基于机器视觉的家蚕微粒子图像识别方法的研究
|
摘要
家蚕微粒子病是由微孢子虫寄生蚕体细胞内引起的可传染性原虫病,它是一种古老的、分布甚广且毁灭性强的蚕病,俗称“蚕癌”,是目前各蚕业生产国规定唯一法定检疫的蚕病。按照优选蚕种、制造无病毒蚕种以及消灭本病的原则,一直沿用母蛾镜检法来防止微粒子病毒通过母体传染,如今已成为防止家蚕微粒子病的主要检测手段。
由于人工镜检的方法存在劳动强度大、结果不可复现且容易产生错检或漏检的问题,本文开展基于基于机器视觉的家蚕微粒子病识别方法的研究,将机器视觉技术引入蚕病的检测,主要内容如下：
(1)针对微粒子显微图像对比度低、图像不清晰的特点,提出了基于模糊信息的图像增强预处理方法,该方法融合了基于全局的Pal模糊增强与局部模糊对比度增强两种算法思想,实现了改善图像整体对比度和增强目标图像局部细节信息的目的,有利于后续的图像分割处理。
(2)针对复杂背景条件下微粒子显微图像的分割技术问题,提出了基于HSI模型的微粒子图像分割技术。根据微粒子图像的颜色特征提取准则,实现了彩色目标对象与非目标杂质图像的直接分离,减少了与微粒子形态相似的其它疑似孢子产生误判的可能性；消除了背景中部分杂质图像对于分割处理效果的不利影响,提高了二维Otsu分割方法对于彩色目标H分量图像分割的适应性。
(3)根据微粒子图像的形态特点,研究了微粒子图像的特征提取技术,实现了微粒子图像初始形态特征参数集的选取；针对微粒子图像多特征选择的优化组合问题,提出了基于多特征融合的微粒子图像特征选择技术,该技术通过相关分析方法,实现了初始特征集中特征冗余信息的去除,并采用基于分类器学习的特征优化选择方法,确定了微粒子图像的最佳分类特征集。
(4)分析了BP神经网络的学习过程,提出了改进的BP优化算法；针对BP神经网络存在“局部极小值”和收敛速度慢的问题,研究了遗传神经网络的混合训练方法,提出了基于遗传神经网络的家蚕微粒子病识别技术方案,确定了识别系统最优的网络结构,验证了遗传神经网络应用于微粒子图像识别问题的有效性与正确性,并对识别系统方案的软硬件实现技术进行了总体设计。
Silkworm pebrine disease is one kind of infectious protozoal disease caused by nosema which parasite inside silkworm cells. It is an ancient, widely distributed and destructive strength of silkworm disease, which is commonly known as "silkworm cancer" and it is the sole statutory quarantine silkworm disease in the sericulture producing countries. In accordance with the principle which is preferred silkworm, silkworm eggs made none of the disease and the elimination of the virus, the female moth microscopic method has been used to prevent maternal transmission of virus particles, and now it has become the particulate detection means of preventing the silkworm diseases.
As the manual examination has the problem of high labor intensity and the results can not reproduce and error-prone or undetected, the research to identification technology to the silkworm pebrine based on computer vision have been studied in this doctoral dissertation, and brought computer vision technology into the silkworm disease detection.The main contents are as following:
(1) According to the characteristics that the microscopic image of particles has low-contrast and it is not clear, fuzzy image enhancement preprocessing method is proposed based on the fuzzy information. This method combines two algorithms which is the theory of Pal fuzzy enhancement based on global and the fuzzy contrast enhancement based on local and improved global contrast image and enhance the local details of the target image, this is conducive to the subsequent image segmentation.
(2) In the light of technical problems for the microscopic image segmentation of particles under complex background and conditions, the technology of image segmentation for particles based on the model of HSI was proposed. According to the extraction criteria of color image feature for particles,the target of color image with a direct non-target separation of impurities was achieved, thus the possibility of false positives for the spores which the form is similar to particles was reduced; as well as the adverse effects for the segmentation which was influenced by the some of the background image of impurities was eliminated, the adaptability of image segmenta-tion which is the H component for color target based on two-dimensional Otsu segmentation method was improved.
(3) According to the morphological characteristics of the image particles, the multi-feature extraction techniques of image feature for particles was studied and the original parameters set of features was extracted; in the light of images for particles more than the optimal combination of feature selection problem, a multi-feature fusion of particles in the image feature selection technique was proposed. By the method of correlation analysis, the removal of early start features and redundant information was achieved, the best classification sets of image feature for particles were determined based on the selection method of optimization feature by learning-based classifier.
(4) The learning process of BP neural network is analyzed, and the improved BP optimal algorithm was proposed. Because of the problems within the BP neural network which are "local minimum" and "slow convergence", the hybrid training method of genetic neural network was studied, and the recognition technology for silkworm pebrine disease based on genetic neural network was proposed, furthermore the optimal network structure of the recognition system was determined. Based on the genetic neural network, the overall design of the recognition system about hardware and software implementation technology was conducted, and the validity and accuracy of the system was verified.
由于人工镜检的方法存在劳动强度大、结果不可复现且容易产生错检或漏检的问题,本文开展基于基于机器视觉的家蚕微粒子病识别方法的研究,将机器视觉技术引入蚕病的检测,主要内容如下：
(1)针对微粒子显微图像对比度低、图像不清晰的特点,提出了基于模糊信息的图像增强预处理方法,该方法融合了基于全局的Pal模糊增强与局部模糊对比度增强两种算法思想,实现了改善图像整体对比度和增强目标图像局部细节信息的目的,有利于后续的图像分割处理。
(2)针对复杂背景条件下微粒子显微图像的分割技术问题,提出了基于HSI模型的微粒子图像分割技术。根据微粒子图像的颜色特征提取准则,实现了彩色目标对象与非目标杂质图像的直接分离,减少了与微粒子形态相似的其它疑似孢子产生误判的可能性；消除了背景中部分杂质图像对于分割处理效果的不利影响,提高了二维Otsu分割方法对于彩色目标H分量图像分割的适应性。
(3)根据微粒子图像的形态特点,研究了微粒子图像的特征提取技术,实现了微粒子图像初始形态特征参数集的选取；针对微粒子图像多特征选择的优化组合问题,提出了基于多特征融合的微粒子图像特征选择技术,该技术通过相关分析方法,实现了初始特征集中特征冗余信息的去除,并采用基于分类器学习的特征优化选择方法,确定了微粒子图像的最佳分类特征集。
(4)分析了BP神经网络的学习过程,提出了改进的BP优化算法；针对BP神经网络存在“局部极小值”和收敛速度慢的问题,研究了遗传神经网络的混合训练方法,提出了基于遗传神经网络的家蚕微粒子病识别技术方案,确定了识别系统最优的网络结构,验证了遗传神经网络应用于微粒子图像识别问题的有效性与正确性,并对识别系统方案的软硬件实现技术进行了总体设计。
Silkworm pebrine disease is one kind of infectious protozoal disease caused by nosema which parasite inside silkworm cells. It is an ancient, widely distributed and destructive strength of silkworm disease, which is commonly known as "silkworm cancer" and it is the sole statutory quarantine silkworm disease in the sericulture producing countries. In accordance with the principle which is preferred silkworm, silkworm eggs made none of the disease and the elimination of the virus, the female moth microscopic method has been used to prevent maternal transmission of virus particles, and now it has become the particulate detection means of preventing the silkworm diseases.
As the manual examination has the problem of high labor intensity and the results can not reproduce and error-prone or undetected, the research to identification technology to the silkworm pebrine based on computer vision have been studied in this doctoral dissertation, and brought computer vision technology into the silkworm disease detection.The main contents are as following:
(1) According to the characteristics that the microscopic image of particles has low-contrast and it is not clear, fuzzy image enhancement preprocessing method is proposed based on the fuzzy information. This method combines two algorithms which is the theory of Pal fuzzy enhancement based on global and the fuzzy contrast enhancement based on local and improved global contrast image and enhance the local details of the target image, this is conducive to the subsequent image segmentation.
(2) In the light of technical problems for the microscopic image segmentation of particles under complex background and conditions, the technology of image segmentation for particles based on the model of HSI was proposed. According to the extraction criteria of color image feature for particles,the target of color image with a direct non-target separation of impurities was achieved, thus the possibility of false positives for the spores which the form is similar to particles was reduced; as well as the adverse effects for the segmentation which was influenced by the some of the background image of impurities was eliminated, the adaptability of image segmenta-tion which is the H component for color target based on two-dimensional Otsu segmentation method was improved.
(3) According to the morphological characteristics of the image particles, the multi-feature extraction techniques of image feature for particles was studied and the original parameters set of features was extracted; in the light of images for particles more than the optimal combination of feature selection problem, a multi-feature fusion of particles in the image feature selection technique was proposed. By the method of correlation analysis, the removal of early start features and redundant information was achieved, the best classification sets of image feature for particles were determined based on the selection method of optimization feature by learning-based classifier.
(4) The learning process of BP neural network is analyzed, and the improved BP optimal algorithm was proposed. Because of the problems within the BP neural network which are "local minimum" and "slow convergence", the hybrid training method of genetic neural network was studied, and the recognition technology for silkworm pebrine disease based on genetic neural network was proposed, furthermore the optimal network structure of the recognition system was determined. Based on the genetic neural network, the overall design of the recognition system about hardware and software implementation technology was conducted, and the validity and accuracy of the system was verified.
引文
[1]茧丝交易网：2010全国蚕茧总产61.6万吨.[EB/OL].2011-01-18http://china.toocle.com/cbna/item/2011-01-18/5618254.html
[2]中国历史文化网：中国古代养蚕科学技术的发展和传播.[EB/OL].2010-07-18http://china-culture.jlmpc.cn/
[3]金琳.中国古代对蚕病症状与防治的记述[J].蚕桑通报,2001,32(2)：7-9.
[4]科技日报数字报：养蚕消毒技术课题通过鉴定.[EB/OL].2010-12-13http://www.stdaily.com
[5]杨继玲.略谈《齐民要术》中古代山东的蚕桑技术[J].管子学刊,2007,5(3)：55-58.
[6]张英利.十九世纪末二十世纪初中国对日本蚕业新科技的引进和影响[J].古今农业,2005(4)：55-60.
[7]李艳梅,李燕.传染性蚕病的综合防治措施[J].云南农业科技,2010,S1：155-156.
[8]李龙.印度蚕业发展研究[D].四川：西南大学,2008.
[9]许刚,潘丽芬.数码显微技术在微粒子病检验中的应用与研究[J].江苏蚕业,2002(1)：14-16.
[10]王雪梅.家蚕微粒子检测技术研究进展[J].广西蚕业,2006,43(2)：16-18.
[11]陈克平,徐家萍,姚勤.家蚕分子生物学研究进展[J].生物科学研究,2003,7(3)：208-213.
[12]Lathrop, Larry D. Spectral classification of motato disease severity levels [C]. Proceeding of the American Society of Photogramm Fall Tech Meet,1978,329-342.
[13]Rehkugler G E, Throop J A. Apple Sorting with machine Vision [J]. Transactions of the ASAE,1985,29(5):1388-1395.
[14]Miller B K, Delwiche M J. A color vision System for peach grading [J].Transactions of the ASAE,1989,32(4):1484-1490.
[15]Shearer S A, Payne F. A Color and defect Sorting of bell peppers using machine vision [J]. Transactions of the ASAE,1990,33(6):2045-2050.
[16]Ng H F, Wilcke W F. Machine vision evaluation of corn kernel mechanical and mold damage [J]. Transactions of ASAE,1998,41(2):415-420.
[17]郭文川,朱新华.机器视觉技术在谷物识别与分级中的研究进展[J].粮食与饲料工业,2002(6)：50-51.
[18]林开颜,吴军辉,徐立鸿.基于计算机视觉技术的水果形状分级方法[J].农业机械学报,2005,36(6)：71-74.
[19]成芳.稻种质量的机器视觉无损检测研究[D].杭州：浙江大学,2004.
[20]刘燕德,应义斌,成芳.机器视觉技术在种子纯度检验中的应用[J].农业机械学报,2003,34(5)：161-163.
[21]黎萍,朱军燕,刘燕德.机器视觉在农产品检测与分级中的应用与展望[J].江西农业大学学报,2005,27(5)：796-800.
[22]黄星弈,李剑,姜松.基于计算机视觉的稻谷品种识别技术的研究[J].江苏大学学报,2004,25(2)：102-104.
[23]张香琴.家蚕微粒子病的图像识别技术[D].江苏：江苏大学,1998.
[24]何东健.数字图像处理[M].西安：西安电子科技大学出版社,2003.
[25]赵荣椿等.数字图象处理导论[M].西安：西北工业大学出版杜,2000.
[26]傅弘,颜鸿森,齐春.基于自适应定向止交投影分解的图像分割方法[J].中国图像图形学报,2003,8(3)：286-291.
[27]王康泰,戴文战.一种基于Sobel算子和灰色关联度的图像边缘检测方法[J].计算机应用,2006,26(5)：1035-1036.
[28]郭臻,陈远知.图像阈值分割算法研究[J].中国传媒大学学报自然科学版,2008,15(2)：77-78.
[29]王广君,田金文,柳健.基于四义树结构的图像分割技术[J].红外与激光工程,2001,30(1)：12-14.
[30]屈彬,王景熙.一种基于区域生长规则的快速边缘跟踪算法[J].四川大学学报,2002,34(2)：10-14.
[31]宋淑娜.基于自适应背景区域选择的图像分割方法[D].江苏：江苏科技大学,2009.
[32]刘勃,应隽,周珑等.数字图像分割技术及其进展[J].天水师范学院学报,2007,27(5)：35-40.
[33]张博,苏永利,张书玲.一种基于区域填充的C-V模型图像分割方法[J].系统仿真学报,2008,20(19)：5228-5230.
[34]杨纶标,高英仪.模糊数学原理与应用第四版[M].广州：华南理工大学出版社,2005.
[35]M.Singh, P.Patel, D.Khosla, T.Kim. Segmeniation of funetional MRI by K-means clustering [J], IEEETrans. Nucl.Sci,1996,43(6):2030-2036.
[36]Mohamed NA, Sameh MY, Nevin M. A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data [J]. IEEE Trans.On Medical Imaging,21(3),2002: 193-199.
[37]Liew AW, Yan H. An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation [J], IEEE Trans. On Medical Imaging,2003,22(9):1063-1075.
[38]颜刚.基于模糊马尔可夫场的图像算法研究[D].广州：南方医科大学,2005.
[39]林亚忠,程跃斌,陈武凡.基于修正的分段模糊吉伯斯随机场模型的图像分割[J].计算机应用,2005,25(11)：2606-2608.
[40]陈琳.基于数学形态学的图像分割技术研究[DD].云南：昆明理工大学,2005.
[41]杨杰.数学形态学的图像分割算法[J].计算机工程与科学,1998,20(4)：21-27.
[42]杨静.基于数学形态学的图像分割研究及应用[J].仪器仪表用户,2005,12(5)：18-20.
[43]张少刚.遗传算法在计算机仿真技术中的应用[J].自动化与仪器仪表,2009,6(146)：56-57.
[44]欧萍,贺电.遗传算法粒在二维最大熵值图像分割中的应用[J].计算机仿真,2011,28(1)：294-298.
[45]何春华,胡迎春.基于改进遗传算法的自动阈值图像分割方法[J].计算机仿真,2011,28(2)：312-315.
[46]艾虎.基于计算机视觉的人工：神经网络和图像处理技术的牛肉大理石花纹自动分级研究[D].四川：四川农业大学,2009.
[47]黄健.基于人工神经网络和纹理特征的马尾松图像分割方法[D].广东：福建农林大学,2008.
[48]孙优贤,卢建刚,许锋.神经网络在图像处理中的应用[J],信息与控制,2003,32(4)：344-350.
[49]杨嘉麟,郑文岭,马文丽.基于改进的BP神经网络的血液细胞图像分割[J].微型电脑应用,2008,24(4)：4-7.
[50]耿伯英,陆建峰,杨静宇.基于模糊主色调的彩色图像分割及道路检测[J].南京理工大学学报,2000,24(4)：353-358.
[51]O'Farrel M,Lewis E,Flanagan C.Using reflection based optical fiber system and neural networks to evaluate the quality of food in a large-scale industrial oven [J].Sensors and Actuators(Physical),2004,5(2):424-433.
[52]Dooley, Karmakar, Manzur. A fuzzy rule-based colour image segmentation algorithm [C]. IEEE International Conference on Image Processing, Barcelona, Spain,2003,977-980.
[53]赵春燕,时秀芳,闫长青.图像分割综述[J].中国科技信息,2009(1)：42-43.
[54]史健芳,张富军,郝宝峰.基于小波变换和数学形态学的图像分割算法[J].太原理工大学学报,2009,40(5)：490-493.
[55]魏晋相,汪华章,何小海.基于模糊C均值聚类和数学形态学的图像分割[J].成都信息工程学院学报,2008,23(6)：618-621.
[56]王克刚,耿国华.基于小波平滑直方图的模糊聚类图像分割方法[C].图像图形技术与应用进展-第三届图像图形技术与应用学术会议论文集,2008,321-328.
[57]吴学明.图像分割的算法研究[D].四川：成都理工大学,2006.
[58]吴贵芳,徐科钢.板表面质量在线监测技术[M].北京：科学出版社,2010.
[59]宋余庆,陈健美,郭依正.基于多特征融合的医学图像识别研究[J].计算机应用研究,2008,25(6)：1750-1752.
[60]陆丽珍,刘仁义,刘南.一种融合颜色和纹理特征的遥感图像检索方法[J].中国图像图形学报,2004,9(3)：328-332.
[61]谈蓉蓉.利用颜色和形状特征的杂草识别方法研究[D].江苏：江苏大学,2009.
[62]闫小梅,刘双喜,张春庆.基于颜色特征的玉米种子纯度识别[J].农业工：程学报,2010,26(1)：46-50.
[63]Majumdar S, Jayas D S. Classification of cereal grains using machine vision [J]. Transactions of the ASAE,2000,43(6):1669-1675.
[64]周平,汪亚明,赵匀.基于颜色分量运算与色域压缩的杂草实时检测方法[J].农业机械学报,2007,38(1)：116-119.
[65]Burks T F, Shearer S A.Classification of weed species using color texture features and discriminate analysis [J]. Transaetion of the ASAE,2000,43(2):441-448.
[66]赵杰文,刘木华,杨国彬.基于HSI颜色特征的田间成熟番茄识别技术[J].农业机械学报,2004,35(5)：122-125.
[67]金飞剑.基于机器视觉的杂草图像特征提取及识别研究[D].江苏：江苏大学,2007.
[68]夏庆观,盛党红,路红.零件图像特征提取和识别的研究[J].中国机械工程,2005,16(22)：2031-2033.
[69]杨铁滨.基于机器视觉的陶瓷球表面缺陷自动检测技术研究[D].哈尔滨：哈尔滨工业大学,2007.
[70]蔡健荣,许俐.家蚕微粒子病的图象形状特征分析[J].江苏理工大学学报,1998,19(5)：24-27.
[71]郑敏江.基于数字图像处理的玉米种子质量分级方法研究[D].武汉：武汉理工大学,2009.
[72]查英,刘铁根,杜东.图像识别技术在零件装配自动识别中的应用[J].计算机工程,2006,32(10)：179-185.
[73]A.N. Rajagopalan, K. Srinivasa Rao, Y. Anoop Kumar. Face recognition using multiple facial features [J]. Pattern Recognition Letters,2007,28(3):335-341.
[74]V.B. Sunil, S.S. Pande. Automatic recognition of features from freeform surface CAD models [J]. Computer-Aided Design,2008,40(4):502-517.
[75]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4)：622-635.
[76]李虹.基于机器视觉路面状态识别关键技术研究[D].长春：吉林大学,2009.
[77]Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification [J]. IEEE Transactions on Systems, Man, and Cybernetics,1973,3(6):610-621.
[78]Soh K S, Tsatsoulis C. Texture analysis of SAR sea ice in agery using gray level coocuurrence matrices [J]. IEEE Transactions on Geoscience and Remote Sensing,1999, 37(2):780-795.
[79]Walker R F, Jackway P T, Longstaff I D. Recent developments in the use of co-occurrence matrix for texture recognition [C]. Proceedings of IEEE Conference on Digital Signal Processing, Greece,1997,1:63-65.
[80]Cross G R, Jain A K. Markov random field texture models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1983,5(1):25-39.
[81]Kapan L M, Kuo C-C. Extending self-sin ilarity for fractional brownian motion [J]. IEEE Transactions on Signal Processing,1994,42(12):3526-3530.
[82]Clausi D A, Jernigan M E. Designing Gabor filters for optimal texture separability [J]. Pattern Recognition,2000,33(11):1835-1849.
[83]Soille P. Morphological Image Analysis Principles and Applications [M]. Germany:Springer Press,2003.
[84]宋凯.基于计算机视觉的农作物病害识别方法的研究[D].沈阳：沈阳农业大学,2008.
[85]Hemming J, T Rath. Computer-vision-based weed identification under field conditions using controlled lighting [J].Transactions of the ASAE,2001,78(3):233-243.
[86]Burks T F, Shearer S A, Green J D. Influence of weed maturity levels on species classification using machine vision [J].Weed Science,2002(50):802-811.
[87]Pydipati R, Burks T F, Lee W S.Statistical and neural network classifiers for citrus disease detection using machine vision [J].Transactions of the American Society of Agricultural Engineers,2005,48(5):2007-2014.
[88]Mathanker S K, Weckler P R, Taylor R K. Canola-weed identification for machine vision based patch spraying. American Society of Agricultural and Biological Engineers (Paper Number:085134).
[89]王丽华.基于神经网络的图像识别系统的研究[D].北京：中国石油大学,2008.
[90]于杨.田间青椒图像识别系统的研究[D].哈尔滨：中国石油大学,2008.
[91]夏庆观,盛党红,路红.零件图像特征提取和识别的研究[J].中国机械工程,2005,16(22)：2031-2033.
[92]王丹.车身零部件视觉检测中摄像机标定方法的研究与应用[D].长春：吉林大学,2009.
[93]周涛,蒋芸,王勇.基于小波神经网络的医学图像分类方法[J].计算机应用,2010,30(10)：2857-2860.
[94]Turkoglu Ibrahim, Arslan Ahmet, Ilkay Erdogan. An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks[J]. Computers in Biology and Medicine,2003,33(4):319-331.
[95]王家文,李仰军.MATLAB 7.0图形图像处理[M].北京：国防工业出版社,2006.
[96]V. Caselles, J.L. Lisani, J.M. Morel. Shape preserving local histogram modification [J]. IEEE Transactions on Image Processing,1999,8(2):220-230.
[97]T. L.Ji, M. K. Sundareshan, H. Roehrig. Adaptive image contrast enhancement based on human visual properties [J]. IEEE Transactions on Medical Imaging,1994,13(4):573-586.
[98]S.K. Pal, R.A.King. Image Enhancement Using Fuzzy Sets [J]. Electron. Lett.,1980,16(9): 376-378.
[99]杨勇,黄淑英.一种改进的Pal和King模糊边缘检测算法[J].仪器仪表学报,2008,29(9)：1918-1922.
[100]郭桂蓉等.模糊模式识别[M].长沙：国防科技大学出版社,1992.
[101]杨水超,马志峰.一种改进的模糊边缘检测快速算法[J].红外技术,2005,27(2)：139-142.
[102]贾允,丁艳,刘泽平.改进图像阈值分割算法的研究[J].光学技术,2005,31(1)：155-157.
[103]李久贤,孙伟,夏良正.一种新的模糊对比度增强算法[J].东南大学学报(自然科学版),2004,34(5)：675-677.
[104]陈书海,傅录祥.实用数字图像处理[M].北京：北京科学出版社,2005.
[105]P K Sahoo, S Soltani. Survey of thresholding techniques [J]. Computer Vision, Graphics, and Image Processing,1998,41(2):233-260.
[106]杨淑莹,边奠英.VC++图像处理程序设计(第二版)[M].北京：清华大学出版社,2007.
[107]Haralick R M, Shapiro L G. Image segmentation techniques [J]. Computer Graphics Image Processing,1985,29:100-132.
[108]刘健庄,栗文清.灰度图像的二维Otsu自动阈值分割法[J].自动化学报,1993,19(1)：101-105.
[109]Nevatia. A color edge detector and its use in scene segmentation [J]. IEEE Transactions on Systems, Man and Cybenetics,1997,7(11):820-826.
[110]王伟智,刘秉瀚,施作霖.基于HSV空间的肿瘤免疫组化阳性目标自动提取分析[J].中国体式学与图像分析,2006,11(1)：13-17.
[111]冈萨雷斯.数字图像处理[M].北京：电子工业出版社,2005.
[112]徐晓燕.医学显微图像的分割研究田].黑龙江：黑龙江大学,2008.
[113]Cheng HD, Jiang XH, SunY. Color image Segmentation:advances and prospects [J]. Pattern Recognition,2001,34(12):2259-2281.
[114]Chatzis V. A generalized fuzzy mathematical morphology and its application in robust 2D and 3D object representation [J]. IEEE Transactions on Image Processing,2000,9(10): 1798-1810.
[115]CHEN Lanlan, BI Duyan. Application of Mathematical Morphology in Image Processing [J]. Modem Electronical Technology,2002,12(8):18-20.
[116]张宏林.Visual C++数字图像处理典型算法及实现(第2版)[M].北京：人民邮电出版社,2008.
[117]刘相滨.基于边界剥离的细胞图像分离算法[J].中国图象图形学报,2002,7(3)：228-232.
[118]Ruberto C D, DempstrA, Khan S. Analysis of infected blood cell images using morphologi-cal operators [J]. ELSEVIER Image and Vision Computing,2002,20(2):133-146.
[119]Huan Liu, LeiYu. Toward integrating feature seleetion algorithms for classification and clustering [J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(4):491-502.
[120]Muni D.P., Pal N.R.. Genetic Programming for simultaneous feature selection and classifier design [J].IEEE Transactions on Systems, Man and Cybernetics,2006,36(1):106-117.
[121]Giannakis G.B., Heath R.W.. Blind identification of multichannel FIR blurs and perfect image restoration [J]. IEEE Transactions on Image Proeessing,2000,9(4):1877-1896.
[122]X Li, Z Zhiying. Group direction difference chain codes for the representation of the border [J]. In Digital and Optional Shape Representation and Pattern Recognition,1988,372-376.
[123]M.K. Hu. Visual pattern recognition by moment invariants [J]. IRE Transaction Information Theory,1962,8(2):179-187.
[124]袁华,董守斌,张凌.GFO和不变矩实现基于形状的图像检索新方法[J].华南理工大学学报,2002,30(4)：60-64.
[125]李先锋.基于特征优化和多特征融合的杂草识别方法研究[D].江苏：江苏大学,2010.
[126]高尚.基于模拟退火算法的可靠性优化[J].上海航天,2002,19(2)：21-23.
[127]He Lifeng, Chao Yuyan. A run-based two-scan labeling algorithm [J]. IEEE Transactions on Image Processing,2008,17 (5):749-756.
[128]刘小英,张健.葡萄干图像长短轴快速检测算法[J].安徽农业科学,2008,36(26)：11482-11484.
[129]Jain A.K., Duin R.P.W.. Statistical pattern recognition:A Review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22 (1):4-37.
[130]边肇棋,张学工.模式识别(第二版)[M].北京：清华大学出版社,2000.
[131]M.T.Hagan, H.B.Demuth, M.Beale.神经网络设计[M].北京：机械工业出版社,2002.
[132]Samanta B. Artificial neural networks and genetic algorithms for gear fault detection [J]. Mechanical Systems and Signal Processing,2004,18 (5):1273-1282.
[133]杨淑莹.图像模式识别-VC++技术实现[M].北京：清华大学出版社,2005.
[134]D. Rumelhart, G. Hinton. Learning Internal Representations by Error Porpagation [M]. Parrallel Distributed Porcessing:MIT Press,1986.
[135]戴永伟,雷志勇.BP网络学习算法研究及其图像模式识别应用[J].计算机与现代化,2006,(11)：67-70.
[136]王旭,王宏.人工神经网络原理与应用(第二版)[M].沈阳：东北大学出版社,2007.
[137]王小平,曹立明.遗传算法—理论、应用与软件实现[M].西安：西安交通大学出版社,2002.
[138]刘冬.基于遗传算法的BP网络在医疗诊断中的应用[D].长春：吉林大学,2006.
[139]魏海坤.遗传算法原理及应用[M].北京：国防工业出版社,2005.
[140]A.D.Parkins. Genetic Programming techniques for handwritten digit recognition. Signal Porcessing [J].2004,84(12):2345-2365.
[141]Yuan C, Niemann H. Neural Networks for Appearance-based 3D Object Recognition [J]. Neuro Computing,2003,51:249-264.
[2]中国历史文化网：中国古代养蚕科学技术的发展和传播.[EB/OL].2010-07-18http://china-culture.jlmpc.cn/
[3]金琳.中国古代对蚕病症状与防治的记述[J].蚕桑通报,2001,32(2)：7-9.
[4]科技日报数字报：养蚕消毒技术课题通过鉴定.[EB/OL].2010-12-13http://www.stdaily.com
[5]杨继玲.略谈《齐民要术》中古代山东的蚕桑技术[J].管子学刊,2007,5(3)：55-58.
[6]张英利.十九世纪末二十世纪初中国对日本蚕业新科技的引进和影响[J].古今农业,2005(4)：55-60.
[7]李艳梅,李燕.传染性蚕病的综合防治措施[J].云南农业科技,2010,S1：155-156.
[8]李龙.印度蚕业发展研究[D].四川：西南大学,2008.
[9]许刚,潘丽芬.数码显微技术在微粒子病检验中的应用与研究[J].江苏蚕业,2002(1)：14-16.
[10]王雪梅.家蚕微粒子检测技术研究进展[J].广西蚕业,2006,43(2)：16-18.
[11]陈克平,徐家萍,姚勤.家蚕分子生物学研究进展[J].生物科学研究,2003,7(3)：208-213.
[12]Lathrop, Larry D. Spectral classification of motato disease severity levels [C]. Proceeding of the American Society of Photogramm Fall Tech Meet,1978,329-342.
[13]Rehkugler G E, Throop J A. Apple Sorting with machine Vision [J]. Transactions of the ASAE,1985,29(5):1388-1395.
[14]Miller B K, Delwiche M J. A color vision System for peach grading [J].Transactions of the ASAE,1989,32(4):1484-1490.
[15]Shearer S A, Payne F. A Color and defect Sorting of bell peppers using machine vision [J]. Transactions of the ASAE,1990,33(6):2045-2050.
[16]Ng H F, Wilcke W F. Machine vision evaluation of corn kernel mechanical and mold damage [J]. Transactions of ASAE,1998,41(2):415-420.
[17]郭文川,朱新华.机器视觉技术在谷物识别与分级中的研究进展[J].粮食与饲料工业,2002(6)：50-51.
[18]林开颜,吴军辉,徐立鸿.基于计算机视觉技术的水果形状分级方法[J].农业机械学报,2005,36(6)：71-74.
[19]成芳.稻种质量的机器视觉无损检测研究[D].杭州：浙江大学,2004.
[20]刘燕德,应义斌,成芳.机器视觉技术在种子纯度检验中的应用[J].农业机械学报,2003,34(5)：161-163.
[21]黎萍,朱军燕,刘燕德.机器视觉在农产品检测与分级中的应用与展望[J].江西农业大学学报,2005,27(5)：796-800.
[22]黄星弈,李剑,姜松.基于计算机视觉的稻谷品种识别技术的研究[J].江苏大学学报,2004,25(2)：102-104.
[23]张香琴.家蚕微粒子病的图像识别技术[D].江苏：江苏大学,1998.
[24]何东健.数字图像处理[M].西安：西安电子科技大学出版社,2003.
[25]赵荣椿等.数字图象处理导论[M].西安：西北工业大学出版杜,2000.
[26]傅弘,颜鸿森,齐春.基于自适应定向止交投影分解的图像分割方法[J].中国图像图形学报,2003,8(3)：286-291.
[27]王康泰,戴文战.一种基于Sobel算子和灰色关联度的图像边缘检测方法[J].计算机应用,2006,26(5)：1035-1036.
[28]郭臻,陈远知.图像阈值分割算法研究[J].中国传媒大学学报自然科学版,2008,15(2)：77-78.
[29]王广君,田金文,柳健.基于四义树结构的图像分割技术[J].红外与激光工程,2001,30(1)：12-14.
[30]屈彬,王景熙.一种基于区域生长规则的快速边缘跟踪算法[J].四川大学学报,2002,34(2)：10-14.
[31]宋淑娜.基于自适应背景区域选择的图像分割方法[D].江苏：江苏科技大学,2009.
[32]刘勃,应隽,周珑等.数字图像分割技术及其进展[J].天水师范学院学报,2007,27(5)：35-40.
[33]张博,苏永利,张书玲.一种基于区域填充的C-V模型图像分割方法[J].系统仿真学报,2008,20(19)：5228-5230.
[34]杨纶标,高英仪.模糊数学原理与应用第四版[M].广州：华南理工大学出版社,2005.
[35]M.Singh, P.Patel, D.Khosla, T.Kim. Segmeniation of funetional MRI by K-means clustering [J], IEEETrans. Nucl.Sci,1996,43(6):2030-2036.
[36]Mohamed NA, Sameh MY, Nevin M. A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data [J]. IEEE Trans.On Medical Imaging,21(3),2002: 193-199.
[37]Liew AW, Yan H. An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation [J], IEEE Trans. On Medical Imaging,2003,22(9):1063-1075.
[38]颜刚.基于模糊马尔可夫场的图像算法研究[D].广州：南方医科大学,2005.
[39]林亚忠,程跃斌,陈武凡.基于修正的分段模糊吉伯斯随机场模型的图像分割[J].计算机应用,2005,25(11)：2606-2608.
[40]陈琳.基于数学形态学的图像分割技术研究[DD].云南：昆明理工大学,2005.
[41]杨杰.数学形态学的图像分割算法[J].计算机工程与科学,1998,20(4)：21-27.
[42]杨静.基于数学形态学的图像分割研究及应用[J].仪器仪表用户,2005,12(5)：18-20.
[43]张少刚.遗传算法在计算机仿真技术中的应用[J].自动化与仪器仪表,2009,6(146)：56-57.
[44]欧萍,贺电.遗传算法粒在二维最大熵值图像分割中的应用[J].计算机仿真,2011,28(1)：294-298.
[45]何春华,胡迎春.基于改进遗传算法的自动阈值图像分割方法[J].计算机仿真,2011,28(2)：312-315.
[46]艾虎.基于计算机视觉的人工：神经网络和图像处理技术的牛肉大理石花纹自动分级研究[D].四川：四川农业大学,2009.
[47]黄健.基于人工神经网络和纹理特征的马尾松图像分割方法[D].广东：福建农林大学,2008.
[48]孙优贤,卢建刚,许锋.神经网络在图像处理中的应用[J],信息与控制,2003,32(4)：344-350.
[49]杨嘉麟,郑文岭,马文丽.基于改进的BP神经网络的血液细胞图像分割[J].微型电脑应用,2008,24(4)：4-7.
[50]耿伯英,陆建峰,杨静宇.基于模糊主色调的彩色图像分割及道路检测[J].南京理工大学学报,2000,24(4)：353-358.
[51]O'Farrel M,Lewis E,Flanagan C.Using reflection based optical fiber system and neural networks to evaluate the quality of food in a large-scale industrial oven [J].Sensors and Actuators(Physical),2004,5(2):424-433.
[52]Dooley, Karmakar, Manzur. A fuzzy rule-based colour image segmentation algorithm [C]. IEEE International Conference on Image Processing, Barcelona, Spain,2003,977-980.
[53]赵春燕,时秀芳,闫长青.图像分割综述[J].中国科技信息,2009(1)：42-43.
[54]史健芳,张富军,郝宝峰.基于小波变换和数学形态学的图像分割算法[J].太原理工大学学报,2009,40(5)：490-493.
[55]魏晋相,汪华章,何小海.基于模糊C均值聚类和数学形态学的图像分割[J].成都信息工程学院学报,2008,23(6)：618-621.
[56]王克刚,耿国华.基于小波平滑直方图的模糊聚类图像分割方法[C].图像图形技术与应用进展-第三届图像图形技术与应用学术会议论文集,2008,321-328.
[57]吴学明.图像分割的算法研究[D].四川：成都理工大学,2006.
[58]吴贵芳,徐科钢.板表面质量在线监测技术[M].北京：科学出版社,2010.
[59]宋余庆,陈健美,郭依正.基于多特征融合的医学图像识别研究[J].计算机应用研究,2008,25(6)：1750-1752.
[60]陆丽珍,刘仁义,刘南.一种融合颜色和纹理特征的遥感图像检索方法[J].中国图像图形学报,2004,9(3)：328-332.
[61]谈蓉蓉.利用颜色和形状特征的杂草识别方法研究[D].江苏：江苏大学,2009.
[62]闫小梅,刘双喜,张春庆.基于颜色特征的玉米种子纯度识别[J].农业工：程学报,2010,26(1)：46-50.
[63]Majumdar S, Jayas D S. Classification of cereal grains using machine vision [J]. Transactions of the ASAE,2000,43(6):1669-1675.
[64]周平,汪亚明,赵匀.基于颜色分量运算与色域压缩的杂草实时检测方法[J].农业机械学报,2007,38(1)：116-119.
[65]Burks T F, Shearer S A.Classification of weed species using color texture features and discriminate analysis [J]. Transaetion of the ASAE,2000,43(2):441-448.
[66]赵杰文,刘木华,杨国彬.基于HSI颜色特征的田间成熟番茄识别技术[J].农业机械学报,2004,35(5)：122-125.
[67]金飞剑.基于机器视觉的杂草图像特征提取及识别研究[D].江苏：江苏大学,2007.
[68]夏庆观,盛党红,路红.零件图像特征提取和识别的研究[J].中国机械工程,2005,16(22)：2031-2033.
[69]杨铁滨.基于机器视觉的陶瓷球表面缺陷自动检测技术研究[D].哈尔滨：哈尔滨工业大学,2007.
[70]蔡健荣,许俐.家蚕微粒子病的图象形状特征分析[J].江苏理工大学学报,1998,19(5)：24-27.
[71]郑敏江.基于数字图像处理的玉米种子质量分级方法研究[D].武汉：武汉理工大学,2009.
[72]查英,刘铁根,杜东.图像识别技术在零件装配自动识别中的应用[J].计算机工程,2006,32(10)：179-185.
[73]A.N. Rajagopalan, K. Srinivasa Rao, Y. Anoop Kumar. Face recognition using multiple facial features [J]. Pattern Recognition Letters,2007,28(3):335-341.
[74]V.B. Sunil, S.S. Pande. Automatic recognition of features from freeform surface CAD models [J]. Computer-Aided Design,2008,40(4):502-517.
[75]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4)：622-635.
[76]李虹.基于机器视觉路面状态识别关键技术研究[D].长春：吉林大学,2009.
[77]Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification [J]. IEEE Transactions on Systems, Man, and Cybernetics,1973,3(6):610-621.
[78]Soh K S, Tsatsoulis C. Texture analysis of SAR sea ice in agery using gray level coocuurrence matrices [J]. IEEE Transactions on Geoscience and Remote Sensing,1999, 37(2):780-795.
[79]Walker R F, Jackway P T, Longstaff I D. Recent developments in the use of co-occurrence matrix for texture recognition [C]. Proceedings of IEEE Conference on Digital Signal Processing, Greece,1997,1:63-65.
[80]Cross G R, Jain A K. Markov random field texture models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1983,5(1):25-39.
[81]Kapan L M, Kuo C-C. Extending self-sin ilarity for fractional brownian motion [J]. IEEE Transactions on Signal Processing,1994,42(12):3526-3530.
[82]Clausi D A, Jernigan M E. Designing Gabor filters for optimal texture separability [J]. Pattern Recognition,2000,33(11):1835-1849.
[83]Soille P. Morphological Image Analysis Principles and Applications [M]. Germany:Springer Press,2003.
[84]宋凯.基于计算机视觉的农作物病害识别方法的研究[D].沈阳：沈阳农业大学,2008.
[85]Hemming J, T Rath. Computer-vision-based weed identification under field conditions using controlled lighting [J].Transactions of the ASAE,2001,78(3):233-243.
[86]Burks T F, Shearer S A, Green J D. Influence of weed maturity levels on species classification using machine vision [J].Weed Science,2002(50):802-811.
[87]Pydipati R, Burks T F, Lee W S.Statistical and neural network classifiers for citrus disease detection using machine vision [J].Transactions of the American Society of Agricultural Engineers,2005,48(5):2007-2014.
[88]Mathanker S K, Weckler P R, Taylor R K. Canola-weed identification for machine vision based patch spraying. American Society of Agricultural and Biological Engineers (Paper Number:085134).
[89]王丽华.基于神经网络的图像识别系统的研究[D].北京：中国石油大学,2008.
[90]于杨.田间青椒图像识别系统的研究[D].哈尔滨：中国石油大学,2008.
[91]夏庆观,盛党红,路红.零件图像特征提取和识别的研究[J].中国机械工程,2005,16(22)：2031-2033.
[92]王丹.车身零部件视觉检测中摄像机标定方法的研究与应用[D].长春：吉林大学,2009.
[93]周涛,蒋芸,王勇.基于小波神经网络的医学图像分类方法[J].计算机应用,2010,30(10)：2857-2860.
[94]Turkoglu Ibrahim, Arslan Ahmet, Ilkay Erdogan. An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks[J]. Computers in Biology and Medicine,2003,33(4):319-331.
[95]王家文,李仰军.MATLAB 7.0图形图像处理[M].北京：国防工业出版社,2006.
[96]V. Caselles, J.L. Lisani, J.M. Morel. Shape preserving local histogram modification [J]. IEEE Transactions on Image Processing,1999,8(2):220-230.
[97]T. L.Ji, M. K. Sundareshan, H. Roehrig. Adaptive image contrast enhancement based on human visual properties [J]. IEEE Transactions on Medical Imaging,1994,13(4):573-586.
[98]S.K. Pal, R.A.King. Image Enhancement Using Fuzzy Sets [J]. Electron. Lett.,1980,16(9): 376-378.
[99]杨勇,黄淑英.一种改进的Pal和King模糊边缘检测算法[J].仪器仪表学报,2008,29(9)：1918-1922.
[100]郭桂蓉等.模糊模式识别[M].长沙：国防科技大学出版社,1992.
[101]杨水超,马志峰.一种改进的模糊边缘检测快速算法[J].红外技术,2005,27(2)：139-142.
[102]贾允,丁艳,刘泽平.改进图像阈值分割算法的研究[J].光学技术,2005,31(1)：155-157.
[103]李久贤,孙伟,夏良正.一种新的模糊对比度增强算法[J].东南大学学报(自然科学版),2004,34(5)：675-677.
[104]陈书海,傅录祥.实用数字图像处理[M].北京：北京科学出版社,2005.
[105]P K Sahoo, S Soltani. Survey of thresholding techniques [J]. Computer Vision, Graphics, and Image Processing,1998,41(2):233-260.
[106]杨淑莹,边奠英.VC++图像处理程序设计(第二版)[M].北京：清华大学出版社,2007.
[107]Haralick R M, Shapiro L G. Image segmentation techniques [J]. Computer Graphics Image Processing,1985,29:100-132.
[108]刘健庄,栗文清.灰度图像的二维Otsu自动阈值分割法[J].自动化学报,1993,19(1)：101-105.
[109]Nevatia. A color edge detector and its use in scene segmentation [J]. IEEE Transactions on Systems, Man and Cybenetics,1997,7(11):820-826.
[110]王伟智,刘秉瀚,施作霖.基于HSV空间的肿瘤免疫组化阳性目标自动提取分析[J].中国体式学与图像分析,2006,11(1)：13-17.
[111]冈萨雷斯.数字图像处理[M].北京：电子工业出版社,2005.
[112]徐晓燕.医学显微图像的分割研究田].黑龙江：黑龙江大学,2008.
[113]Cheng HD, Jiang XH, SunY. Color image Segmentation:advances and prospects [J]. Pattern Recognition,2001,34(12):2259-2281.
[114]Chatzis V. A generalized fuzzy mathematical morphology and its application in robust 2D and 3D object representation [J]. IEEE Transactions on Image Processing,2000,9(10): 1798-1810.
[115]CHEN Lanlan, BI Duyan. Application of Mathematical Morphology in Image Processing [J]. Modem Electronical Technology,2002,12(8):18-20.
[116]张宏林.Visual C++数字图像处理典型算法及实现(第2版)[M].北京：人民邮电出版社,2008.
[117]刘相滨.基于边界剥离的细胞图像分离算法[J].中国图象图形学报,2002,7(3)：228-232.
[118]Ruberto C D, DempstrA, Khan S. Analysis of infected blood cell images using morphologi-cal operators [J]. ELSEVIER Image and Vision Computing,2002,20(2):133-146.
[119]Huan Liu, LeiYu. Toward integrating feature seleetion algorithms for classification and clustering [J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(4):491-502.
[120]Muni D.P., Pal N.R.. Genetic Programming for simultaneous feature selection and classifier design [J].IEEE Transactions on Systems, Man and Cybernetics,2006,36(1):106-117.
[121]Giannakis G.B., Heath R.W.. Blind identification of multichannel FIR blurs and perfect image restoration [J]. IEEE Transactions on Image Proeessing,2000,9(4):1877-1896.
[122]X Li, Z Zhiying. Group direction difference chain codes for the representation of the border [J]. In Digital and Optional Shape Representation and Pattern Recognition,1988,372-376.
[123]M.K. Hu. Visual pattern recognition by moment invariants [J]. IRE Transaction Information Theory,1962,8(2):179-187.
[124]袁华,董守斌,张凌.GFO和不变矩实现基于形状的图像检索新方法[J].华南理工大学学报,2002,30(4)：60-64.
[125]李先锋.基于特征优化和多特征融合的杂草识别方法研究[D].江苏：江苏大学,2010.
[126]高尚.基于模拟退火算法的可靠性优化[J].上海航天,2002,19(2)：21-23.
[127]He Lifeng, Chao Yuyan. A run-based two-scan labeling algorithm [J]. IEEE Transactions on Image Processing,2008,17 (5):749-756.
[128]刘小英,张健.葡萄干图像长短轴快速检测算法[J].安徽农业科学,2008,36(26)：11482-11484.
[129]Jain A.K., Duin R.P.W.. Statistical pattern recognition:A Review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22 (1):4-37.
[130]边肇棋,张学工.模式识别(第二版)[M].北京：清华大学出版社,2000.
[131]M.T.Hagan, H.B.Demuth, M.Beale.神经网络设计[M].北京：机械工业出版社,2002.
[132]Samanta B. Artificial neural networks and genetic algorithms for gear fault detection [J]. Mechanical Systems and Signal Processing,2004,18 (5):1273-1282.
[133]杨淑莹.图像模式识别-VC++技术实现[M].北京：清华大学出版社,2005.
[134]D. Rumelhart, G. Hinton. Learning Internal Representations by Error Porpagation [M]. Parrallel Distributed Porcessing:MIT Press,1986.
[135]戴永伟,雷志勇.BP网络学习算法研究及其图像模式识别应用[J].计算机与现代化,2006,(11)：67-70.
[136]王旭,王宏.人工神经网络原理与应用(第二版)[M].沈阳：东北大学出版社,2007.
[137]王小平,曹立明.遗传算法—理论、应用与软件实现[M].西安：西安交通大学出版社,2002.
[138]刘冬.基于遗传算法的BP网络在医疗诊断中的应用[D].长春：吉林大学,2006.
[139]魏海坤.遗传算法原理及应用[M].北京：国防工业出版社,2005.
[140]A.D.Parkins. Genetic Programming techniques for handwritten digit recognition. Signal Porcessing [J].2004,84(12):2345-2365.
[141]Yuan C, Niemann H. Neural Networks for Appearance-based 3D Object Recognition [J]. Neuro Computing,2003,51:249-264.