摘要
工程图自动识别技术旨在将扫描工程图像转换为与各种CAD系统相兼容的矢量数据格式,精确的矢量化结果是进一步进行图形理解的基础,然而当前的图纸扫描转换系统均未能取得令人满意的图素识别精度,矢量化结果中的错误只能依靠人工交互校正。校正错误的时间往往远大于矢量化的时间。研究如何提高矢量化系统输出数据的质量对提高工程图自动识别技术的水平和矢量化系统的性能及实用化程度有着重要的理论和应用意义。本文围绕这一主题开展矢量化工程图的后处理技术研究,提出“基于识别质量评价”的矢量图素错误自动判别和校正的解决方案,使得图纸扫描转换系统不但具有产生矢量化数据的能力,而且具有对所产生的矢量数据的质量进行评价分析和自适应校正的能力。
本文重点讨论了图素质量评价器的设计,提出采用图素识别质量特征因子来表述图素的识别质量,并以矢量图素对应的光栅图元作为约束矢量图素的模板或公差带,以此提取反映识别质量的特征因子,结合模糊理论的有关概念定义各种特征因子的表达式;图素的识别质量特征因子作为图素识别质量评价器的输入,由评价器经过处理后输出对图素识别质量的评判结果。
本文设计了一个基于人工神经网络的直线图素识别质量评价器,网络经过训练后可以取得类似人眼判断的评判效果,由于各识别质量特征因子在定义的时候一般都取的是和图素线宽的相对比值,因此本文提出的方法对于扫描工程图的分辨率的影响不敏感。对于圆弧型图素,则重点研究了常见的错误模式—伪圆弧的检测和校正技术,首先检测伪圆弧对应的光栅图元轮廓上的角点,并以这些角点对图元轮廓进行分段,再逐段分析。
在获得对图素识别质量的评价之后,质量较差的图素被输入到错误自动校正器进行错误校正处理,本文提出“二次矢量化”的错误校正思想,二次矢量化是在初步矢量化所获得知识的基础之上,取得初始参数,并在跟踪过程中动态校正参数,在跟踪结束时引入跟踪终止检测探针以消除光栅图像中黑白噪音的影响,使得算法具有较强的抗噪音干扰能力,校正后的图素仍需进行质量评价,未能通过评价的图素需递归执行二次矢量化算法。
本文最后一部分详细讨论了图形二维重建的关键技术,包括识别图素间的拓扑关系,建立带权有向图的拓扑关系动态表示模型,尺寸驱动技术及辅助线线型重构技术等。
Engineering drawing recognition technique aims at converting scanned engineering drawing images into vector formats compatible with popular CAD systems. Getting a vectorization result with sufficient accuracy is the basis for further drawing interpretation. Unfortunately, none drawing conversion systems can achieve the satisfactory recognizing accuracy. Correcting manually for vectorized errors is needed and it is a time-consuming process. Research on improving output data qualities from vectorization system is significant for enhancing performance of raster-to-vector systems. In this dissertation, the author presents a recognition quality evaluating mechanism that provides the system with the ability of measure the quality of each primitive generated. .
One of the focuses in this dissertation is the design of a recognition quality evaluator for graph entities. The original image information corresponding to the graph entities is considered as a constrained template or allowable error range. Some evaluating factors, defined by using fuzzy theory, have been proposed to express a graph entity's recognition quality and as the input of the quality evaluator.
To get the evaluating result, a recognition quality evaluator for straight lines based on artificial neural networks has been designed. After training the neural network can work well and output the quality evaluating results. Furthermore, this proposed evaluating approach is not sensitive to scanning image resolution. For the graph entities with arc type, we mainly studied a mis-recognition in graph entity types, referred as "pseudo arc". By searching the corner points on the border of the arc and divide the arc to piece-wise, the analysis is then done for every piece respectively.
For those graph entities with poor recognized results indicated by the quality evaluator, further processing operations for them have to be considered. A correction idea based on re-vectorization has been put forward. Re-vectorization is performed on the basis of original vectorization by obtaining the initial parameters such as line types and slope. Inuring tricing it can adjust
the parameter adaptively. To decrease the influence of noise pixels, we designed a stop probe to detect tracing-stop conditions. Process of re-vectorization is performed recursively until quality of graph entity is satisfactory.
Finally, some key technologies for 2D graphs reconstruction are studied. The issues concerned include the recognition and presentation of topologic relations among graphs entities and a directed and weighted graph model established to describe the relations and techniques on dimension driven. The recognition for assistant type graph entities in engineering drawings, such as dash-dot lines, dash lines and hatched section lines, is investigated.
引文
[1] Alain Filbois. Combining geometric and photometric information to find lines from step edge detection, http://citeseer.nj.nec.com/354738.html [OL]
[2] Amit Kumar Das, Sanjoy Kumar Saha, Bhabatosh Chanda. An empirical measure of the performance of a document image segmentation algorithm. International journal on Document Analysis and Recognition, 2002(4): 183~190
[3] Atul K. Chhabra, vishal Misra. Experiments with statistical connectionist methods and hidden markov models for recognition of text in telephone company drawings, http://citeseer.nj.nec.com/47277.html [OL]
[4] Bei Li, Ching Y.Suen. A Knowledge-based thinning algorithm. Pattern recognition, 1991,24(12): 1211~1221
[5] Berrin A. Yanikolu. Pitch-based segmentation and recognition of dot-matrix text. International journal on Document Analysis and Recognition, 2000(3): 34~39
[6] Boris Pasternak. The Role of Taxonomy in Drawing Interpretation. Proceedings of the third International Conference on Document Analysis and Recognition, Montreal, 1995. 799~802
[7] C.C. Han, K.C. Fan. Skeleton generation of engineering drawings via contour matching, Pattern recognition, 1994, 27(2): 261~275
[8] Chai Fang, Changsong Liu, Liangrui Peng, Xiaoqing Ding. Automatic performance evaluation of printed Chinese character recognition systems. International journal on Document Analysis and Recognition 2002(4): 177~182
[9] C.Choisy, A.Belaid. Cross-learning in analytic word recognition without segmentation. International journal on Document Analysis and Recognition 2002(4):281~289
[10] Claudia Wenzel, Heiko Maus. Leveraging corporate context within knowledge-based document analysis and understanding. International journal on Document Analysis and Recognition, 2001(3):248~260
[11] David S. Doermann. An Introduction to Vectorization and Segmentation. Graphics recognition: algorithm and system: Second International workshop GREC. Nancy(France), 1997. 1~8
[12] Dov Dori, Liu wenyin. Automated CAD conversion with the machine drawing understanding system: concepts, algorithm and performance. http://research.microsoft.com/asia/download/disquisition/16.asp [OL]
[13] Dov Dori, Liu Wenyin. The sparse pixet Vectorization: an algorithm and its performance evaluation. http://citeseer.nj.nec.com/544647.html
[14] Dov Dori, Karl Tombre, From engineering drawings to 3D CAD models: are we ready now? Computer aided design, 1995, 27(4): 243~254
[15] D.Dori, L.wenyin. Arc Segmentation from Complex Line Environments: A Vector-based Stepwise recovery Algorithm, Proceedings of: the 4th International Conference on Document Analysis and Recognition, Ulm, 1997, 76~80
[16] D.Lopresti, A.Tomkins, J.Zhou. Algorithms for matching hand-drawn sketches. http://citeseer.nj.nec.com/lopresti97algorithms.html [OL],1997
[17] Edward Lank, Dorothea Blostein. N-Gram: A well structured knowledge representation for recognition of graphical documents. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 801~804
[18] Eugene Bodansky, Morakot Pilouk. Using local deviations of vectorization to enhance the performance of raster-to-vector conversion systems, International journal on Document Analysis and Recognition, 2000(3): 243~248
[19] Enrico Nardelti, Michelangelo Fossa, Guido Proietti. Raster to object conversion aided by knowledge based image. processing. Proceedings of the ninth conference on artificial intelligence for applications. Orland (Florida), 1993. 951~954
[20] F.Parrnentier, A.Belaid. Logical structure, recognition of scientific bibliographic references. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm. 1997. 1048~1054
[21] Francine R.Chen, Dan S. Bloomberg. Extraction of indicative summary sentences from imaged documents. Proceedings of the 4th International Conference on Document Analysis and Recognition Ulm, 1997. 227~232
[22] Gerd Maderlechner, Helmut Mayer. Conversion of high level information from scanned maps into eographic information systems. Proceedings of the third International Conference on Document Analysis and Recognition, Montreal, 1995. 253~256
[23] G.Hutton, M,Cripps, D.G.Elliman, C.A.Higgins. A strategy for on-line interpretation of sketched engineering drawings. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 771~775
[24] G. Kaufmann, H. Bunke, Detection and correction of recognition errors in check reading, International journal on Document Analysis and recognition, 2000(2):211~221
[25] Gomis, J.M, Gil. Vectorization in recovering engineering drawings.
http://citeseer.nj.nec.com/519943.html [OL]
[26] G.Menier, G.Lorette. Lexical analyzer based on a self-organizing feature map. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 1067~1071
[27] Haralick R.M., Sternberg S.R., Zhuang X., Image Analysis using mathematical morphology. IEEE transaction on PAMI, 1987, 9(8):532~550
[28] Hiroshi Shinjo, Kazuki Nakashima, Massashi Koga, et al. A method for connecting disappeared junction patterns on frame lines in form documents. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 667~670
[29] Ihsin, T. Phllips, Atul K.Chhabra, Robert Haralick. A performance Evaluation Protocol for Graphics Recognition Systems. Graphics recognition: algorithm and system: Second International workshop GREC. Nancy(France), 1997. 372~389
[30] Ihsin, T. Phtlips, Atul, K.Chhabra. Empirical Performance Evaluation of Graphics Recognition Systems. IEEE transaction on pattern analysis and machine intelligence, 1999, 21(9): 849~869
[31] J.Liang, J.HA, R.Rogers, et al. Document layout structure extraction using bounding boxes of different entities. Proceedings Third IEEE workshop on applications of Computer vision, Srasota, 1996. 278~283
[32] J.Ojier, R.Mullot, J.Labich, Y.Lecoutier. An image interpretation device can not be reliable without any semantic coherency analysis of the interpretated objects application to French cadastral maps. In: Proceedings of the 4th International conference on document analysis and recognition, Ulm, 1997. 532~535
[33] J.Arias, A. Chhabra, V.Misra. Finding Straight Lines in Drawings. In: Proceedings of the 4th International conference on document analysis and recognition, Ulm, 1997. 788~791
[34] J C Simon. Invariance in pattern recognition:application to line images. Image and vision computing, 1986, 4(1): 11~24
[35] Jiroshi Shinjo, Kazuki Nakashima, Masashi Koga. A method for connecting disappeared junction patterns on frame lines in form documents. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 667~670
[36] Jiqiang Song, Feng Su, Chiew-Lan Tai, Shijie Cal. An objected progressive simplification based vectorization system for engineering drawings: Model, Algorithm and performance. http://citeseer.nj.com/470670.html
[37] Juan F.Arias, Rangachar Kasturi, Atul Chhabra. Efficient techniques for telephone company line drawing interpretation. Proceedings of the third International Conference on Document Analysis and Recognition, Montreal, 1995. 795~798
[38] Juan F. Arias, Atul Chhabra, Vishal Misra. Finding straight, lines in drawings. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 788~791
[39] Karl-hans Blasius, Beate Grawemeyer et.al. knowledge-based document analysis. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 728~731
[40] Karl Tombre. Analysis of Engineering Drawings: State of the Art and Challenges. Proceedings of Second International Workshop on Graphics Recognition, Nancy (France), 1997.54~61
[41] Karl Tombre. Graphics documents: Achievements and open problems, http://citeseer.nj.nec.com/371055.html [OL]
[42] Karl Tombre. Structural and syntactic methods in line drawing analysis: to which extent do they work? Advances in structural and syntactical pattern recognition: 6th international workshop, SSPR'96, Leipsig, 1996. 310~321
[43] Kyong-Ho Lee, Sung-Bae Cho, Yoon-Chui Choy. A Knowledge-based System for Automated Vectorization. Second International Conference on knowledge-Based intelligencet Electronic Systems, Adelaide, 1998. 396~402
[44] Lin Yu Tseng, Rung-Ching Chen. The recognition of Form Documents based on three typeds of line segments. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 71~75
[45] Liu Wenyin, Dov Dori. Genericity in Graphics Recognition Algorithms. http://citeseer.nj.nec.com/liu98genericity.html [OL]. 1997
[46] Liu Wenyin, Dov Dri. From raster to vectors: extracting visual information from line drawings. Pattern Analysis & Application, 1999(2): 10~21
[47] Liu Wenyin, Dov Dri. A protocol for performance evaluation of line detection algorithms. Machine Vision and Applications, 1997(9):240~250
[48] Liu wenyin, Zhang Liang, Tang Long, Dov Dori. Cost evaluation of interactively correcting recognized engineering drawings, http://research.microsoft.com/asia/download/disquisition/16.asp [OL]
[49] L.Du, A.C.Downton, S.M.Lucas, B.AI-Badr. Generalized Contextual recognition of hand-printed documents using semantic trees with lazy evaluation. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 238~242
[50] M Mirmehdi, P.L, Palmer. J.Kittler. Robust Line segment extraction using genetic algorithms. Sixth conference on imageprocessing and its applications, Dublin, 1997. 15~17
[51] Markus Roosli, et al. A high quality vectorization combining local quality measures and global constraints[A]. Proceedings of the third International conference on document analysis and
recognition, Montreal, 1995. 243~248
[52] Marc Vuileumier Stuckelberg, Christian Pellegrini, Melanie Hilario. An architecture for musical score recognition using high-level domain knowledge. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 813~818
[53] Maragos R A Representation Theory for Morphological linage and Signal Processing, IEEE trans. Pattern analysis and machine intelligence, 1989, 11(6): 586~599
[54] Michael Cannon, Judith Hochberg, Patrick Kelly. Quality assessment and restoration of typewritten document images, International journal on Document Analysis and Recognition 1999(2): 80~89
[55] Nagasamy V, Langrana N A, Engineering drawing processing and vectorization system. CVGIP, 49(3), 1990: 19~26
[56] Pascal Vaxiviere, Karl Tombre. CELESSTIN Ⅳ: knowledge-based of mechanical engineering drawings. IEEE transactions on pattern analysis and machine intelligence, 1992. 242~245
[57] Pascal Vaxiviere, Karl Tombre. Knowledge organization and interpretation process in engineering drawing interpretation[OL]. http://citeseer.nj.com/155580.html
[58] Philippe Dosch, Karl Tombre, Christian Ah-Soon, et.al. A complete system for the analysis of architectural drawings. International journal on Document Analysis and Recognition. 2000(3): 102~116
[59] Pierr M. Devaux, Daniel B.Lysak, Rangachar Kasturi. A complete system for the intelligent interpretation of engineering drawings. International journal on Document Analysis and Recognition, 1999(2): 120~131
[60] Rangachar Kasturi, Sing T. Bow, Wassim EL-Masri, Jayesh Shah, James R. Gattiker, Umesh B. Mokate. A system for Interpretation of Line Drawings. IEEE transaction on pattern analysis and machine intelligence, 1990, 12(10): 978~991
[61] Rahul Singh, Nikolaos P. Papanikolopoulos, Vladimir Cherkassky. Object skeletons from sparse shapes in industrial image settings, http://citeseer.nj.nec.com/40383.html [OL]
[62] Robert M. Haralick. Document image understanding: geometric and logical layout. IEEE computer society conference on computer vision and pattern recognition. Seattle, 1994. 385~390
[63] S.Ablameyko, V.Bereishik. Recognizing engineering drawing entities: technology and results. Sixth conference on image processing and its applications, Dublin, 1997. 15~17
[64] S.Ablameyko, V.Bereishik, O.Frantskevich, M.Homenko, N.Paramonova. Recognition of 'thick' closed polygons in engineering drawing images. Part of the IS&SPIE Conference on Document Recognition and Retrieval Ⅶ, San Jose, 2000. 140~146
[65] S.Ablameyko, V.Bereishik, O.Frantskevich, M.Homenko et.al. A system for automatic recognition of engineering drawing entities. Proceedings 4th International Conference on pattern recognition, Brisban(Australia), 1998. 1546~1548
[66] Sergey Ablameyko, Tony Pridimore. Machine Interpretation of Line Drawing images: technical drawings, maps, and diagrams[M].London, New York: Springer. 2001.
[67] Shouqing Zhang, Ling Li, Hock Soon Seah. Recursive algebraic curve fitting and rendering. The Visual Computer; 1998(14):69~82
[68] S.Tanigawa, O.Hori, S.Shimotsuji. Precise Line Detection From an Engineering drawing using a figure fitting method based on contours and skeletons. Proceedings of the 12th IAPR International Conference on Pattern Recognition, Jerusalem, 1994. 356~360
[69] S Ablameyko, V I Bereishik. Recognising engineering drawing entities: technology and results. Sixth International Conference. on Image Processing and its applications, Dublin, 1997. 736~740
[70] S.H.Joseph. Processing of engineering line drawings for automatic input to CAD. Pattern Recognition, 22(1): 1~11
[71] S.H.Joseph. T.P. Pridmore. Knowledge-Directed Interpretation of Mechanical engineering drawings. IEEE transactions on pattern analysis and machine intelligence, 1992, 14(9): 928~940
[72] Shigeyoshi Shimotsuji, Osamu Hori, Satohide Tanigawa. Engineering drawing recognition based on a line decomposition and recomposition method. IEEE transactions on pattern analysis and machine intelligence, 1992. 225~228
[73] Shin'ichi SATOH, Hiroshi MO, Masao SAKAUCHI. Drawing image understanding System with capability of rule learning; Proceedings of the ninth conference on artificial intelligence for applications. Orland (Florida), 1993. 119~124
[74] Showzow TSUJIO, Toshiro ONO, SeoungSoo LEE. Computer-Aided Drawing Check for CAD Systems-A Method for the checking of dimensions in multiview mechanical drawings. IEEE transactions on pattern analysis and machine intelligence, 1992. 234~237
[75] Song Mao, Tapas Kanungo. Software architecture of PEST: a page segmentation evaluation toolkit. International journal on Document Analysis and Recognition 2002(4): 205~217
[76] Stefan Klink, Thomas Kieninger. Rule-based document structure understanding with a fuzzy combination of layout and textual features. International journal on Document Analysis and Recognition, 2001(4): 18~26
[77] Steffen Frischknecht, Enteta Kanani, Alessandro Carosio. A raster-based approach for the automatic interpretation of topographic maps. IAPRS, 32(1),Columbus, 1998. 523~530
[78] Suzanne COLLIN, Dominique COLNET. Syntactic analysis of technical drawing dimensions.
International Jounal of pattern recognition and artificial intelligence, 1994, 8(5):1131~1148
[79] Tang chao, Feng shan, Xu li-da. A geographical information system based on agent architecture. Journal of software, 2001, 12(6): 791~801
[80] Tapas Kanungo, Henry S. Baird, Robert M. Haralick. Special issue on "Performance evaluation: Theory, practice, and impact". International journal on Document Analysis and Recognition, 2002(4): 139
[81] Tapas Kanungo, Robert M Haralick, Dov Dori. Understanding engineering drawings: a Survey. Proceedings of International workshop on graphics recognition[A], Pennsylvania, 1995. 119~130
[82] tapas Kanungo, Robert M. Haralick. Automatic generation of character groundtruth for scanned documents: a closed-loop approach. In proceedings of international conference on pattern recognition, Vienna(Austria), 1996. 669~675
[83] Tabbone S. Cooperation between edges and junctions for edge grouping. Proceedings of 6th international conference on image processing. 1993. 954~957
[84] Uli Bohnacker, Johannes Schacht, Tulug Yucel. Matching Form Lines Based on a Heuristic Search. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 86~90
[85] V.Consorti, L.P.Cordella, V.Eramo, et.al. Knowledge based search of character strings in line drawings. Proceedings of 12th IAPR International conference on Pattern Recognition, Jerusalem, 1994. 589~591
[86] Wang Duoqiang, Li Qinghua, Tian Xuhong. A smoothing algorithm for engineering drawing and its parallel implementation. Proceedings of 4th International conference/exhibition on high performance computing in Asia-Pacific Region, Beijing, 2000. 794~796
[87] Walter G.Kropatsch, Mark Burge. Minimizing the topological structure of line images. http://citeseer.nj.nec.com/285180.html
[88] Wei Wu, Wei Lu, Masao SAKAUCHI. An objected model for drawing understanding and its ability of noise absorption, Proceedings of the third International Conference on Document Analysis and Recognition, Montreal, 1995. 261~264
[89] Wee Kheng Leow, Seet Chong Lua. An improved Neural network for segmenting objects' boundaries in real images. Proceedings of International conference on Neural networks(Ⅲ), Texas, 1997. 1663~1668
[90] Wei lu, Wei Wu, Ma Sakauchi. A drawing recognition system with rule acquisition ability. Proceedings of the third International Conference on Document Analysis and Recognition, Montreal, 1995. 512~515
[91] Yang Li, Marc Lalonde, Eric Reiher, et al. A knowledge based image understanding environment for document processing. Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, 1997. 979~983
[92] Yang Lirui, Ding Runtao. Morphological Filters with Multiple Structuring Elements. International conference on circuits and systems, 1991, 812~815
[93] Yung-sheng chen. Segmentation and association among lines and junctions for a line image. Pattern recognition. 1994, 27(9): 1135~1157
[94] Yong Qing Cheng, Jing Yu Yang. A knowledge based graphic description tool for understanding engineering drawings. Proceedings of the 2nd international IEEE conference on tools for artificial intelligence, Herndon(USA), 1990. 792~796
[95] Kong B, Philips JT, et al. A benchmark: performance, evaluation of dashed-line detection algorithms. In: Kasturi R, Tombre K(eds) Graphics recognition-methods and applications(Lecture notes in Computer Science vol 1072), Springer Berlin Heidelberg. New York. 270~285
[96] Cheng-lin Liu, Hiroshi Sako, Hiromichi Fujisawa. Performance evaluation of pattern classifiers for handwrittern character recognition. International Journal on Document Analysis and Recognition, 2002(4): 191~204
[97] J.Hu, R.S.Kashi, et al. evaluating performance of table processing algorithms. International Journal on Document Analysis and Recognition, 2002(4): 140~153
[98] Richard G.Casey, Eric Lecolinet. A survy of methods and strategies in character segmentation. IEEE transitions of pattern analysis and machine intelligence, 1996, 18(7):690~705
[99] Pascal Vaxivire, Karl Tombre. Subsampling: A structural Approach To Technical Document Vectorization. http://citeseer.nj.nec.com/119047.html[OL]
[100] C.H.Tech, R.T.Chin. On the detection of dominant points on digital curves. IEEE transactions on pattern analysis and machine intelligence. 1989, 11(8):
[101] 蔡良伟,韩大庆。工程图纸中字符的分离和识别。深圳大学学报,1997,14(4):19~23
[102] 蔡新。微机工程图图像自动识别系统的研究,计算机工程,1992,18(5):43~48
[103] 陈勇,朱林,常明.机械周纸中直线圆弧的整体识别算法,计算机辅助设计与图形学学报(增刊),1996,8:225~229.
[104] 陈洪亮,沈琳琳。基于Kohonen神经网络的地图自动输入技术。小型微型计算机系统,2001,22(12):1464~1466
[105] 陈月林,王平江,朱建新,周济。基于曲率的轮廓精确分段技术。华中理工大学学报,1995,23(6):20~23
[106] 陈振宇,程耿东,郭成安。基于图形拓扑特征的工程图整体识别方法。计算机工程与
科学,2000,22(1):
[107] 程锦,陆国栋,谭建荣。基于直线特性的直线生成集成算法。中国图象图形学报,2001,6A(4):392~395
[108] 董海卫,江早,王永军。基于欠量化的二值工程图符号提取算法。计算机辅助设计与图形学学报,2000,12(4):294~298
[109] 董海卫,江早,王永军。统计与结构结合的工程图纸符号识别方法。计算机辅助设计与图形学学报,2000,12(5):375~379
[110] 董洪志,李玉璇等。车身上程图精确矢量化圆的自适应算法。上海交通大学学报,2000,34(10):1453~1456
[111] David Byrne.巡视光栅矢量化软件(上)。工程设计CAD与智能建筑,2000(7):70~71
[112] David Byrne.巡视光栅矢量化软件(下)。工程设计CAD与智能建筑,2000(8):61~64
[113] 樊丽萍,邹荣金。工程图扫描图像中基于连通群的分类与识别算法。工程图学学报,1999,(3):47~54
[114] 方卫宁,梁锡昌.机械图纸的自动处理与识别。机械工程学报,1995,31(1):8~14
[115] 高均海,黄永忠,范爱民。矿图扫描过程中的质量控制研究。矿山测量,2001(3)
[116] 葛永惠.扫描图像细化后像点点位精度研究.中国图像图形学报,2000,5(A)(2):163~166
[117] 葛永惠等。图象匹配的一种度量及其在扫描地形图要素提取中的应用。信息与控制,2000,29(4):366~371
[118] 郭丙炎,周济,朱建新。工程图形扫描图像的自动识别。机械科学与技术,1998,17(5):852~853
[119] 郭丙焱,朱建新,朱林,周济.工程图形扫描输入后的智能识别方法.中国机械工程,1992,3(6):5~7
[120] 郭云,李建蜀,吴松强。扫描输入图象中曲线图形的细化。计算机应用研究,1996,13(3):68~69
[121] 洪晓燕,叶秀清。基于知识的边界提取算法。计算机学报,1995,19(10):798~800
[122] 霍宇翔,丁宇,陈耘,金龙,周兆英.细化畸变节点修正算法的研究.清华大学学报,1997,37(8):76~79
[123] 霍宇翔,丁宇,陈耘,金龙,周兆英.细化畸变节点形态分析及修正策略研究.计算机辅助设计与图形学学报,1997,9(6):500~505
[124] 胡青泥,王晓丽。一种包含隐含图形信息提取的工程图识别算法。计算机辅助设计与图形学学报,2002,14(1):31~35
[125] 胡友兰,常明,田亚梅等。工程阁纸智能识别的分层理解模型。计算机工程,1998,24(12):
50~55
[126] 江早,刘积仁.分割图形粘连字符的图元屏蔽技术研究.中国图像图形学报,1998,3(1):19~24
[127] 江早,刘积仁,刘晋军.工程图纸图象图文自动分割工具 SegChar.软件学报,1999,10(6):589~594
[128] 李宾,谭建荣,彭群生。一个基于扫描串的同一整体矢量化算法。软件学报,1998,9(6):426~431
[129] 李庆华,王多强,陈志勇.图象的矢量化方法与算法研究.计算机应用研究,1995,12(6):9~12
[130] 李蓉,张树生。扫描工程图二维重建中基于图表达的结构约束校正。计算机工程与科学,2001,23(6):22~24
[131] 李蓉,张树生,王明微。尺寸驱动技术中若干技术的分析与研究。工程图学学报,2002(增刊):35~40
[132] 李蓉,张树生。基于人工神经网络的直线图素识别质量判别器。计算机辅助设计与图形学学报,(录用)
[133] 刘刚,刘强。工程图纸矢量化与识别技术在工时定额制定中的应用。工业工程与管理,2002,(3)
[134] 刘彦花,向南平。地图扫描矢量化问题分析。四川测绘,2001,24(3):122~124
[135] 刘彦花,叶国华。基于扫描地形图的几何纠正算法研究。地矿测绘,2001,17(3):1~3
[136] 陆国栋,黄长林,崔培英。工程图样的特点及数据结构。软件世界,1997(2):81~83
[137] 陆国栋,徐惠萍,黄长林.工程图样处理基本模式.软件世界,1997(2):84~86
[138] 陆国栋,李凌丰,程仙平。零件图处理技术。软件世界,1997(2):87~89
[139] 陆国栋,吴中奇,黄长林.基于知识表达的参数化尺寸标注机理研究与实现.计算机学报,1996,19(4):270~276
[140] 陆国栋,阮建中,江涛,彭群生。基于工程图样的三维重建技术研究与实现。计算机辅助设计与图形学学报,1999,11(6):516~520
[141] 陆国栋,晏群,彭群生。面向图形理解的工程图语义研究.中国图象图形学报,2000,5A(10):861~867
[142] 陆国栋,彭群生。基于工程图样语义的基元关系识别研究。计算机辅助设计与图形学学报,2000,12(9):700~704
[143] 陆国栋,彭群生。三维重建新方法及新技术研究。高技术通讯,2001,(3):57~60
[144] 陆国栋,叶金荣,彭群生。基于分治思想的工程图样智能理解方法研究。计算机集成
制造系统—CIMS,2001,7(5):63~67
[145] 陆宗骐,张秋萍.工程图纸矢量化中平均链码与线条轮廓跟踪.模式识别与人工智能,1997,10(2):147~152
[146] 陆宗骐,张秋萍.工程图纸矢量化中的线条轮廓跟踪法.中国图象图形学报,1997,2(12):878~882
[147] 李伟青,谭建荣,彭群生.基于图段结构的整体识别方法的研究.计算机学报.1998,21(8):751~758
[148] 李新友,唐泽圣.清华图纸自动输入及管理系统.软件学报,1996,7(2):90~99
[149] 李新友,唐泽圣,张凤昌,黄汉文.TH-DAIMS3.0清华图纸自动输入及管理系统.计算机辅助设计与图形学学报,1997,9(5):450~456
[150] 李佐,王姝华,蔡士杰。一种基于前端预测识别的粘连字符分割方法。计算机研究与发展,2001,38(11):1337~1344
[151] 卢朝阳,应道宁,王尔健。图文自动分离的方法研究。工程图学学报,1994,(2):37~44
[152] 刘晓平,王浩,张佑生等。CAD系统中工程剖视图的算法研究。计算机辅助设计与图形学学报,2000,12(11):839~841
[153] 刘云华,陈立平,钟毅芳。工程图形几何特性符号描述及子模式分解。工程图学学报,2000,(2):83~89
[154] 刘学,张助勋,张剑清等。大比例地形图中房屋目标的自动识别。计算机学报,1998,21(11):1027~1032
[155] 刘文印,唐龙,唐泽圣等。一种在矢量基础上进行图形识别的通用方法。软件学报,1997,(5):376~383
[156] 刘志敏,施鹏飞。基于形心同心圆结构的自由手写体数字神经网络分类器。计算机学报,1997,20(9):799~805
[157] 刘钟,张树生,张铁昌.工程图自动转换及识别技术研究.机械工业自动化,1996,18(3):15~17
[158] 林晓帆,丁晓青,吴佑寿。基于置信度分析和多信息融合的高性能手写数字识别。http://ocrserv.ee.tsinghua.edu.cn/~lxf/ccns.doc[OL].2003
[159] 卢满堂,许运良。地图分幅扫描及其矢量图形的拼接。三晋测绘。2000(4):35~37
[160] 孟莉,赵宏,工程图纸的光栅矢量混合编辑技术.微型计算机,1996,16(1):65~66
[161] 孟祥武,李文芳,孙吉清,廖木星。传真天气图的计算机接收识别技术。中国航海,2000(1):16~21
[162] 庞止华,刘秀军。数字筛去除二值图像中斑点的方法。晋中师范高等专科学校学报,2002.19(1)
[163] 彭京亮。一种快速的扫描铅笔稿图细化算法。中国图象图形学报,2000,5(A)(5):434~439
[164] 秦志强,程娣等。矢量化技术在勘探开发中的应用。断块油气田。2002,9(2)
[165] 任金昌,赵荣椿,刘哲。图纸矢量化中的线弧分离与识别。计算机应用,2001,21(1):35~37
[166] 阮建中,陆国栋,周瑞斌。图形处理实用技术剖析.软件世界,1997(2):84~86
[167] 沈立,张晨曦。黑白图像的矢量化。计算机辅助设计与图形学学报,2000,12(3):170~173
[168] 宋继强,苏丰,蔡士杰。基于种子段的方向无关的直线矢量化方法。软件学报,2000,11(9):1196~1201
[169] 苏丰,宋继强等。工程图纸矢量化软件VHVector用户接口的设计与实现。计算机学报,2001,24(9):930~937
[170] 宋晓宇,王永会.工程图自动矢量化算法的设计与实现.中国图像图形学报,2000,5(A)(1):66~69
[171] 谭栢珠,叶邦彦,陈澄洲.基于知识的窗口矢量化技术.计算机辅助设计与图形学学报,2000,12(2):105~109
[172] 谭建荣,彭群生.基于图形约束的工程图扫描图象直线整体识别方法.计算机学报,1994,17(8):561~569
[173] 唐龙,唐泽圣.图形自动输入与理解技术的研究现状.计算机世界,1990(12):66
[174] 田玉敏,刘国景。光栅图形矢量化方法分析与评价。计算机应用研究,2002,(3):6~8
[175] 王德英,李新友,唐泽圣等。图纸图像上线条的交互拾取。计算机学报,1997,20(10):925~932
[176] 王多强,李庆华.工程图纸识别中的模式分离方法研究.计算机辅助设计与图形学学报(增刊),1996,8:232~236
[177] 王耘,刘衍聪,应道宁.工程图纸的识别与理解——问题与思考.中国机械工程,1997,8(1):80~83
[178] 王建华,童秉枢.工程图形的自动跟踪算法.微型计算机应用,1993,14(1):31~33
[179] 王建华,刘红梅,关启明,机械工程图纸的自动处理与识别系统的研究.微计算机应用,1996,17(5):42~46
[180] 王建华,童秉枢.工程图形的两种快速细化方法.计算机研究与发展,1998,35(2):161~163
[181] 王健,张树生,王广。基于节点的线状图骨架提取算法研究。计算机研究与发展,1999,
36(6):725~731
[182] 王金鹤,欧宗瑛,夏晓东.工程扫描图象的直线整体识别算法.中国图像图形学报,1998,3(11):912~917
[183] 王金鹤,欧宗瑛,夏晓东.扫描图像的圆弧的定位识别算法.中国图像图形学报,1999,4(A)(6):497~501
[184] 王加阳,王灿东。自动跟踪地图数字化。小型微型计算机系统,2000,21(8):829~832
[185] 王明哲,林和,肖明。图库中光栅与欠量化技术的应用研究。甘肃科学学报,2000,12(3):49~53
[186] 王晓丽,胡青泥。基于特征分析的工程图智能识别算法。计算机工程,2001,27(3):119~121
[187] 武仲科,焦海星,戴国忠.一种线段和圆弧的逼近方法及其在工程图纸矢量化中的应用.计算机辅助设计与图形学学报,1998,10(4):328~332
[188] 王钲旋,李志林,庞云阶。一个二值图像连通成分标记的快速算法。工程图学学报,1998,(3):80~86
[189] 熊沈蜀,周兆英。基于非线性时序模型的神经网络图形识别方法。自动化学报,1999,25(4):467~475
[190] 熊沈蜀,周兆英,金龙等。工程图矢量化处理系统。清华大学学报,2000,40(4):35~38
[191] 徐尧东,张忠苗,岑岗。工程图扫描输入与识别技术。计算机辅助工程,1997,6(4):44~51
[192] 徐晓钢,于金辉,马利庄。复杂物体轮廓提取。中国图象图形学报,2001,6A(5):455~459
[193] 杨承磊,孟祥旭,李学庆,龚斌,屠长河.基于无向图的图像整体骨架表示模型及其算法,计算机学报,2000,23(3):293~299
[194] 杨立瑞,周济.基于轮廓形状分析的图素识别方法研究.华中理工大学学报,1996,24(4):27~29
[195] 杨健,杨静宇,金忠。最优鉴别特征的抽取及图像识别。计算机研究与发展,2001,38(11):1331~1336
[196] 杨军。如何提高地图扫描矢量化软件成图精度的分析与探讨。北京测绘,2000(2):17~19
[197] 杨薇薇,陈志冲。工程图纸并行矢量化算法的研究。华中理工大学学报,1998,26(11):16~18
[198] 杨晓。工程图形的计算机处理算法与实现。微型机与应用,1998,17(4):40~42
[199] 杨哲海,刘健。基于规则格网数据的区域边界矢量化算法。测绘学院学报,2000,17(1):67~69
[200] 颜学阶,常明,朱林.基于线性轮廓匹配的工程图识别算法研究.华中理工大学学报,
1997,25(3):34~37
[201] 易辉伟,江资斌等。地形图矢量化的后处理。中国有色金属学报,2002,12(4):808~811
[202] 于学军,彭立中。二值图象曲线轮廓提取的新算法。中国图象图形学报,2002,7A(3):272~275
[203] 袁春凤,周根林,画面自动识别技术初探。计算机研究与发展,1990,27(8):9~26
[204] 赵升。二值图像或文字的并行预处理方法(上)。电脑开发与应用,1994,7(4):6~10
[205] 赵升。二值图像或文字的并行预处理方法(下)。电脑开发与应用,1994,7(5):5~7
[206] 张海军,周济,张新访等。工程图解释技术现状与展望。计算机应用,1995,15(3):32~34
[207] 张树生,杨彭基。机械工程图扫描图像/CAD图形的智能变换研究。中国机械工程,1994,5(4):7~9
[208] 张树生,杨彭基。机械工程图的智能输入与识别研究。西北工业大学学报,1995,13(2):217~221
[209] 张树生。一种基于线的标号传播二值图象连通体快速检测方法。计算机研究与发展,1994,31(10):51~54
[210] 张树生,Bruno TACONET。一种适于多网格结构的快速细化算法。计算机学报,1994,17(8):634~638
[211] 张树生,杨彭基。机械工程图扫描图像/CAD图形的智能变换研究。中国机械工程,1994,5(4):
[212] 张习文,欧宗英。基于单义域邻接图的工程图纸扫描图像的字符提取。工程图学学报,2000,(2):90~95
[213] 张习文,欧宗瑛。基于单义域邻接图的圆弧与圆识别。中国图象图形学报,2000,5(A)(1):70~74
[214] 张习文,欧宗英。描述工程图纸扫描图像的单义域邻接图的构建方法。计算机工程与应用,2000,36,(8):62~65
[215] 张习文,欧宗英。工程图纸扫描图象的线段完整识别算法。计算机工程,2000,26(8):83~84
[216] 张习文,蔡士杰,欧宗英。基于矢量邻接图的剖面域识别与重建研究。工程图学学报,2001,(4):7~12
[217] 张习文,欧宗英。机械图纸扫描图像尺寸信息提取。机械科学与技术,2001,20(2):7~12
[218] 张习文,李佐,蔡士杰,欧宗英。基于遗传算法的以线段和圆弧为基元的曲线拟合。计算机辅助设计与图形学学报,2002,14(2):144~147
[219] 张志鸿,童秉枢.工程图形识别中一种矢量跟踪法.清华大学学报,1996,36(3)84~89
[220] 章孝灿,潘云鹤。GIS中基于“删格技术”的删格数据矢量化技术。计算机辅助设计与图形学学报,2001,13(10):895~900
[221] 钟晓钢,李新友,唐泽圣.工程图的子连通域表示及其应用。计算机工程与应用,1999,35(11):1~4
[222] 朱建新.扫描工程图的轮廓矢量提取.工程图学学报,1997(2~3):46~51
[223] 朱学芳,石青云,程明德.一种自适应细化方法.模式识别与人工智能,1997,10(2):140~146
[224] 周激流,张晔,郭晶等。基于先验模板的人脸面部特征提取的研究。计算机辅助设计与图形学学报,2000,12(5):337~339
[225] 周乳良,张军,张洪亮。卫星图像的解译误差与提高精度的方法。云南地理环境研究,2000,12(2):21~24
[226] 邹荣金,陈冀兵,苏丰,蔡士杰,张福炎.工程图纸识别与智能化光栅矢量编辑系统.计算机工程与应用,1999,35(4):24~26
[227] 邹荣金,陈冀兵,苏丰,蔡士杰,张福炎.基于特征段的正交矢量化及其符号识别方法.计算机研究与发展,1999,36(1):85~90
[228] 邹荣金,蔡士杰,张福炎,苏丰,陈冀兵.字符粘连及字线相交的分割与识别方法.软件学报,1999,10(3):241~247
[229] 邹荣金,蔡士杰,张福炎.图纸矢量化中多向字符的分割.中文信息学报,1998,12(4):9~14
[230] 陈立平,向文等.基于实例图形的几何约束满足策略.计算机辅助设计与图形学学报,1996.8(5):381~386
[231] 董金祥,葛建新等.变参绘图系统中的约束求解的新思路.计算机辅助设计与图形学学报,1997,9(6):513~519
[232] 葛建新,董金祥,何志均.ZD-SKETCHER:基于草图的变参设计绘图系统.计算机辅助设计与图形学学报,1994.6(3):207~214
[233] 辜凯宁,唐泽圣,孙家广.从三视图重建三维形体技术的研究,计算机学报,1986,9(6):401~409
[234] 黄晓建,张申生,王忠辉.超二维环境下尺寸驱动和参数化设计研究.计算机辅助设计与图形学学报,1997,9(4):349~355
[235] 兰箭,张荣成等。基于图的参数化设计方法。计算机辅助设计与图形学学报,1997,9(4):356~360
[236] 林峰,颜永年,卢清萍,童永光.基于图形数据的图形参数化方法,计算机辅助设计与图形学学报,1993,5(3):184~190
[237] 陆国栋,吴中奇.关于多通道多变量图形的参数化研究.计算机学报,1994,17(11):872~877
[238] 罗浩,陈立平,周济.基于规则的集合约束推理的研究.计算机辅助设计与图形学学报,1997,9(3):256~263
[239] 孟祥旭,汪嘉业,刘慎权.基于有向超图的参数化表示模型及其实现.计算机学报,1997,20(11):982~988
[240] 张东亮,谭建荣等.基于尺寸约束离线形成的参数化驱动方法.计算机学报,1996,19(12):916~922
[241] 陈文云。扫攒工程图拓扑关系识别与参数化重构:[硕士学位论文]。西安:西北工业大学,1998
[242] 董复光。扫描机械工程图中剖面线、点划线、虚线的自动识别技术研究:[硕士学位论文]。西安:西北工业大学,1999
[243] 刘晓翔。工程图纸光栅矢量混合编辑技术研究与实现:[硕士学位论文]。西安:西北工业大学,2000
[244] 王健。基于截序图的扫描工程图骨架提取方法研究:[硕士学位论文]。西安:西北工业大学,1997
[245] 刘钟。扫描工程图的精确重建及特征识别研究:[博士学位论文]。西安:西北工业大学,1997
[246] 王宗彦。扫描机械工程图的精确参数化三维重构研究:[博士学位论文]。西安:西北工业大学,2000
[247] 谭建荣。工程图纸扫描图像的整体识别及图形重建的研究:[博士学位论文]。杭州:浙江大学,1992
[248] 李伟青。基于整体识别的工程图纸扫描转换系统研究:[博士学位论文]。杭州:浙江大学,1996
[249] 高玮。基于二维视图特征的三维重建及多视图参数化技术的研究:[博士学位论文],杭州:浙江大学,1996
[250] 陆国栋。基于工程语义的三维重建方法研究:[博士学位论文]。杭州:浙江大学,2000
[251] 邹荣金。工程图纸矢量化与识别技术研究:[博士学位论文]。南京:南京大学,1999
[252] 陈振宇。基于圈形整体拓扑特征的工程图纸扫描图像自动识别输入方法的研究:[博士学位论文]。大连:大连理工大学,1998
[253] 徐建锵。基于知识的机械图纸识别与理解方法的研究:[博士学位论文]。哈尔滨:哈
尔滨工业大学,1994
[254] 冯秀娟。计算机绘图的工程应用技术研究:[博士学位论文]。北京:北京航空航天大学,1994
[255] 朱建新。基于轮廓匹配和拓扑信息的工程图识别原理及系统实现:[博士学位论文]。武汉:华中理工大学,1998
[256] 谭栢珠。工程图解释中关键技术的研究:[博士学位论文]。广州:华南理工大学,
[257] 李宾。基于认知模型的工程图层次矢量化算法研究:[博士学位论文]。浙江:浙江大学,1998
[258] 孙家广等。计算机图形学。北京:清华大学出版社,1996
[259] 马颂德,张正友。计算机视觉—计算理论与算法基础.北京:科学出版社,1998
[260] 唐荣锡。CAD/CAM技术。北京:北京航空航天出版社,1994
[261] 章毓晋。图象工程。北京:清华大学出版社,1999
[262] 边肇祺,张学工。模式识别。北京:清华大学出版社,2000
[263] 蔡青,高光焘。CAD/CAM系统的可视化,集成化,智能化,网络化。西安:西北工业大学出版社,1996
[264] 何华灿。人工智能导论。西安:两北工业大学出版社,1988
[265] 李孝安等。神经网络与神经计算机导论。西安:西北工业大学出版社,1995
[266] [美国]D.马尔,姚国政,刘磊,汪云九译。视觉计算理论。北京:科学出版社,1988
[267] 严蔚敏,吴伟民。数据结构。北京:清华大学出版社,1992
[268] 大连工学院工程画教研室。机械制图。北京:高等教育出版社,1974
[269] [美国]Michael J.Young,邱仲潘译。Visual C++4从入门到精通。北京:电子工业出版社,1997
[270] [美国]J. P. Marques de Sa,吴逸飞译 模式识别—原理、方法及应用.北京:清华大学出版社,2002
[271] 施鸿宝,王秋荷。专家系统。西安:西安交通大学出版社,1990
[272] 刘勇奎。计算机图形学的基础算法。北京:科学出版社,2001
[273] 陆国栋,张树有。工程图样数字化转换与智能理解。北京:机械工业出版社,2001
[274] VPStudio, Vpmax pro矢量化软件说明书,Softelec公司
[275] 刘普寅,吴孟达。模糊理论及其应用。长沙:国防科技大学出版社,1998
[276] 童俯,沈一栋。知识工程。北京:科学出版社,1992
[277] [美国]Abhijit Spandya,徐勇,荆涛译 神经网络模式识别及其实现。北京:电子工业出版社,1999