This book presents refereed and revised papers presented at GREC 2001, the 4th IAPR International Workshop on Graphics Recognition, which took place in Kingston, Ontario, Canada in September 2001. Graphics recognition is a branch of document image analysis that focuses on the recognition of two-dimensional notations such as engineering drawings, maps, mathematical notation, music notation, tables, and chemical structure diagrams. Due to the growing demand for both o?-line and on-line document recognition systems, the ?eld of graphics recognition has an excitingand promisingfuture. The GREC workshops provide an opportunity for researchers at all levels of experience to share insights into graphics recognition methods. The workshops enjoy strongparticipation from researchers in both industry and academia. They are sponsored by IAPR TC-10, the Technical Committee on Graphics Recog- tion within the International Association for Pattern Recognition. Edited v- umes from the previous three workshops in this series are available as Lecture Notes in Computer Science, Vols. 1072, 1389, and 1941. After the GREC 2001 workshop, authors were invited to submit enhanced versions of their papers for review. Every paper was evaluated by three reviewers. We are grateful to both authors and reviewers for their careful work during this review process. Many of the papers that appear in this volume were thoroughly revised and improved, in response to reviewers’ suggestions.

This book presents refereed and revised papers presented at GREC 2001, the 4th IAPR International Workshop on Graphics Recognition, which took place in Kingston, Ontario, Canada in September 2001. Graphics recognition is a branch of document image analysis that focuses on the recognition of two-dimensional notations such as engineering drawings, maps, mathematical notation, music notation, tables, and chemical structure diagrams. Due to the growing demand for both o?-line and on-line document recognition systems, the ?eld of graphics recognition has an excitingand promisingfuture. The GREC workshops provide an opportunity for researchers at all levels of experience to share insights into graphics recognition methods. The workshops enjoy strongparticipation from researchers in both industry and academia. They are sponsored by IAPR TC-10, the Technical Committee on Graphics Recog- tion within the International Association for Pattern Recognition. Edited v- umes from the previous three workshops in this series are available as Lecture Notes in Computer Science, Vols. 1072, 1389, and 1941. After the GREC 2001 workshop, authors were invited to submit enhanced versions of their papers for review. Every paper was evaluated by three reviewers. We are grateful to both authors and reviewers for their careful work during this review process. Many of the papers that appear in this volume were thoroughly revised and improved, in response to reviewers’ suggestions.

Data Structures, Computer Graphics, and Pattern Recognition focuses on the computer graphics and pattern recognition applications of data structures methodology. This book presents design related principles and research aspects of the computer graphics, system design, data management, and pattern recognition tasks. The topics include the data structure design, concise structuring of geometric data for computer aided design, and data structures for pattern recognition algorithms. The survey of data structures for computer graphics systems, application of relational data structures in computer graphics, and observations on linguistics for scene analysis are also elaborated. This text likewise covers the design of satellite graphics systems, interactive image segmentation, surface representation for computer aided design, and error-correcting parsing for syntactic pattern recognition. This publication is valuable to practitioners in data structures, particularly those who are applying real computer systems to problems involving image, speech, and medical data.

This book constitutes the strictly refereed post-workshop proceedings of the Second International Workshop on Graphics Recognition, GREC'97, held in Nancy, France, in August 1997. The 34 thoroughly revised full papers presented were carefully selected for inclusion in the book on the basis of a second round of post-workshop reviewing. The book is divided into sections on vectorization and segmentation, symbol recognition, form processing, map processing, engineering drawings, applications and systems, performance evaluation, and a graphics recognition contest.

1 Thisbookcontainsrefereedandimprovedpaperspresentedatthe5thIAPR - ternational Workshop on Graphics Recognition (GREC 2003). GREC 2003 was held in the Computer Vision Center, in Barcelona (Spain) during July 30–31, 2003. TheGRECworkshopisthemainactivityoftheIAPR-TC10,theTechnical 2 Committee on Graphics Recognition . Edited volumes from the previous wo- shops in the series are available as Lecture Notes in Computer Science: LNCS Volume 1072 (GREC 1995 at Penn State University, USA), LNCS Volume 1389 (GREC 1997 in Nancy, France), LNCS Volume 1941 (GREC 1999 in Jaipur, India), and LNCS Volume 2390 (GREC 2001 in Kingston, Canada). Graphics recognition is a particular ?eld in the domain of document ana- sis that combines pattern recognition and image processing techniques for the analysis of any kind of graphical information in documents, either from paper or electronic formats. Topics of interest for the graphics recognition community are: vectorization; symbol recognition; analysis of graphic documents with - agrammatic notation like electrical diagrams, architectural plans, engineering drawings, musical scores, maps, etc. ; graphics-based information retrieval; p- formance evaluation in graphics recognition; and systems for graphics recog- tion. Inadditiontotheclassicobjectives,inrecentyearsgraphicsrecognitionhas faced up to new and promising perspectives, some of them in conjunction with other, a?ne scienti?c communities. Examples of that are sketchy interfaces and on-line graphics recognition in the framework of human computer interaction, or query by graphic content for retrieval and browsing in large-format graphic d- uments, digital libraries and Web applications. Thus, the combination of classic challenges with new research interests gives the graphics recognition ?eld an active scienti?c community, with a promising future.

This edited volume contains refereed and improved versions of select papers 1 that were presented at the third IAPR Workshop on Graphics Recognition (GREC’99), held at Rambagh Palace in Jaipur, India, 26–27, September 1999. The workshop was organized by the TC10 (Technical Committee on Graphics Recognition) of the IAPR. Edited volumes from the previous two workshops in this series are also available as Lecture Notes in Computer Science (volumes 1072 and 1389). Graphics recognition is the study of techniques for computer interpretation of images of line drawings and symbols. This includes methods such as vectori- tion, symbol recognition, and table and chart recognition for applications such as engineering drawings, schematics, logic drawings, maps, diagrams, and musical scores. Some recently developed techniques include graphics-based information or drawing retrieval and recognition of online graphical strokes. With the recent advances in the ?eld, there is now a need to develop benchmarks for evaluating and comparing algorithms and systems. Graphics recognition is a growing ?eld of interest in the broader document image recognition community. The GREC’99 workshop was attended by ?fty-?ve people from ?fteen co- tries. The workshop program consisted of six technical sessions. Each session began with a half-hour invited talk which was followed by several short talks. Each session closed with a half-hour panel discussion where the authors ?elded questions from the other participants. Several interesting new research directions were discussed at the workshop.

This edited volume addresses a subject which has been discussed inten sively in the computer vision community for several years. Performance characterization and evaluation of computer vision algorithms are of key importance, particularly with respect to the configuration of reliable and ro bust computer vision systems as well as the dissemination of reconfigurable systems in novel application domains. Although a plethora of literature on this subject is available for certain' areas of computer vision, the re search community still faces a lack of a well-grounded, generally accepted, and--eventually-standardized methods. The range of fundamental problems encoIl!passes the value of synthetic images in experimental computer vision, the selection of a representative set of real images related to specific domains and tasks, the definition of ground truth given different tasks and applications, the design of experimental test beds, the analysis of algorithms with respect to general characteristics such as complexity, resource consumption, convergence, stability, or range of admissible input data, the definition and analysis of performance measures for classes of algorithms, the role of statistics-based performance measures, the generation of data sheets with performance measures of algorithms sup porting the system engineer in his configuration problem, and the validity of model assumptions for specific applications of computer vision.