基于生物形态学的赤潮藻显微图像分割与特征提取研究
|
摘要
近年来近海赤潮频发,规模不断扩大,对海洋生态环境、资源及公众健康构成了严重威胁,造成巨大的经济损失,已引起各国政府及科学界的关注和高度重视。因此,研究赤潮发生的机制,对赤潮的发生、变化、消长及灾情趋势作出监测预报从而采取相应治理措施是一项非常迫切的任务。国家从基础研究、高技术发展等不同层面开展赤潮研究工作,正着手建立业务化的赤潮自动监测体系。赤潮生物的种类和数量是决定赤潮危害程度的关键因素,而人工形态学分类存在主观性和劳动强度大等问题,因此快速有效地鉴定主要赤潮藻种是赤潮自动监测的一个重要环节。
本文以中国海常见的40种赤潮藻为研究对象,在对本课题生物形态学知识积累基础上,分门类概括了赤潮藻种的主要生物形态学特征,并以此为分类原则提出了赤潮藻形态学分类思想,设计了藻种显微图像识别系统。在分析了目前国内外已有的研究成果基础上,针对赤潮藻显微图像分割和特征提取,进行了较为深入的研究,主要工作包括：
1.藻种显微图像分割与目标提取。根据所研究40种赤潮藻生物形态学特点,将这40种赤潮藻分为无角毛类藻和角毛藻两大类,制订了藻种细胞粗分类方法。
1)结合自动闽值理论分析和实验,说明采用最小误差阈值化方法可以有效实现形状规则的无角毛类藻种图像分割；针对自动阈值法在图像分割中的缺陷,提出了一种基于多方向投影积分的自动阈值藻种细胞提取方法,该方法通过保留图像在八个方向上最大投影积分区间去除细胞体周围杂质,从而提取完整的细胞目标。
2)针对形态多变、角毛灰度信息微弱的角毛藻,提出了一种基于灰度曲面方向角模型的藻种细胞提取方法,该方法首先建立了灰度曲面的矢量化表示模型,通过将灰度曲面法线矢量分解为水平与垂直两方向上的灰度矢量映射图像消除噪声干扰,保留角毛的方向信息,结合滤波、形态学区域填充等操作实现对角毛藻细胞提取。与阈值法对比实验表明,该方法在精确提取目标的同时可更多地保留角毛信息。
2.无角毛类藻种特征提取与模式分类。重点研究了无角毛类藻种生物特征区域的提取方法,并结合藻种细胞通用形态特征和领域相关特征,优化选择建立藻种多视点形貌特征集合。
1)提出了一种快速提取藻种顶刺的形态学方法,该方法引入了像素宽度的概念,以藻种目标像素宽度直方图和面积分布为判别依据,自动判定最佳结构元尺寸。
2)提出了一种基于特征灰度和约束标记分水岭变换的横沟提取方法,针对分水岭变换存在的过分割问题,该方法利用灰度包容球获取图像特征灰度集合,通过有效降低图像中灰度级数目减少无意义的局部极小值区域,对灰度重构后的梯度图像极小值区域采用阈值法进行标记并对标记加以横沟质心、形状和面积约束,极小值标定修改梯度图后采用分水岭变换实现横沟提取。
3)提取藻种全局形状特征、纹理特征和局部形态特征建立藻种细胞生物形态特征集合,选择C-SVM采用一对一方法构建多类别分类模型,实验验证了选取特征集合的不变性和有效性,并给出识别结果。
3.角毛藻细胞目标表示与特征提取。基于骨架表征形状的能力建立骨架树模型对角毛藻细胞目标进行表示并提取其生物形态学特征。
1)提出了一种基于竞争机制的骨架层次分解方法,该方法通过定义使与脊柱基元具有一致方向性的分支基元获胜跟踪的竞争策略,消除了骨架提取中不同分支的相互影响,保证分解后脊柱基元的完整性；以分解后各基元作为节点构建骨架树获取角毛藻目标的表示形式,该树的层次和节点间的连接关系反映了目标的拓扑性质。
2)针对角毛藻目标具有的生物形态特征,最终建立骨架树的拓扑结构差异和几何特征差异作为描述角毛藻细胞的特征集合,并将目标中特征提取的问题转化为骨架树距离求解过程,建立了对分类角毛藻显微图像有效的相似性度量。
In recent years, more and more frequent HABs(harmful algae blooms) have posed serious threats on coastal environment, marine resources and public health. It is a grievous global marine disaster causing billions of economic loss every year in China. Governments and the scientific community are concerned with this situation and pay much attention to this issue. Artificial observation and analysis cannot satisfy the prediction of red tide due to the limitation of their efforts and biological knowledge. It is thus very urgent to study the methods of warning, forecasting red tide and establish operational monitoring system. It should be noted that identifying the dominant species of red tide plays an important role in automatic monitoring of red tide.
On the sum-up of 40 algae species in the coastal waters of China Sea, and the analysis of their biological characteristics, the following conclusions are gotten:shape, cingulum, spine, seta, etc. are the dominant biological characteristics which can be utilized to recognize these species. Taking these biological characters into account, the micro-images recognition frame is designed.
1. Image segmentation is a necessary pretreatment step in many target recognition applications. A coarse classification scheme is presented according to several characteristics of micro-images such as noises and poor constrast and so on.
1) Minimum error thresholding is proved to be suitable for algae without seta by theorization and experiments. Aiming at the defect of thresholding methods, a target extraction method based on thresholding and projection intergal on multiple directions is proposed. The noises are removed by searching for the largest integral and seting other lesser integral zero. The results show that the approach proposed can extract cell object exactly.
2) According to the specific problem of micro-image of Chaetoceros, the orientation angle model of gray image is established, in which seta components are reserved by decomposing the orientation angle vector into two gray images on X and Y axises. Then combining the filtering and morphological operations, Chaetoceros image segmentation is realized. The results show that the method outperfom thresholding as majority of seta components are extracted.
2. This thesis focuses on biological features extraction based on biological characters of algae without seta. And then feature set is selected and established by combining the universal with domain-correlative characters.
1) A method for extracting spine feature based on mathematical morphology is proposed, in which the pixel-width is introduced and the optimal structure element is selected automaticly by pixel-width histogram and area distribution.
2) To tackle the over-segmentation problem in watershed algorithm, a method based on dominant gray levels and constraint marker watershed is proposed to extract cingulum region. In this algorithm, original image is reconstructed by dominant gray levels, eliminating local minima and noise disturber. Then markers of reginal minima are extracted from gradient image by using threshold, and imposed by shape, area and centroid constraints. The watershed transformation of the maker-modified gradient image is performed to achieve the cingulum feature extraction.
3) Besides, after global shape features, texture features and domain specific features are analysised and extracted, C-SVM classifer is designed by "one-against-one" approach, recognition results of 15 species of algae without seta are received.
3. This thesis deals with the research on Chaetoceros object representation and feature extraction based on skeleton. The skeleton tree is used to represent the Chaetoceros and geometrical features are extracted from it based on skeleton theory.
1) A skeleton hierarchical decomposition approach based on competitive mechanism is advanced, in which the competitive mechanism is defined as the branch with the consistent direction with rachis element succeeds to trace, guaranteeing the rachis element integrity. The Chaetoceros object is represented by attributed tree by forming the rachis elements and branches into it, and the hierarchy of the tree and the connection relations of the nodes reflect the topological characteristics of skeleton.
2) Considering the geometric characters of Chaetoceros object, combining the topological difference and geometric difference as the feature set, the similarity measurement suitable for micro-images of Chaetoceros is established.
本文以中国海常见的40种赤潮藻为研究对象,在对本课题生物形态学知识积累基础上,分门类概括了赤潮藻种的主要生物形态学特征,并以此为分类原则提出了赤潮藻形态学分类思想,设计了藻种显微图像识别系统。在分析了目前国内外已有的研究成果基础上,针对赤潮藻显微图像分割和特征提取,进行了较为深入的研究,主要工作包括：
1.藻种显微图像分割与目标提取。根据所研究40种赤潮藻生物形态学特点,将这40种赤潮藻分为无角毛类藻和角毛藻两大类,制订了藻种细胞粗分类方法。
1)结合自动闽值理论分析和实验,说明采用最小误差阈值化方法可以有效实现形状规则的无角毛类藻种图像分割；针对自动阈值法在图像分割中的缺陷,提出了一种基于多方向投影积分的自动阈值藻种细胞提取方法,该方法通过保留图像在八个方向上最大投影积分区间去除细胞体周围杂质,从而提取完整的细胞目标。
2)针对形态多变、角毛灰度信息微弱的角毛藻,提出了一种基于灰度曲面方向角模型的藻种细胞提取方法,该方法首先建立了灰度曲面的矢量化表示模型,通过将灰度曲面法线矢量分解为水平与垂直两方向上的灰度矢量映射图像消除噪声干扰,保留角毛的方向信息,结合滤波、形态学区域填充等操作实现对角毛藻细胞提取。与阈值法对比实验表明,该方法在精确提取目标的同时可更多地保留角毛信息。
2.无角毛类藻种特征提取与模式分类。重点研究了无角毛类藻种生物特征区域的提取方法,并结合藻种细胞通用形态特征和领域相关特征,优化选择建立藻种多视点形貌特征集合。
1)提出了一种快速提取藻种顶刺的形态学方法,该方法引入了像素宽度的概念,以藻种目标像素宽度直方图和面积分布为判别依据,自动判定最佳结构元尺寸。
2)提出了一种基于特征灰度和约束标记分水岭变换的横沟提取方法,针对分水岭变换存在的过分割问题,该方法利用灰度包容球获取图像特征灰度集合,通过有效降低图像中灰度级数目减少无意义的局部极小值区域,对灰度重构后的梯度图像极小值区域采用阈值法进行标记并对标记加以横沟质心、形状和面积约束,极小值标定修改梯度图后采用分水岭变换实现横沟提取。
3)提取藻种全局形状特征、纹理特征和局部形态特征建立藻种细胞生物形态特征集合,选择C-SVM采用一对一方法构建多类别分类模型,实验验证了选取特征集合的不变性和有效性,并给出识别结果。
3.角毛藻细胞目标表示与特征提取。基于骨架表征形状的能力建立骨架树模型对角毛藻细胞目标进行表示并提取其生物形态学特征。
1)提出了一种基于竞争机制的骨架层次分解方法,该方法通过定义使与脊柱基元具有一致方向性的分支基元获胜跟踪的竞争策略,消除了骨架提取中不同分支的相互影响,保证分解后脊柱基元的完整性；以分解后各基元作为节点构建骨架树获取角毛藻目标的表示形式,该树的层次和节点间的连接关系反映了目标的拓扑性质。
2)针对角毛藻目标具有的生物形态特征,最终建立骨架树的拓扑结构差异和几何特征差异作为描述角毛藻细胞的特征集合,并将目标中特征提取的问题转化为骨架树距离求解过程,建立了对分类角毛藻显微图像有效的相似性度量。
In recent years, more and more frequent HABs(harmful algae blooms) have posed serious threats on coastal environment, marine resources and public health. It is a grievous global marine disaster causing billions of economic loss every year in China. Governments and the scientific community are concerned with this situation and pay much attention to this issue. Artificial observation and analysis cannot satisfy the prediction of red tide due to the limitation of their efforts and biological knowledge. It is thus very urgent to study the methods of warning, forecasting red tide and establish operational monitoring system. It should be noted that identifying the dominant species of red tide plays an important role in automatic monitoring of red tide.
On the sum-up of 40 algae species in the coastal waters of China Sea, and the analysis of their biological characteristics, the following conclusions are gotten:shape, cingulum, spine, seta, etc. are the dominant biological characteristics which can be utilized to recognize these species. Taking these biological characters into account, the micro-images recognition frame is designed.
1. Image segmentation is a necessary pretreatment step in many target recognition applications. A coarse classification scheme is presented according to several characteristics of micro-images such as noises and poor constrast and so on.
1) Minimum error thresholding is proved to be suitable for algae without seta by theorization and experiments. Aiming at the defect of thresholding methods, a target extraction method based on thresholding and projection intergal on multiple directions is proposed. The noises are removed by searching for the largest integral and seting other lesser integral zero. The results show that the approach proposed can extract cell object exactly.
2) According to the specific problem of micro-image of Chaetoceros, the orientation angle model of gray image is established, in which seta components are reserved by decomposing the orientation angle vector into two gray images on X and Y axises. Then combining the filtering and morphological operations, Chaetoceros image segmentation is realized. The results show that the method outperfom thresholding as majority of seta components are extracted.
2. This thesis focuses on biological features extraction based on biological characters of algae without seta. And then feature set is selected and established by combining the universal with domain-correlative characters.
1) A method for extracting spine feature based on mathematical morphology is proposed, in which the pixel-width is introduced and the optimal structure element is selected automaticly by pixel-width histogram and area distribution.
2) To tackle the over-segmentation problem in watershed algorithm, a method based on dominant gray levels and constraint marker watershed is proposed to extract cingulum region. In this algorithm, original image is reconstructed by dominant gray levels, eliminating local minima and noise disturber. Then markers of reginal minima are extracted from gradient image by using threshold, and imposed by shape, area and centroid constraints. The watershed transformation of the maker-modified gradient image is performed to achieve the cingulum feature extraction.
3) Besides, after global shape features, texture features and domain specific features are analysised and extracted, C-SVM classifer is designed by "one-against-one" approach, recognition results of 15 species of algae without seta are received.
3. This thesis deals with the research on Chaetoceros object representation and feature extraction based on skeleton. The skeleton tree is used to represent the Chaetoceros and geometrical features are extracted from it based on skeleton theory.
1) A skeleton hierarchical decomposition approach based on competitive mechanism is advanced, in which the competitive mechanism is defined as the branch with the consistent direction with rachis element succeeds to trace, guaranteeing the rachis element integrity. The Chaetoceros object is represented by attributed tree by forming the rachis elements and branches into it, and the hierarchy of the tree and the connection relations of the nodes reflect the topological characteristics of skeleton.
2) Considering the geometric characters of Chaetoceros object, combining the topological difference and geometric difference as the feature set, the similarity measurement suitable for micro-images of Chaetoceros is established.
引文
[1]邹景忠.赤潮生物与赤潮灾害研究.见：曾呈奎,编.中国海洋科学研究及开发.青岛：青岛出版社,1992：284-287
[2]华泽爱.赤潮灾害.北京：海洋出版社,1994
[3]周为峰,樊伟.应用MODIS进行赤潮遥感监测的研究进展.遥感技术与应用,2007,22(6)： 768-772
[4]姜国建.对比研究中国和美国的海洋灾害预报机制管理体制.海洋开发与管理,2006,6： 30-34
[5]周名江,朱明远.我国近海有害赤潮发生的生态学、海洋学机制及预测防治研究进展.地球科学进展,2006,21(7)：673-679
[6]邹景忠.赤潮灾害.见：曾呈奎,编.中国海洋志.河南：大象出版社,2003：802-826
[7]苏纪兰.中国的赤潮研究.中国科学院院刊,2001(5)：339-342
[8]丛丕福,张丰收,曲丽梅.赤潮灾害监测预报研究综述.灾害学,2008,23(2)：127-130
[9]俞志明.赤潮灾害的预防与治理.北京：科学出版社.1994
[10]王修林,孙培艳,高振会等.中国有害赤潮预测方法研究现状和进展.海洋科学进展,2003,21(1)：93-98
[11]梁松,钱宏林,齐雨藻.中国沿海的赤潮问题.生态科学,2000,19(4)：44-50
[12]冯晨,姬光荣.基于分形维数的中国海常见浮游植物细胞图像特征提取：[博士学位论文].青岛：中国海洋大学,2007
[13]高亚辉,杨军霞,骆巧琦等.海洋浮游植物自动分析和识别技术.厦门大学学报(自然科学版),2006,45(S2)：40-45
[14]高亚辉,罗金飞,骆巧琦等.数学形态学在海洋浮游植物显微图像处理中的应用.厦门大学学报(自然科学版),2008,47(S2)：242-245
[15]齐雨藻.中国沿海赤潮.北京：科学出版社,2003
[16]GEOHAB. Global Ecology and Oceanography of Harmful Algal Blooms science plan. Baltimore and Paris:SCOR and IOC,2001:86
[17]Anderson D.M. Turning back the harmful red tide. Nature,1997, (388):513-514
[18]吕颂辉,齐雨藻.中国的赤潮、危害、成因和防治.见：张利民,编.中国赤潮研究与防治.北京：海洋出版社,2005：1-7
[19]胡国成.我国沿海赤潮发生的原因及危害.中国水产,2006,(2)：73-74,80
[20]周名江,朱明远,张经.中国赤潮的发生趋势和研究进展.生命科学,2001,13(2)：54-59
[21]江天久,佟蒙蒙,齐雨藻.赤潮的分类分级标准及预警色设置.生态科学,2006,26(6)：2035-2040
[22]潘克厚,姜广信.有害藻华(HAB)的发生、生态学影响和对策.中国海洋大学学报(自然科学版),2004,34(5)：781-786
[23]郑海永.基于生物形态学的有害赤潮显微图像诊断研究：[博士学位论文].青岛：中国海洋大学电子系.2009
[24]FJR Taylor. The taxonomy and relationships of red tide dinoflagellates. In:Anderson DM, White AW, Baden DG (eds). Toxic Dinoflagellates. Elsevier, New York.1985:11-26
[25]AD Cembella, FJR Taylor. Electrophoretic variability within the Protogonyaulax tamarensis/catenella species complex:red tide dinoflagellates. Biochemical Systematics and Ecology,1986,15:171-186
[26]Sako, Y. Isozyme and cross analysis of mating populations in the Alexandrium catenella/tamarense species complex. In:Graneli E, Sunderstrom E, Edler, et al., (eds). Proceedings of Toxic Marine Phytoplankton. New York:Elsevier,1990:87-93
[27]Kirkpatrick G J,.Millie D E, Moline M A, et al Optical discrimination of a phytoplankton species in natural mixed populations. Limnol Oceanogr,2000,45(2):467-471
[28]李继刚,王世忠,高志等.藻类和悬浮物的光谱识别研究.高技术通讯,2000,(7)：68-71
[29]Cowles T J,Desiderio R A.Neuer S. In situ characterization of phytoplankton from vertical profiles of fluorescence emission spectra. Marbiol,1993,115:217-222.
[30]Seppaelae J,Balode M. The use of spectral fluorescence methods to detect changes in the phytoplankton community. Hydrobiologia,1998,363(1/3):207-217.
[31]张前前,类淑河,王修林等.浮游植物活体三维荧光光谱分类判别方法研究.光谱学与光谱分析,2004,24(10)：1227-1229
[32]Furuya K, HayashiM, Yabushita Y, et al Phytop lanktondynamics in the East China Sea in spring and summer as revealed by HPLC2 derived pigment signatures. Deep Sea Research Part II Topical Studies in Oceanography.2003,50(2):367-387.
[33]王海黎,洪华生,徐立.反相高效液相色谱法分离、测定海洋浮游植物的叶绿素和类胡萝卜素.海洋科学,1999,4：6-9
[34]姚鹏,于志刚,米铁柱.海洋浮游藻类的化学分类法.海洋环境科学,2003,22(1)：75-80
[35]Balfootr H W,Snoek J, Smiths J R M, et al Automatic identification of algae:neural network analysis of flow cytometric data. J Plankton Res,1992,14(4):575-589
[36]焦念志,杨燕辉.四类海洋超微型浮游生物的同步监测.海洋与湖沼,1999,30(5)：506-511
[37]张利华,张经,晁敏.流式细胞术对微微型浮游植物识别初探.海洋科学,2002,26(3)：60-65
[38]Asai R, Matsukawa R, lkebukuro K, Highly sensitive chemiluminescence flow-injection detection of the red tide phytoplankton Heterosigma carterae. Ana Chimi Acta,1999, 390(123):237-244
[39]Scholin C A,Marin R,Miller P E, et al DNA probes and a receptor-binding assay for detection of Pseudo-nitzschia (Bacillariophyceae) species and domoic acid activity in cultured and natural samples. J Phycol,1999:1356-1367.
[40]Scholin C A, Anderson D M. Two distinct small subunit ribosomal RNA genes in the north American toxic dinoflagellate Alexandrium fundyense (Dinophyceae). Journal of Phycology,1993,29:209-216
[41]Scholin C A, Anderson D M. Identification of group-and strain specific genetic markers for globally distributed Alexandrium (Dinophyceae). I:RFLP analysis of SSU rRNA genes. Journal of Phycology,1994,30(4):744-754.
[42]Scholin C A, Anderson D M. LSU rDNA-based assays for discriminating species and strains of Alexandrium (Dinophyceae). Journal of Phycology,1996,32:1022-1035.
[43]http://www.algaebase.org
[44]http://diatom.acnatsci.org/AlgaeImage/
[45]http://www.shigen.nig.ac.jp/algae/
[46]http://brim.ihb.ac.cn/08/CN/08.asp
[47]http://algaebase.oicp.net/
[48]高华,梁君荣,高亚辉.我国沿海常见浮游植物检索数据库的建立.厦门大学学报(自然科学版),2006,45(S)：230-233
[49]Jeffries H.P, Berman M.S, Katsinis et al. Automated sizing and counting and identification of zooplankton by pattern recognition. Marine Biology,1984,78:329-334
[50]H du Buf and MM Bayer. Automatic Diatom Identification. World Scientific, Series in Machine Perception and Artificial Intelligence,2002,51:316.
[51]Andrei C. Jalba, Michael H. F. Wilkinson, et al Automatic diatom identification using contour analysis by morphological curvature scale spaces. Machine Vision and Applications, 2005,16(4):217-227
[52]ADIAC:http://rbg-web2.rbge.org.uk/ADIAC/db/adiacdb.htm
[53]Hicks Y, Marshall D, Martin R R, et al. Automatic landmarking for building biological shape models. Proceedings of IEEE International Conference on Image Processing, 2002:801-804
[54]Culverhouse P F, Simpson R G, Ellis R, et al. Automatic classification of field collected dinoflagellates by artificial neural network. Marine Ecology Progress Serries,1996,139: 281-287.
[55]Davis, C.S, Fredrik T, et al. A three-axis fast-tow digital Video Plankton Recorder for rapid surveys of plankton taxa and hydrography. American Society of Limnology and Oceanography:Methods 3,2005:59-74
[56]Davis, C.S., Gallager, S.M., Slow, A.R. Microaggregations of Ocean Plankton Observed by Towed Video Microscopy. Science,1992,257:230-232
[57]Qiao Hu, Davis, C.S. Automatic plankton image recognition with co-occurrence matrices and Support Vector Machine. Marine Ecology Progress Series.2005,295:21-31
[58]Tang X, Stewart W K, Huang H, et al. Automatic plankton image recognition. Artificial Intelligence Review,1998,12:177-199
[59]Tang X, Lin F, Andrew Remsen. Binary plankton image classification. IEEE Journal of Oceanic Engineering,2006,31(3):728-735.
[60]Luo T, Kramer K, Goldgof D B, et al. Recognizing plankton images from the shadow image particle profiling evaluation recorder. IEEE Transactions on System, Man and Cybernetics,2004,34:2423-2433.
[61]Pech-Pacheco J L, Alvarez-Borrego J. Optical-digital system applied to the identification of five phytoplankton species. Marine Biology,1998,132:357-365
[62]Pech-Pacheco J L, Alvarez-Borrego J, et al. Identification of a red tide blooming species through an automatic optical-digital system. Proceedings of Algorithms and Systems for Optical Information Processing V, Optics and Imaging Systems. San Diego,CA, USA, 2001,4471:243-250
[63]See Jason H, Campbell Lisa, et al. Combining new technologies for determination of phytoplankton community structure in the northern gulf of mexico. Journal of phycology, 2005,41:305-310
[64]Embleton K V, Gibson C E, Heaney S I. Automated counting of phytoplankton by pattern recognition:a comparison with a manual counting method. Journal of Plankton Research, 2003,25:669-681
[65]Rodenacker, K,Gais, P,Jutting, U et al. Semi-Automatic Recognition of Microorganisms in Water. Proceedings 2001 International Conference on, Thessaloniki, Greece,2001,3:30-33
[66]Forero-Vargas M G,Alvarado J E, Luna-Tamayo A. Automatic diatom recognition on digital images. Proceedings of Applications of Digital Image Processing XXV, volume 4790 of Image Classification. Seattle, WA, USA,2002,133-142
[67]戴君伟,王博亮,谢杰镇等.海洋赤潮生物图像实时采集系统,高技术通讯.2006,16(12)： 1316-1320
[68]郑少平,谢杰镇,王博亮等.基于形状特征描述子的赤潮优势种识别研究.厦门大学学报(自然科学版),2009,48(5)：676-679
[69]Luo Jinfei, Luo Qiaoqi, Yang Chenhui. Towards a computer-aided identification system for marine phytoplankton images.2008(涉密)
[70]赵文仓,姬光荣,周立俭等.浮游植物细胞图像识别方法的研究.计算机工程,2005,31(24)：143-144,155
[71]程军娜,姬光荣,冯晨.基于数学形态学的藻细胞图像预处理.中国海洋大学学报, 2008,38(3)：513-516
[72]周立俭,姬光荣,冯晨.基于多小波的浮游植物细胞图像边缘检测方法.通信技术,2008,41(7)：242-243,246
[73]张磊,王学民,王明时.基于图像处理技术的赤潮生物自动识别.仪器仪表学报,2003,24(S4)： 369-370
[74]王学民,张磊,王明时.图像处理技术在赤潮生物自动识别中的应用.计算机辅助设计与图形学学报,2004,16(2)：158-162
[75]王明时,王学民,张磊.显微图像分析技术在赤潮生物识别中的应用.天津大学学报,2004,37(5)：392-395
[76]曹洪宝,王学民.基于双光谱有毒赤潮优势藻图像分析的研究：[硕士学位论文].天津：天津大学,2005
[77]孙勇,王学民.基于双光谱有毒赤潮藻显微图像自动识别系统的研究：[硕士学位论文].天津：天津大学,2007
[78]程兆第,高亚辉.Mike Dickman硅藻彩色图集合.北京：海洋出版社,1996：120,101图版
[79]郭皓,王健国,易晓蕾等.中国近海赤潮生物图谱.北京：海洋出版社,2004
[80]郭玉洁,钱树本.中国海藻志.第五卷.硅藻门.北京：科学出版社,2003
[81]杨世民,董树刚.中国海域常见浮游硅藻图谱.青岛：中国海洋大学出版社,2006
[82]章毓晋.图像分割.北京：科学出版社,2001
[83]Gonzalez R C, Woods R E. Digital Image Processing.3rd. ed. Addison-Wesley,1992
[84]罗西平,田捷等.图像分割方法综述.模式识别与人工智能,1999,12(3)：300-312
[85]Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging,2004,13(1):146-165
[86]T.W.Ridler, S.Calvard. Picture threshold Picture thresholding using an iterative selection method. IEEE Transsactions on Systems, Man and Cybern,1978, SMC-8:630-632
[87]Otsu N. A threshold selection method from gray-level histograms. IEEE Transsactions on Systems, Man and Cybern,1979,SMC-9(1):62-66
[88]J.Kittler, J. Illingworth. Minimum error thresholding. Pattern Recognition,1986,19:41-47
[89]边肇祺,张学工等.模式识别.北京：清华大学出版社.2001
[90]Serra J. Image Analysis and Mathematical Morphology. Academic Press, London,1982
[91]崔屹.数学形态学方法及应用.北京：科学出版社,2000
[92]LA Ruiz, E Molto et al. Location and characterization of the stem-calyx area on oranges by computer vision. Journal of Agricultural Engineering,1996,64:165-172
[93]N Sarkar, RR Wolfe. Feature extraction techniques for sorting tomatoes by computer vision. Transactions of the ASAE,1985,28(3):970-974
[94]Q S Yang. Machine vision for Fruit Blemish Detection:[PhD Thesis]. U K:Cranfield University Silsoe Campus,1995
[95]P. Soille. Morphological Image Analysis:Principles and Applications. Second edition. Springer-Verlag.2008
[96]Vincent. L, Soille, P. Watershed in digital space:An efficient algorithm based immersion simulations. IEEE Trans on Pattern Analysis & Machine Intelligence,1991,13(6):583-598
[97]X Wu. Adaptive split-and-megre segmentation based on piecewise least-square approximation. IEEE Transactions on Pattern Analysis & Machine Intelligence,1993, 15(8):808-815
[98]N. Malpica, J.E.Ortuno, A. Santos. A multichannel watershed-based algorithm for supervised texture segmentation. Pattern Recognition Letters.2003,24:1545-1554
[99]K. Haris, S.N.Efstratiadis, N. Maglaveras, et al. Hybrid image segmentation using watersheds and fast region merging. IEEE Transactions on Imge Processing. 1998,7(12):1684-1699
[100]马东,程敬之,李斌.细胞图像的彩色纹理分析方法研究.西安交通大学学报,2000,34(1)：108-110
[101]章毓晋.基于内容的视觉信息检索.北京：科学出版社,2003
[102]Kenneth R.Castleman. Digital image Processing(Second Edition). Publishing House of Electronics Industry,2005,409-415
[103]龚声蓉,刘纯平,王强等.数字图像处理与分析.北京：清华大学出版社.2006
[104]王铌.海洋浮游生物数字图像处理方法：[硕士学位论文].青岛：中国海洋大学.2006
[105]Hu M.K.Visual pattern recognition by moment invariants. IRE Transaction Information Theory,1962,8(2):179-187
[106]葛晓青.图像检索中纹理特征提取的研究：[硕士学位论文].哈尔滨：哈尔滨理工大学.2005
[107]R.M.Haralick, K.Shanmugam, et al. Texture Features for Image Classification. IEEE Transaction. On Systems, Man and Cybernetics,1973, SMC-3(6):610-621
[108]R.M.Haralick. Statistical and structural approaches to texture. Proceedings of the IEEE, 1979,67:786-804
[109]T.R.Reed, J.M.H. du Buf. A review of recent texture segmentation and feature extraction techniques. CVGIP:Image Understanding,1993,57(3):359-372
[110]IT Jolliffe. Principal component analysis. New York:Springer,1986
[111]V.Vapnik. The nature of statistics learning theory. New York:Springer Verlag,1995
[112]E Osuna, R Freund, F Girosi. An improved training algorithm for support vector machines. In proceedings of 1997 IEEE workshop on Neural Networks for Signal Processing. 1997:276-285
[113]E Osuna, R Freund, F Girosit. Training support vector machines:an application to face detection. Proceedings of CVPR'97, New York,NY,IEEE,1997:130-136
[114]T Joachims. Text categorization with support vector machines. Technical report 23, University of Dortmund, German,1997
[115]T Joachims. Text categorization with support vector machines:learning with many relevant features. Machine Learning:ECML-98,1998:137-142
[116]C Bahlmann, B Haasdonk, H Burkhardt. Online handwriting recognition with support vector machines-a kernel approach. In Proceedings 8th Int. Workshop on Frontiers in Handwriting Recognition,2002:49-54
[117]V.Vapnik. Statistical learning theory. New York:J.Wiley,1998
[118]Chih-Chung Chang and Chih-Jen Lin. LIBSVM:a library for support vector machines, 2001. Software available at http://www.csie.ntu.edu.tw/～cjlin/libsvm
[119]BE Boser, IM Guyon, VN Vapnik. A training algorithm for optimal margin classifiers. Proceedings of the fifth annual workshop on Computational Learning Theory, ACM Press, 1992:144-152
[120]车武军,杨勋年,汪国昭.动态骨架算法.软件学报.2003,14(4)：818-823
[121]H Blum. A transformation for extracting new descriptors of shape. Models for the perception of speech and visual form. Cambridge, Mass:MIT Press,1967
[122]H Blum. Biological shape and visual science (Part Ⅰ). Journal of Theoretical Biology, 1973,38:205-287
[123]JW Brandt. Convergence and continuity criteria for discrete approximations of the continuous planar skeleton. CVGIP:Image Understanding,1994,59(1):116-124
[124]刘俊义.基于对称性的目标描述和识别技术：[博士学位论文].长沙：国防科学技术大学.2001
[125]DT Lee. Medial axis transformation of a planar shape. IEEE Transactions on Pattern Analysis and Machine and Intelligence,1982,4(4):363-369
[126]D Shaked, AM Bruckstein. The curve axis. Computer vision and image understanding, 1996,63(2):367-378
[127]RL Ogniewicz, O Kubler. Hierarchic voronoi skeletons. Pattern Recognition,1995, 28(3):343-359
[128]廖志武.2-D骨架提取算法研究进展.四川师范大学学报(自然科学版).2009,32(5)： 676-688
[129]Rosenfield A, Pfaltz J. Sequential operations in digital picture processing. Journal of association for computing machinery,1966,13(4):471-494
[130]H. Talbot, L. Vincent. Euclidean skeletons and conditional bisectors. Visual Communi-cations and Image Processing'92,1992:862-876
[131]刘宏申.击中击不中变换在笔画细化中的应用.安徽工业大学学报.2002,19(3)：251-253
[132]刘志敏,杨杰,施鹏飞.数学形态学的细化算法.上海交通大学学报,1998,32(9)：15-19
[133]陈晓飞.基于骨架的目标表示和识别技术：[博士学位论文].长沙：国防科学技术大学.2004
[134]Ablameyko S.V, Arcelli C, Baja G.S.D. Hierarchical decomposition of distance labeled skeletons. International journal pattern recognition and artificial intelligence,1996, 10(8):957-970
[135]徐钢锋,王平等.基于骨架特征的机场主跑道识别.红外与激光工程,2006,36(6)：717-721
[136]蔡自兴,成浩.一种基于骨架特征和神经网络的手写体字符识别技术.计算机技术与自动化,2001,20(3)：59-65
[137]宋婷,刘文予等.基于骨架树的线性骨架拓扑相似性度量算法.红外与激光工程,2005,34(1)：74-79
[138]刘文予,刘俊涛.基于骨架树描述符匹配的物体相似性度量方法.红外与毫米波学报,2005,24(6)：432-436
[139]陈晓飞,王润生.目标骨架的多尺度树表示.计算机学报,2004,27(11)：1540-1545
[140]王飞,张树生等.拓扑和形状特征相结合的三维模型检索.计算机辅助设计与图形学学报,2008,20(1)：99-103
[141]K Siddiqi, A Shokoufandeh, SJ Dickinson, et al. Shock Graphs and Shape Matching. International Journal of Computer Vision,1999,35(1):13-32
[2]华泽爱.赤潮灾害.北京：海洋出版社,1994
[3]周为峰,樊伟.应用MODIS进行赤潮遥感监测的研究进展.遥感技术与应用,2007,22(6)： 768-772
[4]姜国建.对比研究中国和美国的海洋灾害预报机制管理体制.海洋开发与管理,2006,6： 30-34
[5]周名江,朱明远.我国近海有害赤潮发生的生态学、海洋学机制及预测防治研究进展.地球科学进展,2006,21(7)：673-679
[6]邹景忠.赤潮灾害.见：曾呈奎,编.中国海洋志.河南：大象出版社,2003：802-826
[7]苏纪兰.中国的赤潮研究.中国科学院院刊,2001(5)：339-342
[8]丛丕福,张丰收,曲丽梅.赤潮灾害监测预报研究综述.灾害学,2008,23(2)：127-130
[9]俞志明.赤潮灾害的预防与治理.北京：科学出版社.1994
[10]王修林,孙培艳,高振会等.中国有害赤潮预测方法研究现状和进展.海洋科学进展,2003,21(1)：93-98
[11]梁松,钱宏林,齐雨藻.中国沿海的赤潮问题.生态科学,2000,19(4)：44-50
[12]冯晨,姬光荣.基于分形维数的中国海常见浮游植物细胞图像特征提取：[博士学位论文].青岛：中国海洋大学,2007
[13]高亚辉,杨军霞,骆巧琦等.海洋浮游植物自动分析和识别技术.厦门大学学报(自然科学版),2006,45(S2)：40-45
[14]高亚辉,罗金飞,骆巧琦等.数学形态学在海洋浮游植物显微图像处理中的应用.厦门大学学报(自然科学版),2008,47(S2)：242-245
[15]齐雨藻.中国沿海赤潮.北京：科学出版社,2003
[16]GEOHAB. Global Ecology and Oceanography of Harmful Algal Blooms science plan. Baltimore and Paris:SCOR and IOC,2001:86
[17]Anderson D.M. Turning back the harmful red tide. Nature,1997, (388):513-514
[18]吕颂辉,齐雨藻.中国的赤潮、危害、成因和防治.见：张利民,编.中国赤潮研究与防治.北京：海洋出版社,2005：1-7
[19]胡国成.我国沿海赤潮发生的原因及危害.中国水产,2006,(2)：73-74,80
[20]周名江,朱明远,张经.中国赤潮的发生趋势和研究进展.生命科学,2001,13(2)：54-59
[21]江天久,佟蒙蒙,齐雨藻.赤潮的分类分级标准及预警色设置.生态科学,2006,26(6)：2035-2040
[22]潘克厚,姜广信.有害藻华(HAB)的发生、生态学影响和对策.中国海洋大学学报(自然科学版),2004,34(5)：781-786
[23]郑海永.基于生物形态学的有害赤潮显微图像诊断研究：[博士学位论文].青岛：中国海洋大学电子系.2009
[24]FJR Taylor. The taxonomy and relationships of red tide dinoflagellates. In:Anderson DM, White AW, Baden DG (eds). Toxic Dinoflagellates. Elsevier, New York.1985:11-26
[25]AD Cembella, FJR Taylor. Electrophoretic variability within the Protogonyaulax tamarensis/catenella species complex:red tide dinoflagellates. Biochemical Systematics and Ecology,1986,15:171-186
[26]Sako, Y. Isozyme and cross analysis of mating populations in the Alexandrium catenella/tamarense species complex. In:Graneli E, Sunderstrom E, Edler, et al., (eds). Proceedings of Toxic Marine Phytoplankton. New York:Elsevier,1990:87-93
[27]Kirkpatrick G J,.Millie D E, Moline M A, et al Optical discrimination of a phytoplankton species in natural mixed populations. Limnol Oceanogr,2000,45(2):467-471
[28]李继刚,王世忠,高志等.藻类和悬浮物的光谱识别研究.高技术通讯,2000,(7)：68-71
[29]Cowles T J,Desiderio R A.Neuer S. In situ characterization of phytoplankton from vertical profiles of fluorescence emission spectra. Marbiol,1993,115:217-222.
[30]Seppaelae J,Balode M. The use of spectral fluorescence methods to detect changes in the phytoplankton community. Hydrobiologia,1998,363(1/3):207-217.
[31]张前前,类淑河,王修林等.浮游植物活体三维荧光光谱分类判别方法研究.光谱学与光谱分析,2004,24(10)：1227-1229
[32]Furuya K, HayashiM, Yabushita Y, et al Phytop lanktondynamics in the East China Sea in spring and summer as revealed by HPLC2 derived pigment signatures. Deep Sea Research Part II Topical Studies in Oceanography.2003,50(2):367-387.
[33]王海黎,洪华生,徐立.反相高效液相色谱法分离、测定海洋浮游植物的叶绿素和类胡萝卜素.海洋科学,1999,4：6-9
[34]姚鹏,于志刚,米铁柱.海洋浮游藻类的化学分类法.海洋环境科学,2003,22(1)：75-80
[35]Balfootr H W,Snoek J, Smiths J R M, et al Automatic identification of algae:neural network analysis of flow cytometric data. J Plankton Res,1992,14(4):575-589
[36]焦念志,杨燕辉.四类海洋超微型浮游生物的同步监测.海洋与湖沼,1999,30(5)：506-511
[37]张利华,张经,晁敏.流式细胞术对微微型浮游植物识别初探.海洋科学,2002,26(3)：60-65
[38]Asai R, Matsukawa R, lkebukuro K, Highly sensitive chemiluminescence flow-injection detection of the red tide phytoplankton Heterosigma carterae. Ana Chimi Acta,1999, 390(123):237-244
[39]Scholin C A,Marin R,Miller P E, et al DNA probes and a receptor-binding assay for detection of Pseudo-nitzschia (Bacillariophyceae) species and domoic acid activity in cultured and natural samples. J Phycol,1999:1356-1367.
[40]Scholin C A, Anderson D M. Two distinct small subunit ribosomal RNA genes in the north American toxic dinoflagellate Alexandrium fundyense (Dinophyceae). Journal of Phycology,1993,29:209-216
[41]Scholin C A, Anderson D M. Identification of group-and strain specific genetic markers for globally distributed Alexandrium (Dinophyceae). I:RFLP analysis of SSU rRNA genes. Journal of Phycology,1994,30(4):744-754.
[42]Scholin C A, Anderson D M. LSU rDNA-based assays for discriminating species and strains of Alexandrium (Dinophyceae). Journal of Phycology,1996,32:1022-1035.
[43]http://www.algaebase.org
[44]http://diatom.acnatsci.org/AlgaeImage/
[45]http://www.shigen.nig.ac.jp/algae/
[46]http://brim.ihb.ac.cn/08/CN/08.asp
[47]http://algaebase.oicp.net/
[48]高华,梁君荣,高亚辉.我国沿海常见浮游植物检索数据库的建立.厦门大学学报(自然科学版),2006,45(S)：230-233
[49]Jeffries H.P, Berman M.S, Katsinis et al. Automated sizing and counting and identification of zooplankton by pattern recognition. Marine Biology,1984,78:329-334
[50]H du Buf and MM Bayer. Automatic Diatom Identification. World Scientific, Series in Machine Perception and Artificial Intelligence,2002,51:316.
[51]Andrei C. Jalba, Michael H. F. Wilkinson, et al Automatic diatom identification using contour analysis by morphological curvature scale spaces. Machine Vision and Applications, 2005,16(4):217-227
[52]ADIAC:http://rbg-web2.rbge.org.uk/ADIAC/db/adiacdb.htm
[53]Hicks Y, Marshall D, Martin R R, et al. Automatic landmarking for building biological shape models. Proceedings of IEEE International Conference on Image Processing, 2002:801-804
[54]Culverhouse P F, Simpson R G, Ellis R, et al. Automatic classification of field collected dinoflagellates by artificial neural network. Marine Ecology Progress Serries,1996,139: 281-287.
[55]Davis, C.S, Fredrik T, et al. A three-axis fast-tow digital Video Plankton Recorder for rapid surveys of plankton taxa and hydrography. American Society of Limnology and Oceanography:Methods 3,2005:59-74
[56]Davis, C.S., Gallager, S.M., Slow, A.R. Microaggregations of Ocean Plankton Observed by Towed Video Microscopy. Science,1992,257:230-232
[57]Qiao Hu, Davis, C.S. Automatic plankton image recognition with co-occurrence matrices and Support Vector Machine. Marine Ecology Progress Series.2005,295:21-31
[58]Tang X, Stewart W K, Huang H, et al. Automatic plankton image recognition. Artificial Intelligence Review,1998,12:177-199
[59]Tang X, Lin F, Andrew Remsen. Binary plankton image classification. IEEE Journal of Oceanic Engineering,2006,31(3):728-735.
[60]Luo T, Kramer K, Goldgof D B, et al. Recognizing plankton images from the shadow image particle profiling evaluation recorder. IEEE Transactions on System, Man and Cybernetics,2004,34:2423-2433.
[61]Pech-Pacheco J L, Alvarez-Borrego J. Optical-digital system applied to the identification of five phytoplankton species. Marine Biology,1998,132:357-365
[62]Pech-Pacheco J L, Alvarez-Borrego J, et al. Identification of a red tide blooming species through an automatic optical-digital system. Proceedings of Algorithms and Systems for Optical Information Processing V, Optics and Imaging Systems. San Diego,CA, USA, 2001,4471:243-250
[63]See Jason H, Campbell Lisa, et al. Combining new technologies for determination of phytoplankton community structure in the northern gulf of mexico. Journal of phycology, 2005,41:305-310
[64]Embleton K V, Gibson C E, Heaney S I. Automated counting of phytoplankton by pattern recognition:a comparison with a manual counting method. Journal of Plankton Research, 2003,25:669-681
[65]Rodenacker, K,Gais, P,Jutting, U et al. Semi-Automatic Recognition of Microorganisms in Water. Proceedings 2001 International Conference on, Thessaloniki, Greece,2001,3:30-33
[66]Forero-Vargas M G,Alvarado J E, Luna-Tamayo A. Automatic diatom recognition on digital images. Proceedings of Applications of Digital Image Processing XXV, volume 4790 of Image Classification. Seattle, WA, USA,2002,133-142
[67]戴君伟,王博亮,谢杰镇等.海洋赤潮生物图像实时采集系统,高技术通讯.2006,16(12)： 1316-1320
[68]郑少平,谢杰镇,王博亮等.基于形状特征描述子的赤潮优势种识别研究.厦门大学学报(自然科学版),2009,48(5)：676-679
[69]Luo Jinfei, Luo Qiaoqi, Yang Chenhui. Towards a computer-aided identification system for marine phytoplankton images.2008(涉密)
[70]赵文仓,姬光荣,周立俭等.浮游植物细胞图像识别方法的研究.计算机工程,2005,31(24)：143-144,155
[71]程军娜,姬光荣,冯晨.基于数学形态学的藻细胞图像预处理.中国海洋大学学报, 2008,38(3)：513-516
[72]周立俭,姬光荣,冯晨.基于多小波的浮游植物细胞图像边缘检测方法.通信技术,2008,41(7)：242-243,246
[73]张磊,王学民,王明时.基于图像处理技术的赤潮生物自动识别.仪器仪表学报,2003,24(S4)： 369-370
[74]王学民,张磊,王明时.图像处理技术在赤潮生物自动识别中的应用.计算机辅助设计与图形学学报,2004,16(2)：158-162
[75]王明时,王学民,张磊.显微图像分析技术在赤潮生物识别中的应用.天津大学学报,2004,37(5)：392-395
[76]曹洪宝,王学民.基于双光谱有毒赤潮优势藻图像分析的研究：[硕士学位论文].天津：天津大学,2005
[77]孙勇,王学民.基于双光谱有毒赤潮藻显微图像自动识别系统的研究：[硕士学位论文].天津：天津大学,2007
[78]程兆第,高亚辉.Mike Dickman硅藻彩色图集合.北京：海洋出版社,1996：120,101图版
[79]郭皓,王健国,易晓蕾等.中国近海赤潮生物图谱.北京：海洋出版社,2004
[80]郭玉洁,钱树本.中国海藻志.第五卷.硅藻门.北京：科学出版社,2003
[81]杨世民,董树刚.中国海域常见浮游硅藻图谱.青岛：中国海洋大学出版社,2006
[82]章毓晋.图像分割.北京：科学出版社,2001
[83]Gonzalez R C, Woods R E. Digital Image Processing.3rd. ed. Addison-Wesley,1992
[84]罗西平,田捷等.图像分割方法综述.模式识别与人工智能,1999,12(3)：300-312
[85]Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging,2004,13(1):146-165
[86]T.W.Ridler, S.Calvard. Picture threshold Picture thresholding using an iterative selection method. IEEE Transsactions on Systems, Man and Cybern,1978, SMC-8:630-632
[87]Otsu N. A threshold selection method from gray-level histograms. IEEE Transsactions on Systems, Man and Cybern,1979,SMC-9(1):62-66
[88]J.Kittler, J. Illingworth. Minimum error thresholding. Pattern Recognition,1986,19:41-47
[89]边肇祺,张学工等.模式识别.北京：清华大学出版社.2001
[90]Serra J. Image Analysis and Mathematical Morphology. Academic Press, London,1982
[91]崔屹.数学形态学方法及应用.北京：科学出版社,2000
[92]LA Ruiz, E Molto et al. Location and characterization of the stem-calyx area on oranges by computer vision. Journal of Agricultural Engineering,1996,64:165-172
[93]N Sarkar, RR Wolfe. Feature extraction techniques for sorting tomatoes by computer vision. Transactions of the ASAE,1985,28(3):970-974
[94]Q S Yang. Machine vision for Fruit Blemish Detection:[PhD Thesis]. U K:Cranfield University Silsoe Campus,1995
[95]P. Soille. Morphological Image Analysis:Principles and Applications. Second edition. Springer-Verlag.2008
[96]Vincent. L, Soille, P. Watershed in digital space:An efficient algorithm based immersion simulations. IEEE Trans on Pattern Analysis & Machine Intelligence,1991,13(6):583-598
[97]X Wu. Adaptive split-and-megre segmentation based on piecewise least-square approximation. IEEE Transactions on Pattern Analysis & Machine Intelligence,1993, 15(8):808-815
[98]N. Malpica, J.E.Ortuno, A. Santos. A multichannel watershed-based algorithm for supervised texture segmentation. Pattern Recognition Letters.2003,24:1545-1554
[99]K. Haris, S.N.Efstratiadis, N. Maglaveras, et al. Hybrid image segmentation using watersheds and fast region merging. IEEE Transactions on Imge Processing. 1998,7(12):1684-1699
[100]马东,程敬之,李斌.细胞图像的彩色纹理分析方法研究.西安交通大学学报,2000,34(1)：108-110
[101]章毓晋.基于内容的视觉信息检索.北京：科学出版社,2003
[102]Kenneth R.Castleman. Digital image Processing(Second Edition). Publishing House of Electronics Industry,2005,409-415
[103]龚声蓉,刘纯平,王强等.数字图像处理与分析.北京：清华大学出版社.2006
[104]王铌.海洋浮游生物数字图像处理方法：[硕士学位论文].青岛：中国海洋大学.2006
[105]Hu M.K.Visual pattern recognition by moment invariants. IRE Transaction Information Theory,1962,8(2):179-187
[106]葛晓青.图像检索中纹理特征提取的研究：[硕士学位论文].哈尔滨：哈尔滨理工大学.2005
[107]R.M.Haralick, K.Shanmugam, et al. Texture Features for Image Classification. IEEE Transaction. On Systems, Man and Cybernetics,1973, SMC-3(6):610-621
[108]R.M.Haralick. Statistical and structural approaches to texture. Proceedings of the IEEE, 1979,67:786-804
[109]T.R.Reed, J.M.H. du Buf. A review of recent texture segmentation and feature extraction techniques. CVGIP:Image Understanding,1993,57(3):359-372
[110]IT Jolliffe. Principal component analysis. New York:Springer,1986
[111]V.Vapnik. The nature of statistics learning theory. New York:Springer Verlag,1995
[112]E Osuna, R Freund, F Girosi. An improved training algorithm for support vector machines. In proceedings of 1997 IEEE workshop on Neural Networks for Signal Processing. 1997:276-285
[113]E Osuna, R Freund, F Girosit. Training support vector machines:an application to face detection. Proceedings of CVPR'97, New York,NY,IEEE,1997:130-136
[114]T Joachims. Text categorization with support vector machines. Technical report 23, University of Dortmund, German,1997
[115]T Joachims. Text categorization with support vector machines:learning with many relevant features. Machine Learning:ECML-98,1998:137-142
[116]C Bahlmann, B Haasdonk, H Burkhardt. Online handwriting recognition with support vector machines-a kernel approach. In Proceedings 8th Int. Workshop on Frontiers in Handwriting Recognition,2002:49-54
[117]V.Vapnik. Statistical learning theory. New York:J.Wiley,1998
[118]Chih-Chung Chang and Chih-Jen Lin. LIBSVM:a library for support vector machines, 2001. Software available at http://www.csie.ntu.edu.tw/～cjlin/libsvm
[119]BE Boser, IM Guyon, VN Vapnik. A training algorithm for optimal margin classifiers. Proceedings of the fifth annual workshop on Computational Learning Theory, ACM Press, 1992:144-152
[120]车武军,杨勋年,汪国昭.动态骨架算法.软件学报.2003,14(4)：818-823
[121]H Blum. A transformation for extracting new descriptors of shape. Models for the perception of speech and visual form. Cambridge, Mass:MIT Press,1967
[122]H Blum. Biological shape and visual science (Part Ⅰ). Journal of Theoretical Biology, 1973,38:205-287
[123]JW Brandt. Convergence and continuity criteria for discrete approximations of the continuous planar skeleton. CVGIP:Image Understanding,1994,59(1):116-124
[124]刘俊义.基于对称性的目标描述和识别技术：[博士学位论文].长沙：国防科学技术大学.2001
[125]DT Lee. Medial axis transformation of a planar shape. IEEE Transactions on Pattern Analysis and Machine and Intelligence,1982,4(4):363-369
[126]D Shaked, AM Bruckstein. The curve axis. Computer vision and image understanding, 1996,63(2):367-378
[127]RL Ogniewicz, O Kubler. Hierarchic voronoi skeletons. Pattern Recognition,1995, 28(3):343-359
[128]廖志武.2-D骨架提取算法研究进展.四川师范大学学报(自然科学版).2009,32(5)： 676-688
[129]Rosenfield A, Pfaltz J. Sequential operations in digital picture processing. Journal of association for computing machinery,1966,13(4):471-494
[130]H. Talbot, L. Vincent. Euclidean skeletons and conditional bisectors. Visual Communi-cations and Image Processing'92,1992:862-876
[131]刘宏申.击中击不中变换在笔画细化中的应用.安徽工业大学学报.2002,19(3)：251-253
[132]刘志敏,杨杰,施鹏飞.数学形态学的细化算法.上海交通大学学报,1998,32(9)：15-19
[133]陈晓飞.基于骨架的目标表示和识别技术：[博士学位论文].长沙：国防科学技术大学.2004
[134]Ablameyko S.V, Arcelli C, Baja G.S.D. Hierarchical decomposition of distance labeled skeletons. International journal pattern recognition and artificial intelligence,1996, 10(8):957-970
[135]徐钢锋,王平等.基于骨架特征的机场主跑道识别.红外与激光工程,2006,36(6)：717-721
[136]蔡自兴,成浩.一种基于骨架特征和神经网络的手写体字符识别技术.计算机技术与自动化,2001,20(3)：59-65
[137]宋婷,刘文予等.基于骨架树的线性骨架拓扑相似性度量算法.红外与激光工程,2005,34(1)：74-79
[138]刘文予,刘俊涛.基于骨架树描述符匹配的物体相似性度量方法.红外与毫米波学报,2005,24(6)：432-436
[139]陈晓飞,王润生.目标骨架的多尺度树表示.计算机学报,2004,27(11)：1540-1545
[140]王飞,张树生等.拓扑和形状特征相结合的三维模型检索.计算机辅助设计与图形学学报,2008,20(1)：99-103
[141]K Siddiqi, A Shokoufandeh, SJ Dickinson, et al. Shock Graphs and Shape Matching. International Journal of Computer Vision,1999,35(1):13-32