摘要
空间在人类认知中扮演了基础性的角色。在任意日常场景中,空间通常被认为是由空间关系交织构成的结构体,而不是简单的承载相互独立的空间对象的容器。因此,空间关系一直以来都是许多学科的重要研究内容之一,包括人工智能、认知科学、心理学、语言学、地理学以及图形学等。在图像理解相关领域中,理解图像中各对象间的空间关系以及自动构建图像中对象间空间关系的自然语言描述都是极其重要的研究内容,这两方面内容构成了空间关系描述研究的两个层次。针对空间关系描述这一课题,论文对空间方向关系基础理论、空间方向关系形式化模型以及空间关系自然语言组合描述等理论和方法进行了深入的研究,本文的主要贡献有以下几个方面：
(1)完善了空间方向关系的基础理论。首先,对空间方向关系、空间对象的类型、空间方向关系参考框架、观察角度以及基本方向等空间方向关系的基本概念进行了明确的定义,为空间方向关系研究打下了基础；其次,提出了第二类空间方向关系参考框架,与第一类参考框架一起为提出完备的空间方向关系形式化模型体系提供理论支持；然后,分析了空间方向关系的性质和特点,为空间方向关系形式化模型的建立提供了基本原则；最后,提出了两种空间方向关系分类方法,为提出基本方向关系和特殊方向关系的形式化模型以及基于细节空间关系的描述方法提供了相关依据。
(2)提出了影响空间方向关系的因素并分析了现有的空间方向关系形式化模型。首先,通过建立空间方向关系图形库,提出并分析了影响空间方向关系的因素,为空间方向关系形式化模型的建立提供了理论基础；其次,根据空间方向关系的基础理论和影响空间方向关系的因素分析了现有的空间方向关系形式化模型的特点,经比较发现直方图模型充分考虑了方位角、形状和相对距离对空间方向关系的影响,并且具有描述准确性高、适用性强等特点,所以将直方图模型确立为空间方向关系形式化模型的基础模型。
(3)提出了一种空间方向关系形式化模型体系。首先,提出了一种在观察者参考框架下的可视域直方图模型,该模型根据可视性理论采用对象间的可视域作为研究对象,以角直方图模型作为基础模型,有效地解决了观察者参考框架下的空间方向关系描述问题；其次,提出了一种新的四叉树直方图,该直方图针对以往直方图计算量大的缺点,考虑到图形综合理论,引入了图形综合为点的两个条件,采用四叉树算法对空间对象进行四叉树划分,在划分结果的基础上计算直方图,同时保证了较高的精确度和较低的计算量；然后,建立了一种新的基本方向关系模糊判定方法,该方法针对以往基本方向关系判定方法存在的问题,考虑到空间方向关系的削弱作用以及偏移性,有效地解决了判定结果多于两个方向以及狭长对象发生误判的问题；最后,提出了一种新的特殊方向关系模糊判定方法,有效地克服了现有特殊方向关系判定方法的缺陷。实验结果证明,可视域直方图模型和四叉树直方图模型较其他模型更符合人的空间方向认知,且具有更广泛的适用性。
(4)提出了空间关系自然语言组合描述方法。首先,采用半自动的模式提取方法获取了空间方向关系描述的常用句法模式以及细粒度构词模式；然后,提出了基于直方图模型和模糊规则的空间关系词汇选取方法,自动生成空间方向词、距离词以及程度修饰词等；接着,在外部和内部参考框架下依照相应的句法模式和细粒度构词模式自动生成了空间关系自然语言组合描述；最后,提出了细节空间关系的概念以及不同参考框架下的细节空间关系自然语言组合描述方法,有效地解决了在某些空间拓扑关系条件下空间关系自然语言描述不够详细、准确的问题。实验结果证明,本文提出的空间关系自然语言组合描述方法,能够比较准确地生成符合人类日常空间关系交流习惯的空间关系自然语言组合描述语句。
Space plays a fundamental role in human cognition. In everyday situations, it is often viewed as a construct induced by spatial relationships, rather than as a container that exists independently of the objects located in it. Spatial relationships, therefore, have been thoroughly investigated in many disciplines, including artificial intelligence, cognitive science, psychology, linguistics, geography, graphics and so on. In image understanding and related fields, understanding the spatial organization of regions in images and building the linguistic descriptions of spatial relation automatically are two important tasks, and these two aspects constitute the two levels of the study of spatial relation description. For the subject of spatial relation description, this paper thoroughly studies the fundamental theory of spatial directional relation, the formal model of spatial directional relation and linguistic descriptions of spatial relation. The main achievements are concluded as follows:
(1) The perfect fundamental theories of spatial directional relation are proposed. Firstly, several clear definitions, including spatial directional relation, types of spatial object, reference frame of spatial directional relation, observation angle and basic direction, are proposed, and they lay the foundation for spatial direction relation research. Secondly, properties and characteristics of spatial directional relation are analyzed, and they provide the basic principles for the formal model of spatial directional relation. Thirdly, two classification methods of spatial directional relation are proposed, and they provide related basis for the formal model of basic directional relation and special directional relation and the linguistic description method based on detailed spatial relation.
(2) The influence factors of spatial directional relation are proposed, and existing formal models of spatial directional relation are analyzed. Firstly, through the establishment of the graphic library of spatial directional relation, the factors that affect spatial directional relation are proposed and analyzed, and they provide theoretical basis for the formal model of spatial directional relation. Secondly, the characteristics of existing formal models of spatial directional relation are analyzed based on the fundamental theories and the influence factors of spatial directional relation, the results of analysis show that histogram model has fully taken into account orientation angle, shape, and relative distance of spatial objects to impact on representation of spatial directional relation. In this paper histogram model is defined basic model of spatial directional relation for its higher accuracy and applicability.
(3) The perfect model system of spatial directional relation is proposed. Firstly, the visual area histogram model in observer reference framework is proposed, and it uses visual area between objects as the object of study based on visibility theory and effectively solved the problems of description in observer reference framework. Secondly, a new quadtree histogram is proposed, and it uses quadtree arithmetic to divide spatial objects into a number of simple and regular sub-objects based on two factors affecting the integration of graphics. Quadtree histogram is calculated based on the sub-objects, and it can ensure high accuracy and low computation. Thirdly, a new fuzzy judgment approach of the basic directional relation is proposed, and it using the availability degree and the certainty degree of directional relation to resolve the problems of existing judgment approaches of the basic directional relation. Finally, a new fuzzy judgment approach of the special directional relation is proposed, and it can resolve the problems of existing judgment approaches of the special directional relation. The experimental results show that the visual area histogram model and the quadtree histogram model are in better harmony with human spatial perception.
(4) The linguistic descriptions approaches of spatial relation are proposed. Firstly, the common syntax patterns and fine-grained word-formation patterns are found by semi-automatic pattern extraction method. Secondly, several directional terms, distance terms and degree adverbs are automatically generated based on histogram models and fuzzy rules. Thirdly, the linguistic descriptions of spatial relation are automatically generated based on syntax patterns and fine-grained word-formation patterns in inner reference frame and outer reference frame. Finally, a linguistic descriptions approach of detailed spatial relation is proposed based on detailed spatial relation in different reference frames, and it can resolve the problems that the descriptions are not detailed enough in some topological conditions. The experimental results show that the linguistic descriptions approaches in this paper can accurately generate linguistic descriptions of spatial relation which are basically accordant with actual communication habits of human.
引文
[1]Space. Wikipedia, the Free Encyclopedia, http://en.wikipedia.org/w/index.php?title=Space&oldid=19194480.Accessed Dec.20, 2011.
[2]Space Perception. Encyclopaedia Britannica from Encyclopaedia Britannica Online, http://search.eb.com/eb/article?tocld=46639. Accessed June 12,2005.
[3]郭仁忠.空间分析.武汉：武汉测绘科技大学出版社,1997.
[4]杜世宏.空间关系模糊描述及组合推理的理论和方法研究.[博士学位论文]中国科学院遥感应用研究所,北京,2004.
[5]钟义信.信息科学原理.北京：北京邮电大学出版社,2002.
[6]钟义信.“理解”论：信息内容认知机理的假说.北京邮电大学学报,2008,31(3)：1-8.
[7]Mark D., Egenhofer M.J. Modeling Spatial Relations Between Lines and Regions: Combining Formal Mathematical Models and Human Subjects Testing. Cartography and Geographical Information Systems,1994,21(3):195-212.
[8]闫浩文.空间关系方向关系的概念、计算和形式化模型.[博士学位论文]武汉大学,武汉,2002.
[9]刘丽虹,张积家,王惠萍.习惯的空间术语对空间认知的影响.心理学报2005,37(4),469-475.
[10]王润生.图像理解.长沙：国防科学技术大学出版社,1995.
[11]张会章,张利霞,郭雷.图像理解.计算机工程,2003,29(11)：23,24,71.
[12]谢昭.图像理解的关键问题和方法研究.[博士学位论文]合肥工业大学,合肥,2007.
[13]钟义信.机器知行学原理：信息、知识、智能转化的统一理论.北京：科学出版社,2007.
[14]钟义信.高等智能-机制主义-信息转换.北京邮电大学学报,2010,33(1)：1-6.
[15]钟义信.关于“信息-知识-智能转换规律”的研究.电子学报,2004,32(4)：601-605.
[16]钟义信.知行学引论——信息知识智能的统一理论.中国工程科学,2004,6(6)： 2-8.
[17]钟义信.论“信息-知识-智能转换规律”.北京邮电大学学报,2007,30(1)：1-9.
[18]Abdelmoty A.I., Williams M.H. Approaches to the Representation of Qualitative Spatial Relationships for Geographic DataBases. Geodesy,1994,40:204-216.
[19]J. Freeman. The modelling of spatial relations. Computer Graphics and Image Processing,1975.
[20]Gaterell A.C. Distance and Space:a Geographical Perspective. Oxford:Clarendon Press,1983.
[21]胡勇,陈军.基于Voronoi图的空间临近关系表达和查询操作.中国GIS系统协会第二届年会论文集,北京,1997：346-356.
[22]Peuquet D.J. An Algorithm for Calculation Minimum Euclidean Distance between Two Geographical Features. Computers and Geosciences,1992,18(8):989-1001.
[23]Koshizuka T., Kurita O. Approximate Formulas of Average Distance Associated with Regions and their Applications to Location Problems. Mathematical Programming: Session B,1991,52:99-123.
[24]Hong J.H., Egenhofer M.J., Frank A.U. On the Robustness of Qualitative Distance and Direction-Reasoning. Proceedings of AutoCarto 12, Charlotte. NC,1995:301-310.
[25]Hong J.H. Qualitarive Distance and Direction Reasoning in Geographic Space. PHD Thesis, University of Maine,1994.
[26]Goyal R.K. Similarity Assessment for Cardinal Directions between Extended Spatial Objects. PHD Thesis, the University of Maine,2000.
[27]Egenhofer M., Golledge R. Spatial and Temporal Reasoning in Geographic Information Systems. Spatial Information Systems. New York:Oxford University Press,1998.
[28]Haar R. Computational Models of Spatial Relations. Computer Science. University of Maryland College Park,1976:83-121.
[29]Frank A. Qualitative Spatial Reasoning about Distances and Directions in Geographic Space. Journal of Visual Languages and Computing,1992,3:343-371.
[30]Peuquet D., Zhan C.X. An Algorithm to Determine the Directional Relation Between Arbitrarily Shaped Polygons in the Plane. Pattern Recognition,1987, 20(1):65-74.
[31]郭庆胜,郑春燕.锥形空间方向关系模型的改进.武汉大学学报(信息科学版),2007,32(1)：81-84.
[32]Chang S.K. Iconic Indexing by 2-D String. IEEE Trans. Pattern Anal. Machine Intelligence,1987, (9):413-428.
[33]Jurgert E., Chang S.K. An Algebra for Symbolic Image Manipulation and Transformation. Visual Databased Systems, Elsevier Science Publishers.1989: 301-317.
[34]Chang S.K., Jungert E. and Li Y. Representation and Retrieval of Symbolic Pictures using Generalized 2D-Strings. Visual Commun. and Image Processing, Philadelphia,1989.
[35]Lee S.Y., Hsu F.J.2D C-String:A New Spatial Knowledge Representation for Image Database Systems. Pattern Recognition,1990,23(10):1077-1087.
[36]Papadias D., Theodoridis Y. and Sellis T. Spatial Relations, Minimum Bounding Rectangles, and Spatial Data Structures. International Journal of Geographical Information Science,1997,11(2):111-138.
[37]Goyal R., Egenhofer M.J. Consistent Queries over Cardinal Directions across Different Levels of Detail. In Proceedings of the 11th International Workshop on Database and Expert Systems Applications, Greenwich,2000:876-880.
[38]李成名,朱英浩,陈军.利用Voronoi图形式化描述和判断GIS中的方向关系.解放军测绘学院学报,1998,19(2)：117-120.
[39]闫浩文,郭仁忠.用Voronoi图描述空间方向关系的理论依据.武汉大学学报(信息科学版),2002,27(3)：306-310.
[40]闫浩文,郭仁忠.空间方向关系形式化描述模型研究.测绘学报,2003,32(1)：42-46.
[41]Krishnapuram R., Keller J. and Ma Y. Quantitative Analysis of Properties and Spatial Relations of Fuzzy Image Regions, IEEE Transactions on Fuzzy Systems, 1993,1(3):222-233.
[42]Miyajima K., Ralescu A. Spatial-organization in 2d Segmented Images: Representation and Recognition of Primitive Spatial Relations. Fuzzy Sets and Systems,1994,65(2):100-105.
[43]Wang Y. H., Makedon F. R-Histogram:Quantitative Representation of Spatial Relations for Similarity-Based Image Retrieval. The Eleventh ACM International Conference on Multimedia,2003:323-326.
[44]Wang Y. H., Makedon F. and Chakrabarti A. R*-Histograms:Efficient Representation of Spatial Relations between Objects of Arbitrary Topology, the Twelve ACM International Conference on Multimedia,2004:356-359.
[45]Matsakis P., Wendlling L. A New Way to Represent the Relative Position between Areal Objects, IEEE Transaction on Pattern Analysis and Machine Intelligence, 1999,21(7):634-644.
[46]Ni J.B., Matsakis P. Force Histograms Computed in O(NlogN).18th International Conference on Pattern Recognition,2006:1-4.
[47]杜世宏,秦其明,王桥.空间关系及其应用.地学前缘,2006,15(3)：69-80.
[48]杜世宏,王桥,杨一鹏,李治江.空间方向关系模糊描述.计算机辅助设计与图形学学报,2005,17(8)：1744-1751.
[49]杜世宏,王桥,秦其明.空间关系模糊描述与组合推理.北京：科学出版社,2007.
[50]Papadias D., Karacapilidis N. and Arkoumanis D. Processing Fuzzy Spatial Queries:Aconfiguration Similarity Approach. International Jouranl of Geographical Information Science,1999,13(2):93-118.
[51]Cicerone S., Felice P.D. Cardinal Relations between Regions with a Broad Boundary. The 8th ACM Symposium on Advances in Geographic Information Systems,2000:15-20.
[52]谢琦,刘大有,虞强源.一种不确定区域间的方向关系模型.吉林大学学报(理学版),2006,44(5)：748-753.
[53]何建华,刘耀林,俞艳.不确定方向关系的模糊描述模型.武汉大学学报(信息科学版),2008,33(3)：257-260.
[54]杜世宏,王桥,魏斌,等.空间方向关系粗糙推理.测绘学报,2003,32(4)：334-338.
[55]刘波,李大军,刘学军,马东岭.拓扑关系和方向关系的定性组合描述.地理与地理信息科学,2006,22(4)：44-46.
[56]杜世宏,王桥,杨一鹏.一种定性细节方向关系的表达模型.中国图像图形学报,2004,9(12)：1496-1450.
[57]刘新,刘文宝,李成名.三维空间关系的描述及其定性推理.北京：测绘出版社,2010.
[58]Matsakis P. Combined Extraction of Directional and Topological Relationship Information from 2D Concave Objects. Fuzzy Modeling with Spatial Information for Geographic Problems,2005:15-40.
[59]Santosh K.C., Wendling L. and Lamiroy B. Using Spatial Relations for Graphical Symbol Description. International Conference on Pattern Recognition,2010: 2041-2044.
[60]Randell D.A., Cui Z. and Cohn A.G. A Spatial Logic Based on Regions and Connection. Proceedings of the 3rd International Conference on Principles of Knowledge Representation and Reasoning, San Francisco:Morgan Kaufmann Publishers,1992:165-176.
[61]何建华,刘耀林,唐新明.离散空间的拓扑关系模型.测绘学报,2005,34(4)：343-348.
[62]Cohn A.G., Bennett B. And Gooday J. Qualitative Spatial Representation and Reasoning with the Region Connection Calculus, Netherlands,1997:1-44.
[63]邓敏,刘文宝,黄杏元,等.空间目标的拓扑关系及其GIS应用分析.中国图象图形学报,2006,11(12)：1743-1749.
[64]吴长彬,闾国年.空间拓扑关系若干问题研究现状的评析.地球信息科学学报,2010,12(4)：524-531.
[65]熊金城.点集拓扑学讲义.北京：高等教育出版社,1981.
[66]Egenhofer M., Franzosar. Point-set Topological Spatial Relations. International Journal of Geographical Information Systems,1991,5(2):161-174.
[67]Egenhofer M., Herringj. Categoring Binary Topological Relationships between Regions, Lines, Points in Geographic Databases. Oronoi:Department of Surveying Engineering, University of Maine,1991.
[68]Chen J., Licm, Lizl, et al. A Voronio-based 9-Intersection Model for Spatial Relations. International Journal of Geographical Information Science,2001,15(3): 201-220.
[69]邓敏,刘文宝,冯学智.GIS面目标间拓扑关系的形式化模型.测绘学报,2005,34(1)：85-90.
[70]Cohn A.G., Gotts N.M. The " Egg-Yolk " Representation of Regions with Indeterminate Boundaries. Proceedings of GISDATA-Specialist Meeting on Special Objects with Indeterminate Boundaries, London:Taylor & Francis,1996: 171-187.
[71]Bjorke J.T. Topological Relations between Fuzzy Regions:Derivation of Verbal Terms. Fuzzy Sets and Systems,2004,141:449-469.
[72]Clementini E. A Model for Uncertain Lines. Journal of Visual Languages and Computing,2005,16:271-288.
[73]刘文宝,邓敏,夏宗国.矢量GIS中属性数据的不确定性分析.测绘学报,2000,29(1)：76-81.
[74]杜晓初,黄茂军.不确定线-面拓扑关系的描述与判别.测绘学报,2007,36(3)：340-350.
[75]杜世宏,秦其明,王桥.复杂宽边界区域拓扑关系计算模型.自然科学进展,2007,17(7)：943-949.
[76]虞强源,刘大有,欧阳继红.基于区间值模糊集的模糊区域拓扑关系模型.电子学报,2005,33(1)：186-189.
[77]李大军,刘波,程朋根,等.模糊空间对象拓扑关系的Rough描述.测绘学报,2007,36(1)：72-77.
[78]Regier T. P. The Acquisition of Lexical Semantics for Spatial Terms:A Connectionist Model of Perceptual Categorization. PhD Thesis, University of California at Berkeley,1992.
[79]Kopp L. A Neural Network for Spatial Relations:Connecting Visual Scenes to Linguistic Dscriptions. Lund University Cognitive Studies,1994,32.
[80]Abella A., Kender J.R. From Images to Sentences via Spatial Relations. In Proceedings ICCV'99 Workshop on the Integration of Image and Speech Understanding, Greece,1999.
[81]Roy D. Grounded Spoken Language Acquisition:Experiments in Word Learning. IEEE Transaction on Multimedia,2003,5(7):1-15.
[82]Keller J.M., Wang X.A. Fuzzy Rule-based Approach to Scene Description Involving Spatial Relationships. Computer Vision and Image Understanding,2000, 80(1):21-41.
[83]Matsakis P., Keller J. M., Wending L. Linguistic Descriptions of Relative Positions in Images. IEEE Transactions on Systems, Man, and Cybernetics,2001,31(4): 573-588.
[84]Skubic M., Matsakis P., Chronis G. Generating Multi-level Linguistic Spatial Descriptions from Range Sensor Readings Using the Histogram of Forces. Autonomous Robots,2003,14(1):51-69.
[85]Skubic M., Blisard S., Bailey C., Adams J.A. and Matsakis P. Qualitative Analysis of Sketched Route Maps:Translating a Sketch into Linguistic Descriptions. IEEE Transactions on Systems, Man, and Cybernetics,2004,32(2):1275-1282.
[86]Sjahputera O., Matsakis P. and Keller J.M. Linguistic Descriptions for an Object in Motion. Fuzzy Information Processing Society,2002,243-248.
[87]Sjahputera O., Keller J.M. and Matsakis P. Temporal Fusion in Dynamic Linguistic Descriptions.IEEE International Conference on Fuzzy Systems,2003:613-623.
[88]Wawrzyniak L., Nikitenko D., Matsakis P. Describing Topological Relationships in Words:Refinements. IEEE International Conference on FuzzySystems.2005: 743-748.
[89]Matsakis P., Wawrzyniak L., Ni J. Relative Positions in Words:A System that Builds Descriptions around Allen Relations. International Journal of Geographical Information Science,2010,24(1):1-23.
[90]杜世宏,王桥,李治江.GIS中自然语言空间关系定义.武汉大学学报(信息科学版),2005,30(6)：533-538.
[91]张克定.空间关系及其语言表达的认知语言学阐释.河南大学学报(社会科学版),2008,48(1)：1-8.
[92]谭云霞.从认知的角度阐释空间关系的语言表达.考试周刊,2010,8：88-90.
[93]Wang X., Matsakis P., Trick L. and Nonnecke. A Study on How Humans Describe Relative Positions of Image Objects.13th Int. Symposium on Spatial Data Handling,2008:1-18.
[94]李晗静.基于自然语言处理的空间概念建模研究.[博士学位论文]哈尔滨工业大学,哈尔滨,2007.
[95]余建伟,李清泉.位置感知计算中定位信息的自然语言描述.地理与地理信息科学,2009,25(1)：10-13.
[96]张雪英,间国年.自然语言空间关系及其在GIS中的应用研究.地球信息科学,2007,9(6)：77-81.
[97]邓敏,黄雪萍,刘慧敏,李光强.利用自然语言空间关系的空间查询方法研究.武汉大学学报(信息科学版),2011,36(9)：1089-1093.
[98]Direction. Wikipedia, the Free Encyclopedia, http://en.wikipedia.org/wiki/Direction. Accessed Dec.20,2011.
[99]中国社会科学院语言研究所词典编辑室.现代汉语词典.北京：商务印书馆,第 五版,2008.
[100]Timothy C., Clausner, Croft W. Domains and Image Schemas.Cognitive Linguistics,1999,10(1):1-31.
[101]Levinoson S. C. Space in Language and Cognition:Explorations in Cognitive Diversity. Cambridge:Cambridge University Press,2003.
[102]Schmidt G. R.Various Views on Spatial Prepositons.AI Magazine,1988,9(2): 95-105.
[103]Carlson-Radvansky L. A., Irwin E. E. Frames of reference in vision and language: Where is above? Cognition,1993,46(3):223-244.
[104]Klir G., Folger T. Fuzzy Sets, Uncertainty, and Information. Englewood Cliffs: Prentice Hall,1988.
[105]Dubois D., Prade H. Fuzzy Sets and Systems:Theory and Applications. New York: Academic Press,1980.
[106]Wang Y., Makedon F., Drysdale R.L. Fast Algorithms to Compute the Force Histogram.2004, uppublised.
[107]Ni J., Matsakis P. An Equivalent Definition of the Histogram of Forces: Theoretical and Algorithmic Implicaitons. Pattern Recognition,2010,43: 1607-1617.
[108]Matsakis P., Wawrzyniak L., Ni J. A General Approach to the Fuzzy Modeling of Spatial Relationships, Studies in Fuzziness and Soft Computing,2010,256:49-74.
[109]科夫卡(Koffka). Principle of Gestalt Psychology浙江：浙江教育出版社,1997.
[110]Canny J. A Comutational Approach to Edge Detection. IEEE T-PAMI,1986,8(6): 679-698.
[111]Zadeh L. A. Fuzzy sets. Information and Control,1965,8:338-353.
[112]李柏年.模糊数学及其应用.合肥：合肥工业大学出版社,2007.
[113]Gapp K. P. Basic Meanings of Spatial Relations:Computation and Evaluation in 3D Space, AAAI,1994:1393-1398.
[114]I. Bloch. Fuzzy Relative Position between Objects in Image Proceeing:New Definition and Properties Based on a Morphological Approach. Int. J. of Uncertainty Fuzziness and Knowledge-Based Systems,1999,7(2):99-133.
[115]A. Rosenfeld, R. Klette. Degree of Adjacency or Surroundedness. Pattern Recognition, 1985,18(2):169-177.
[116]P. Matsakis, S. Andrefouet. The Fuzzy Line Between and Surround. The 2002 IEEE International Conference on Fuzzy Systems,2002:1596-1601.
[117]王乙宁.2D图像空间关系特征与描述词汇对齐的研究.[硕士学位论文]北京邮电大学,北京,2012.