-643.
[61] OTSU N. A threshold selection method from gray-level histograms[J].IEEE Transaction on System Man and Cybernetic,1979,9(1):62-66.
[62]何瑾,刘铁根,张昊等.应用的支票方形印鉴自适应分割.光学精密工程, 2009, 17(10): 2583-2591.
[63]姜蓉蓉,肖沙里,高家利.改进分水岭算法的彩色图像分割技术[J].计算机工程与应用. 2009, 45(19): 172-173.
[64]王晓鹏,罗进文.基于形态学梯度重建的分水岭分割.光电子激光.2005, 1(16): 98-101.
[65]边肇祺,张学工.模式识别[M].北京,清华大学出版社. 1999.
[66]董立岩,苑森淼,刘光远,李永丽.基于贝叶斯方法的尿沉渣图像分割[J].计算机工程与应用. 2007, 43(10): 15-18.
[67]张问银,金宁德,刘印锋.基于支持向量机的CD4细胞图像识别方法[J].计算机工程与科学. 2009, 31(7): 150-152.
[68]颜云辉,马朋仁,曹宇光,张坚.金属断口图像句法模式识别与分类方法[J].中国机械工程. 2004, 15(3): 259-263.
[69]王凯,张建正.尿显微图像中细胞自动识别与分类的研究与分析系统的实现[J].仪器仪表学报. 2000, 21(6): 648-650.
[70]张果,李晓娟.基于模糊模式识别的显微图像分类[J].计算机工程与设计. 2008, 29(5): 1241-1243.
[71]程迪祥,易东.重叠双核淋巴细胞的模糊模式识别方法[J].数理医药学杂志. 1998, 11(2): 115-117.
[72]冯强,于盛林,黄晓晴,张维.一种新颖的有核细胞边缘检测方法[J].中国图象图形学报. 2009, 14(10): 2004-2009.
[73]刘芳,单德彬,吕炎..基于人工神经网络的2A70铝合金形变显微组织预测[J].上海理工大学学报. 2008, 30(4): 396-399.
[74]郭晓敏,伍小明,詹希美.基于概率神经网络的寄生虫卵显微图像识别.计算机工程与应用. 2005, 41(15): 198-199.
[75]王洪元,石澄贤,曾生根,夏德深.癌细胞显微图像分割与识别研究.计算机工程与应用. 2003, 39(36): 214-216.
[76]刘铁根.光学防伪检测技术[M].北京:电子工业出版社出版:2008.
[77] Micron Technology Inc. MT9T0013-MEGAPIXEL DIGITAL IMAGE SENSOR.2004,9.
[78] EDA先锋工作室. Altera FPGA/CPLD设计(基础篇)[M].北京,人民邮电出版社:2005.
[79]李兰英,NiosⅡ嵌入式软核SOPC设计原理及应用,北京:北京航空航天大学出版社,2006
[80]李英伟,王成儒,练秋生等. USB2.0原理与工程开发(第2版).2002:273-275
[81] Cypress Corporation,CY7C68013 EZ-USB FX2? USB Microcontroller High-speed USB Peripheral Controller ,Datasheet,2002.12
[82]钱峰. EZ-USB FX2单片机原理、编程及应用[M].北京,北京航空航天大学出版社:2006.
[83]郁道银,谈恒英.工程光学[M].北京,机械工业出版社:2006.
[84]萧泽新.工程光学设计(第二版)[M].北京,电子工业出版社:2008.
[85]王超,蒋远大,翟光杰等.基于数字图像处理的自控显微镜聚焦算法研究[J].仪器仪表学报. 2009,30(6):1290-1294.
[86] PAVLOVIC G,,TEKAL PA M. Maximum likelihood parametric blur identification based on a continuous spatial domain model[J].IEEE Transactions on Image Processing.1992, 1(10): 496-504.
[87] Meenavathi MB.Volterra filtering techniques for removal of Gaussian and mixed Gaussianimpulse noise [J]. International Journal of AppliedMathematics and Computer Sciences. 2007, 4(1) :51-56.
[88] Hinich,M J,Wilson G R. Detection of Non-Gauusian Signals inNon-Gaussian Noise Usingthe Bispectrum[J]. IEEE Trans. On ASSR.1990,38(7):1126-1131.
[89] Lopes R Touzi,E Nezry. Adaptive speckle fikers and scene heterogeneity[J]. IEEE Trans On Geoseience and Remote Sensing. 1990,11,vol 28(6):992-1000.
[90] Kasparis T, Gorgiopoulos M,Payne E. Non-linear filtering techniques for narrow-band interference rejection indirect sequence spread-spectrum systems[C] , IEEE MilCOM’.1991,Mclean VA,1991:360—364.
[91] HARDIE R C,BARNER K E Rank. Conditioned rank selection filters for signal restoration[J]. IEEE Trans. Image Processing. 1994, 3(2):192-206.
[92] Wang Zhou,Zhang David. Progressive Switching Median Filter forthe Removal of Impulse Noise from Highly Corrupted Im ages[J]. IEEE Tran sactions on Circuits and Systems: Analog and DigitalSignal Processing.1999, 46(1): 78-80.
[93] Sanlie J , Donohue K D , Bilgutay N M . Order statistics filter as postdetection processors[J].IEEE Trans onAcoust, Speech, Signal Processing.1990, 38(10): 1722-1732.
[94]鲍歌堂,赵辉,陶卫.图像测量技术中几种自动调焦算法的对比分析[J].上海交通大学学报. 2005,39(1): 121-124.
[95]刘斌.基于图像技术的自动调焦方法研究与实现[硕士论文].杭州,浙江大学:2004.
[96] ITU-R.1992. ITU-R Recommendation 500-5 method for the subjectiveassessment of the quality of television pictures[S].
[97] Sheikh H R, Bovik A C.Image information and visual quality[J]. IEEE Transactions on Image Processing. 2006, 15(2): 430-444.
[98] Piella G. New quality measures fo image fusion[C]. The 7th International Conference on Information Fusion.2004, (1):542-546.
[99] Canny J.A computational approach to edge detection[J].IEEE Trans.on Pattern Analysis and Machine intelligence, PAM I-8(6),1986: 679-698.
[100] Cooksey Erica, Withers. Wm. Douglas. Rapid image binarization with morphological operators [C]. IEEE Computer Society, ICIP 2008 Proc. 2008 IEEE International Conference on Image Processing. 2008, 76408: 1017-1020.
[101] Pun T.Entropic thresholding: A new approach[J].Computer Vision Graphics Image Process. 1981, 16:210-239.
[102] John E, Alubs, Lloyd J,etc.. Centroid tracking using a probability my for target segmentation[J]. SPIE Acquisition Tracking and Pointing XVI, 2004(4714):175-185.
[103] Malladi R,Sethian J A,Vemuri B C.Shape modeling with front propagation:A level set approach.IEEE Tr.on PAMI.2001, 17(2):158-175.
[104] Wang Bing,Fan Shaosheng. An improved CANNY edge detection algorithm[C]. IEEE Computer Society, 2nd International Workshop on Computer Science and Engineering, WCSE. Qingdao, China. 2009,79686:497-500.
[105] S Arora, J Acharya, A Verma etc.. Multilevel thresholding for image segmentation through a fast statistical recursive algorithm[J]. Pattern Recognition Letters. 2008, 29 (2):119-125.
[106] Vincent L,Soille P. Watersheds in digital spaces: an efficient algorithm based on immersion simulations[J] . IEEE Transactions On Pattern Analysis And Machine Intelligence. 1991,13(6):583-598.
[107] Vladimir N. Vapnik著,许建华译.统计学习理论[M].北京,电子工业出版社:2009.
[108] V. Vapnik. The Nature of Statistical Learning Theory[M]. Springer, 1995.
[109] Papavassiliou V, Stafylakis T, Katsouros V, Carayannis G. Handwritten document image segmentation into text lines and words. Pattern recognition, 2010, 43(1): 369-377.
[110]瓦普尼克著,张学工译.统计学习理论的本质.北京,清华大学出版社:2000.
[111] X. Chen, Y. Li, R. Harrison, YQ. Zhang. Type-2 fuzzy logic-based classifier fusion for support vector machines. Applied Soft Computing, 2008, 8: 1222-1231.
[112] M. H. Fatemi, S. Gharaghani, S. Mohammadkhani, Z. Rezaie. Prediction of selectivity coefficients of univalent anions for anion-selective electrode using support vector machine. Electrochimica Acta, 2008, 53: 4276-4282.
[113] PLATT J.How to implement SVMS [J].IEEE intelligent systems.1998, 8(1):26-28.
[114] Downs Gates K E,Masters A.Exact Simplification of Support Vector Solutions[J].Journal of Machine Learning Research. 2001.2(3): 293-297.
[115] KEERTHI S S,LIN C J. Asymptotic behaviors of support vector machines with gaussian kernel[J]. Neural Computation,2003, 15: 1667-1689.
[116] Tang C-W , Hang H-M . A featured-based robust digital image watermarking scheme[J].IEEE Transactions on Signal Processing. 2003, 51(4): 950-959.
[117] Yoshua B, Yves G. No Unbiased Estimator of the Variance of K-Fold Cross-Validation[J]. The Journal of Machine Learning Research. 2004,5(12): 1089-1105.
[118] Kim, Pyunghyun, Rhee, Sehun. Three dimensional inspection of ball grid array using laser vision system[J].IEEE Transactions on Electronics Packaging Manufacturing. 1999,22(2): 151-155.
[119] C.J.Tay, He.X., Kang.X. Coplanarity study on ball grid array packaging[J]. Optics communications. 2001,40(8):1608-1612.
[120] C.J.Tay, S.H.Wang, C.Quan. Measurement of a micro solderball height using a laserprojection method[J].Optics communications. 2004, 234(1-6): 77-86.
[121] LIU Lei,CHANG Ben-kang.Spectral matching factors between super S25 and New S25 photo cathodesand reflective radiation of objects [J].Applied Optics. 2004,43(3): 616-619.
[122] N Aleixos,J Blasco,F Navarron.Multispectral inspection of citrus in real-time using machine vision and digital signal processors[J].Computers and Electronics in Agriculture. 2002, 33: 121-137.
[123]孔祥伟.组合光源与图像处理算法在工件表面缺陷检测中的应用[硕士论文].天津:天津大学,2007
[124] CCS LED机器视觉光源主要类型.http://www.xamv.com/peitao/CSS.html
[125] LightTools软件. http://www.lighttools.com/.
[126]钱关旻.万能工具显微镜放大倍数及视差的调修[J].工业计量. 2009,19(6):61-62.
[127] Yoshua B, Yves G. No Unbiased Estimator of the Variance of K-Fold Cross-Validation[J]. The Journal of Machine Learning Research. 2004,5(12): 1089-1105.
[128] Weiss S. M., Kulikowski.C.A. Computer Systemsthatlearn. Morgan Kaufinann, SanMateo, CA., 1990.
[129]刘卫平,李甘地,刘永惠.细胞毒颗粒相关蛋白TIA—1在鼻NK/T细胞淋巴瘤及淋巴增生组织中的表达[J].中华病理学杂志. 1998,27(4): 247-250.
[130] SUN Y Q. Precise solution of minimum zone circles[J].International Symposium on Instrumentation Science and Technology.2002, 3(8): 877-880.
[131] COOTES T F,TAY[ OR C J,COOPER D H, et al.. Active shape models-their training and application [J]. Computer Vision and Image Understanding.1995, 61(1):38-59.
[132] JIAO FENG,LI S,SHUM H-Y, et a1.Face alignment using statistical models and wavelet feature[C]. Proceedings of IEEE Conference on CVPR.[S.1.]:IEEE. 2003,1:321—327.
[133] GB/T 13305-2008.不锈钢中α-相面积含量金相测定法[S].
[134]刘持森.双相不锈钢中相含量的精确测定[J].理化检验-物理分册.2003,39(8): 414-416.
[135]燕惠芳.钢铁金相组织自动识别系统关键技术研究[硕士论文].南京:南京航空航天大学,2006:40-46.
[136]汤力琨.金相组织图像分析中关键算法研究[硕士论文].成都:四川大学,2005:18-24..
[137]黄丽华.彩色金相显微图像分析系统的建立与彩色图像分割方法的研究[硕士论文].杭州:浙江大学,2004:67-77.
[2]章效锋.清晰的纳米世界显微镜终极目标的千年追求[M].北京:清华大学出版社,2005.
[3]陈惠民,张延武.医用光学显微镜的分类介绍[J].医疗卫生装备. 2004,(10): 39- 41
[4]何伟业,蓝红云,唐琼华.尿液中红细胞、白细胞的UF-100尿沉渣分析仪和显微镜检测结果比较[J].现代中西医结合杂志.2009,18(1):73-74.
[5]吴敏瑾,高相理,金胜航,曹寒沁,徐卫益.尿液干化学分析仪、沉渣仪与显微镜联合检测尿液有形成分的临床应用[J].浙江检验医学. 2008, 6(2): 32- 33.
[6] Ulf Rdler, Elias Horn.适用于光学显微镜的细胞培养芯片[J].生命科学仪器. 2007, 5(5): 42- 44
[7]侯晓萍.高连续变倍比体视显微镜[硕士论文].南京:南京理工大学,2007.
[8]庄琳.三维体视显微镜在文件检验中的应用[J].森林公安.2008,(02):28-29.
[9]柳雯,杨柳,许晓芳,李颂.数字化X线牙片和体视显微镜测量根管锥度的体外研究[J].牙体牙髓牙周病学杂志.2008,18(8):429-433
[10]陈宝泓. SMT线路板组装过程中的质量控制[J].电子工艺技术. 2000, 21(2): 60-63.
[11] Liguo Chen, Lingyu Ma, Lining Sun etc.. Zoom microscope based micro positioning for MEMS sensor packaging system[C]. IECON Proc., IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006, p 3863- 3867.
[12] Wang Li-Min, Li Qiu-Rong. Corrosion behavior of CuCr alloy coated with NaCl deposit [J]. Material science and technology. 2005, 13(2):196-199.
[13] http://www.leica-microsystems.com/
[14] http://cn.olympus.com/
[15] http://www.beionmed.com/chn/microxyz.asp
[16] http://www.motic.com.cn/Home.aspx?r=AP&lang=cn_s
[17] http://www.naturegene.cn/
[18] http://www.teradyne.com/china/index.htm
[19] http://vision.lusterinc.com/solution/display.aspx?ClassID=154
[20] http://www.xmfxgd.com.cn/
[21] http://www.c-ave.com/
[22]马立,荣伟彬,孙立宁,龚振邦.面向光学精密装配的微操作机器人[J].机械工程学报. 2009, 45(2): 280- 286.
[23] http://www.shchawer.com/company.htm
[24] http://bg.qincai.net/corp-255506.html
[25] http://www.szhipower.com/
[26] Rafael C.G, Richard E.W, Steven L.E. Digital image using MATLAB [M]. Beijing, China: Publishing Houses of Electronics Industry, 2006
[27] Jarvis R A. Focus optimization criteria for computer image processing [J]. Microscope. 1976, 24 (2): 163-180.
[28] Nayar S K, Nakagawa Y. Shape from focus system [J]. IEEE trans. pattern analysis and machine intelligence.1994, 16 (8) : 824～831.
[29] Je-Ho Lee, Kun-Sop Kim. Implementation of passive automatic focusing algorithm for digital still camera [ J ]. IEEE Transactions on consumer electronics. 1995, 41 (3): 449-453.
[30] Kang-Sun Choi, Sung-Jae Ko. New Auto focusing technique using the frequency selective weighted median filter for video cameras [J ]. IEEE Transactions on consumer electronics, 1999, 45(3): 820-826.
[31] TTE Yeo,S H Ong,Jayasooriah,R Sinniah. Auto focusing for Tissue Microscopes [J].Image and vision computing.1995, 11(1): 629-659.
[32]高赞,姜威,朱孔凤.基于最大梯度和阈值的自动聚焦算法[J].电子测量与仪器学报.2007,21(5): 49-53.
[33] Baina J, Dublet J. Automatic focus and iris control for video cameras [C]. Image processing and its applications fifth international conference, 1995: 232-235.
[34] Subbarao M,Choi T,Nikzad A.Focusing techniques[J]. J. Opt. Eng.1993,32(11):2824—2836
[35]菅维乐,姜威,周贤.一种基于小波变换的数字图像自动聚焦算法[J].山东大学学报(自然科学版). 2004, 34(6): 38-40.
[36]郭丙华,廖启亮,余志.基于小波变换的快速自动聚焦算法[J].中山大学学报(自然科学版). 2007, 46(2): 12- 15.
[37]王昕,刘畅.基于提升小波变换的图像清晰度评价算法[J].东北师大学报(自然科学版).2009, 41(4): 52-57.
[38]祝世平,房建成,周锐.一种新的能量谱-熵图像聚焦评价函数[J].北京航空航天大学学报. 1999, 25(6): 720-723.
[39] Li X, Liu G S, Ni J L. Autofocusing of ISAR imaging based on entropy minimization. IEEE Trans.on Aerospace and electronic system.1999, 35(4): 1240-1251.
[40]贾晓艳,萧泽新,邓仕超.基于聚焦评价函数的自动调焦方法的研究[J].光学技术.2007, 33(Z1):7-9.
[41] Jia Y.H., Fusion of Landsat TM and SAR images based on principal component analysis[J]. Remote Sensing Technology and Application.1998, 13 (1): 46-49.
[42] Burt P.J., Adelson E.H., The Laplacian pyramid as a compact image code, IEEE Trans. on Communications, 1983, 31(4): 532-540.
[43] Toet A.Image Fusion by a Ratio of Low-pass Pyramid[J].Pattern Recognition Letters,1989,9(4):255—261.
[44] Burr P J,Kolczynski R J. Enhanced image capture through fusion[C].Proc the 4th Iutl Conf on Computer Vision, Berlin, Germany, 1993:l73一l82.
[45] Ranchin T., Wald L., The wavelet transform for the analysis of remotely sensed images [J]. International Journal of Remote Sensing.1993, 14(3): 615-619.
[46] Unser M., Texture classification and segmentation using wavelet frames, IEEE Trans. On Image Processing, 1995, 11(4): 1549-1560.
[47]曾志峰,马华山.小波变换和清晰块搜索结合的图像融合算法[J].计算机工程与应用. 2008, 44(31): 199-201.
[48] Donoho D L,Duncan M R. Digital curvelet transform: Strategy, implementation and experiments [C]. Proc. of SPIE, the international society for optical engineering, Orlando, FL, USA. 2000,V4056: 12-30.
[49] DO M N, VETTERLI M. The Contourlet transform: an efficient directional mu1tiresolution image representation[J].IEEE Trans. Image Proc. 2005, 14(12): 2091—2106.
[50] LU Y,DO M N A new Contourlet transform withsharp frequency localization [c].Proc. of 2006 IEEE International Conference on Image Processing, Atlanta,USA. 2006, 1629-1632.
[51]屈小波,闫敬文,杨贵德.改进拉普拉斯能量和的尖锐频率局部化Contourlet域多聚焦图像融合方法[J].光学精密工程. 2009, 17(5):1204-1212.
[52] Tang J.S., A contrast based image fusion technique in the DCT domain [C]. Digital Signal Processing, 2004, 14(3): 218-226
[53]张建伟,张启衡.基于块遍历的直线边缘特征提取[J].光学精密工程. 2009,17(3): 662-668.
[54]陈平,潘晋孝,刘宾.CT图像边缘退化模型的建立及其在图像尺寸测量中的应用[J].光学精密工程,2009,17(9):2269-2275
[55] DENG S C, LIU T G, XIAO Z X et al.. An automatic detection system for flatness of integrated circuit pins[C]. Proc. SPIE - The International Society for Optical Engineering, 2008 International Conference on Optical Instruments and Technology: Optical Systems and Optoelectronic Instruments,Beijing. 2008, 7156: 715639
[56] Canny J.A. Computational approach to edge detection [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1986,8(6):679-698
[57]向静波.基于Contourlet变换和Canny算子的图像边缘检测方法[J].红外技术,2009,31(8):479-482
[58]黄剑玲,邹辉.一种精确的自适应图像边缘提取方法[J].计算机工程与科学. 2009, 31(9): 53-55
[59]杨凯,赵峰民,姚晓奇.基于自适应阀值Canny算法的海天线检测算法[J].舰船电子对抗. 2009, 32(4): 82-84.
[60] Mallat S, Hwang W L. Singularity detection and processing with wavelets[J]. IEEE Transactions on information theory. 1992, 38(2): 617-643.
[61] OTSU N. A threshold selection method from gray-level histograms[J].IEEE Transaction on System Man and Cybernetic,1979,9(1):62-66.
[62]何瑾,刘铁根,张昊等.应用的支票方形印鉴自适应分割.光学精密工程, 2009, 17(10): 2583-2591.
[63]姜蓉蓉,肖沙里,高家利.改进分水岭算法的彩色图像分割技术[J].计算机工程与应用. 2009, 45(19): 172-173.
[64]王晓鹏,罗进文.基于形态学梯度重建的分水岭分割.光电子激光.2005, 1(16): 98-101.
[65]边肇祺,张学工.模式识别[M].北京,清华大学出版社. 1999.
[66]董立岩,苑森淼,刘光远,李永丽.基于贝叶斯方法的尿沉渣图像分割[J].计算机工程与应用. 2007, 43(10): 15-18.
[67]张问银,金宁德,刘印锋.基于支持向量机的CD4细胞图像识别方法[J].计算机工程与科学. 2009, 31(7): 150-152.
[68]颜云辉,马朋仁,曹宇光,张坚.金属断口图像句法模式识别与分类方法[J].中国机械工程. 2004, 15(3): 259-263.
[69]王凯,张建正.尿显微图像中细胞自动识别与分类的研究与分析系统的实现[J].仪器仪表学报. 2000, 21(6): 648-650.
[70]张果,李晓娟.基于模糊模式识别的显微图像分类[J].计算机工程与设计. 2008, 29(5): 1241-1243.
[71]程迪祥,易东.重叠双核淋巴细胞的模糊模式识别方法[J].数理医药学杂志. 1998, 11(2): 115-117.
[72]冯强,于盛林,黄晓晴,张维.一种新颖的有核细胞边缘检测方法[J].中国图象图形学报. 2009, 14(10): 2004-2009.
[73]刘芳,单德彬,吕炎..基于人工神经网络的2A70铝合金形变显微组织预测[J].上海理工大学学报. 2008, 30(4): 396-399.
[74]郭晓敏,伍小明,詹希美.基于概率神经网络的寄生虫卵显微图像识别.计算机工程与应用. 2005, 41(15): 198-199.
[75]王洪元,石澄贤,曾生根,夏德深.癌细胞显微图像分割与识别研究.计算机工程与应用. 2003, 39(36): 214-216.
[76]刘铁根.光学防伪检测技术[M].北京:电子工业出版社出版:2008.
[77] Micron Technology Inc. MT9T0013-MEGAPIXEL DIGITAL IMAGE SENSOR.2004,9.
[78] EDA先锋工作室. Altera FPGA/CPLD设计(基础篇)[M].北京,人民邮电出版社:2005.
[79]李兰英,NiosⅡ嵌入式软核SOPC设计原理及应用,北京:北京航空航天大学出版社,2006
[80]李英伟,王成儒,练秋生等. USB2.0原理与工程开发(第2版).2002:273-275
[81] Cypress Corporation,CY7C68013 EZ-USB FX2? USB Microcontroller High-speed USB Peripheral Controller ,Datasheet,2002.12
[82]钱峰. EZ-USB FX2单片机原理、编程及应用[M].北京,北京航空航天大学出版社:2006.
[83]郁道银,谈恒英.工程光学[M].北京,机械工业出版社:2006.
[84]萧泽新.工程光学设计(第二版)[M].北京,电子工业出版社:2008.
[85]王超,蒋远大,翟光杰等.基于数字图像处理的自控显微镜聚焦算法研究[J].仪器仪表学报. 2009,30(6):1290-1294.
[86] PAVLOVIC G,,TEKAL PA M. Maximum likelihood parametric blur identification based on a continuous spatial domain model[J].IEEE Transactions on Image Processing.1992, 1(10): 496-504.
[87] Meenavathi MB.Volterra filtering techniques for removal of Gaussian and mixed Gaussianimpulse noise [J]. International Journal of AppliedMathematics and Computer Sciences. 2007, 4(1) :51-56.
[88] Hinich,M J,Wilson G R. Detection of Non-Gauusian Signals inNon-Gaussian Noise Usingthe Bispectrum[J]. IEEE Trans. On ASSR.1990,38(7):1126-1131.
[89] Lopes R Touzi,E Nezry. Adaptive speckle fikers and scene heterogeneity[J]. IEEE Trans On Geoseience and Remote Sensing. 1990,11,vol 28(6):992-1000.
[90] Kasparis T, Gorgiopoulos M,Payne E. Non-linear filtering techniques for narrow-band interference rejection indirect sequence spread-spectrum systems[C] , IEEE MilCOM’.1991,Mclean VA,1991:360—364.
[91] HARDIE R C,BARNER K E Rank. Conditioned rank selection filters for signal restoration[J]. IEEE Trans. Image Processing. 1994, 3(2):192-206.
[92] Wang Zhou,Zhang David. Progressive Switching Median Filter forthe Removal of Impulse Noise from Highly Corrupted Im ages[J]. IEEE Tran sactions on Circuits and Systems: Analog and DigitalSignal Processing.1999, 46(1): 78-80.
[93] Sanlie J , Donohue K D , Bilgutay N M . Order statistics filter as postdetection processors[J].IEEE Trans onAcoust, Speech, Signal Processing.1990, 38(10): 1722-1732.
[94]鲍歌堂,赵辉,陶卫.图像测量技术中几种自动调焦算法的对比分析[J].上海交通大学学报. 2005,39(1): 121-124.
[95]刘斌.基于图像技术的自动调焦方法研究与实现[硕士论文].杭州,浙江大学:2004.
[96] ITU-R.1992. ITU-R Recommendation 500-5 method for the subjectiveassessment of the quality of television pictures[S].
[97] Sheikh H R, Bovik A C.Image information and visual quality[J]. IEEE Transactions on Image Processing. 2006, 15(2): 430-444.
[98] Piella G. New quality measures fo image fusion[C]. The 7th International Conference on Information Fusion.2004, (1):542-546.
[99] Canny J.A computational approach to edge detection[J].IEEE Trans.on Pattern Analysis and Machine intelligence, PAM I-8(6),1986: 679-698.
[100] Cooksey Erica, Withers. Wm. Douglas. Rapid image binarization with morphological operators [C]. IEEE Computer Society, ICIP 2008 Proc. 2008 IEEE International Conference on Image Processing. 2008, 76408: 1017-1020.
[101] Pun T.Entropic thresholding: A new approach[J].Computer Vision Graphics Image Process. 1981, 16:210-239.
[102] John E, Alubs, Lloyd J,etc.. Centroid tracking using a probability my for target segmentation[J]. SPIE Acquisition Tracking and Pointing XVI, 2004(4714):175-185.
[103] Malladi R,Sethian J A,Vemuri B C.Shape modeling with front propagation:A level set approach.IEEE Tr.on PAMI.2001, 17(2):158-175.
[104] Wang Bing,Fan Shaosheng. An improved CANNY edge detection algorithm[C]. IEEE Computer Society, 2nd International Workshop on Computer Science and Engineering, WCSE. Qingdao, China. 2009,79686:497-500.
[105] S Arora, J Acharya, A Verma etc.. Multilevel thresholding for image segmentation through a fast statistical recursive algorithm[J]. Pattern Recognition Letters. 2008, 29 (2):119-125.
[106] Vincent L,Soille P. Watersheds in digital spaces: an efficient algorithm based on immersion simulations[J] . IEEE Transactions On Pattern Analysis And Machine Intelligence. 1991,13(6):583-598.
[107] Vladimir N. Vapnik著,许建华译.统计学习理论[M].北京,电子工业出版社:2009.
[108] V. Vapnik. The Nature of Statistical Learning Theory[M]. Springer, 1995.
[109] Papavassiliou V, Stafylakis T, Katsouros V, Carayannis G. Handwritten document image segmentation into text lines and words. Pattern recognition, 2010, 43(1): 369-377.
[110]瓦普尼克著,张学工译.统计学习理论的本质.北京,清华大学出版社:2000.
[111] X. Chen, Y. Li, R. Harrison, YQ. Zhang. Type-2 fuzzy logic-based classifier fusion for support vector machines. Applied Soft Computing, 2008, 8: 1222-1231.
[112] M. H. Fatemi, S. Gharaghani, S. Mohammadkhani, Z. Rezaie. Prediction of selectivity coefficients of univalent anions for anion-selective electrode using support vector machine. Electrochimica Acta, 2008, 53: 4276-4282.
[113] PLATT J.How to implement SVMS [J].IEEE intelligent systems.1998, 8(1):26-28.
[114] Downs Gates K E,Masters A.Exact Simplification of Support Vector Solutions[J].Journal of Machine Learning Research. 2001.2(3): 293-297.
[115] KEERTHI S S,LIN C J. Asymptotic behaviors of support vector machines with gaussian kernel[J]. Neural Computation,2003, 15: 1667-1689.
[116] Tang C-W , Hang H-M . A featured-based robust digital image watermarking scheme[J].IEEE Transactions on Signal Processing. 2003, 51(4): 950-959.
[117] Yoshua B, Yves G. No Unbiased Estimator of the Variance of K-Fold Cross-Validation[J]. The Journal of Machine Learning Research. 2004,5(12): 1089-1105.
[118] Kim, Pyunghyun, Rhee, Sehun. Three dimensional inspection of ball grid array using laser vision system[J].IEEE Transactions on Electronics Packaging Manufacturing. 1999,22(2): 151-155.
[119] C.J.Tay, He.X., Kang.X. Coplanarity study on ball grid array packaging[J]. Optics communications. 2001,40(8):1608-1612.
[120] C.J.Tay, S.H.Wang, C.Quan. Measurement of a micro solderball height using a laserprojection method[J].Optics communications. 2004, 234(1-6): 77-86.
[121] LIU Lei,CHANG Ben-kang.Spectral matching factors between super S25 and New S25 photo cathodesand reflective radiation of objects [J].Applied Optics. 2004,43(3): 616-619.
[122] N Aleixos,J Blasco,F Navarron.Multispectral inspection of citrus in real-time using machine vision and digital signal processors[J].Computers and Electronics in Agriculture. 2002, 33: 121-137.
[123]孔祥伟.组合光源与图像处理算法在工件表面缺陷检测中的应用[硕士论文].天津:天津大学,2007
[124] CCS LED机器视觉光源主要类型.http://www.xamv.com/peitao/CSS.html
[125] LightTools软件. http://www.lighttools.com/.
[126]钱关旻.万能工具显微镜放大倍数及视差的调修[J].工业计量. 2009,19(6):61-62.
[127] Yoshua B, Yves G. No Unbiased Estimator of the Variance of K-Fold Cross-Validation[J]. The Journal of Machine Learning Research. 2004,5(12): 1089-1105.
[128] Weiss S. M., Kulikowski.C.A. Computer Systemsthatlearn. Morgan Kaufinann, SanMateo, CA., 1990.
[129]刘卫平,李甘地,刘永惠.细胞毒颗粒相关蛋白TIA—1在鼻NK/T细胞淋巴瘤及淋巴增生组织中的表达[J].中华病理学杂志. 1998,27(4): 247-250.
[130] SUN Y Q. Precise solution of minimum zone circles[J].International Symposium on Instrumentation Science and Technology.2002, 3(8): 877-880.
[131] COOTES T F,TAY[ OR C J,COOPER D H, et al.. Active shape models-their training and application [J]. Computer Vision and Image Understanding.1995, 61(1):38-59.
[132] JIAO FENG,LI S,SHUM H-Y, et a1.Face alignment using statistical models and wavelet feature[C]. Proceedings of IEEE Conference on CVPR.[S.1.]:IEEE. 2003,1:321—327.
[133] GB/T 13305-2008.不锈钢中α-相面积含量金相测定法[S].
[134]刘持森.双相不锈钢中相含量的精确测定[J].理化检验-物理分册.2003,39(8): 414-416.
[135]燕惠芳.钢铁金相组织自动识别系统关键技术研究[硕士论文].南京:南京航空航天大学,2006:40-46.
[136]汤力琨.金相组织图像分析中关键算法研究[硕士论文].成都:四川大学,2005:18-24..
[137]黄丽华.彩色金相显微图像分析系统的建立与彩色图像分割方法的研究[硕士论文].杭州:浙江大学,2004:67-77.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |