Graphics Recognition 

Abstract: In this paper, we propose a system for the recognition and the automatic learning of hand-drawn graphic symbols in engineering drawings. The graphic symbols and the drawings are represented by attributed relational graphs. The recognition process is formulated as a search process for error-tolerant subgraph isomorphisms from the symbol graphs to the drawing graph. In the beginning, there is a limited set of graphic symbols that are known to the system. The learning algorithm is able to identify new, i.e. unknown, symbols. From the set of all unknown symbols, representative candidates are selected and integrated into the database of known models. The system has been completely implemented and succesfully tested on a number of hand-drawn input pictures.

Abstract: There is a host of open issues in the graphics recognition research area, and there is no doubt as to the viability and growing importance of the field. Contribution has already been made in specialized areas, for instance, for telephone and power companies which hold huge numbers of drawings with the same syntax and appearance, making the development of a specialized system for processing them cost effective. Image and graphical document databases are two multimedia-enabling technologies that seem to be heavy consumers of graphic based operations such as graphical queries. Likewise, the bi-directionality of exchanging information stored on paper and electronic media will make increasing use of graphic recognition capabilities. Overall, a technology that was originally motivated by the pressing need to convert paper documents containing graphics into electronic formats is becoming more and more useful in a variety of information technology domains never before thought of. Once the technology becomes mature enough, one can envision a team of humans working with robots, where both humans and robots read the same graphical document (displayed on any media) and coordinate their tasks based on understanding the same document.

Abstract: Tables are the only acceptable means of communicating certain types of structured data. A precise definition of "tabularity" remains elusive because some bureaucratic forms, multicolumn text layouts, and schematic drawings share many characteristics of tables. There are significant differences between typeset tables, electronic files designed for display of tables, and tables in symbolic form intended for information retrieval. Although most research to date has addressed the extraction of low-level geometric information from scanned raster images of paper tables, the recent trend toward the analysis of tables in electronic form may pave the way to a higherl evel of table understanding. Recent research on table composition and table analysis has improved ourunde rstanding of the distinction between the logical and physical structures of tables, and has led to improved formalisms for modeling tables. The present study indicates that progress on half-a-dozen specific research issues would open the door to using existing paper and electronic tables for database update, tabular browsing, structured information retrieval through graphical and audio interfaces, multimedia table editing, and platform-independent display. Although tables are not a conventional format for conveying the primary content of technical papers, here we attempt to subdue our natural garrulity by adopting this genre to communicate what we have to say about tables entirely in tabular form.

Abstract: This paper presents analyses of different methods of post-processing lines that have resulted from the raster-to-vector conversion of black and white line drawing. Special attention was paid to the borders of connected components of maps. These methods are implemented with compression and smoothing algorithms. Smoothing algorithms can enhance accuracy, so using both smoothing and compression algorithms in succession gives a more accurate result than using only a compression algorithm. The paper also shows that a map in vector format may require more memory than a map in raster format. The Appendix contains a detailed description of the new smoothing method (continuous local weighted averaging) suggested by the authors.